WO2021057752A1 - 图像选优方法及电子设备 - Google Patents

图像选优方法及电子设备 Download PDF

Info

Publication number
WO2021057752A1
WO2021057752A1 PCT/CN2020/116963 CN2020116963W WO2021057752A1 WO 2021057752 A1 WO2021057752 A1 WO 2021057752A1 CN 2020116963 W CN2020116963 W CN 2020116963W WO 2021057752 A1 WO2021057752 A1 WO 2021057752A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
electronic device
decision model
images
feature
Prior art date
Application number
PCT/CN2020/116963
Other languages
English (en)
French (fr)
Inventor
陈艳花
刘宏马
张雅琪
张超
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to US17/764,391 priority Critical patent/US20220343648A1/en
Publication of WO2021057752A1 publication Critical patent/WO2021057752A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/617—Upgrading or updating of programs or applications for camera control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/765—Interface circuits between an apparatus for recording and another apparatus
    • H04N5/77—Interface circuits between an apparatus for recording and another apparatus between a recording apparatus and a television camera
    • H04N5/772—Interface circuits between an apparatus for recording and another apparatus between a recording apparatus and a television camera the recording apparatus and the television camera being placed in the same enclosure
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01B—SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL
    • A01B63/00—Lifting or adjusting devices or arrangements for agricultural machines or implements
    • A01B63/14—Lifting or adjusting devices or arrangements for agricultural machines or implements for implements drawn by animals or tractors
    • A01B63/24—Tools or tool-holders adjustable relatively to the frame
    • A01B63/26—Tools or tool-holders adjustable relatively to the frame by man-power
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G06V10/17—Image acquisition using hand-held instruments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/778—Active pattern-learning, e.g. online learning of image or video features
    • G06V10/7784—Active pattern-learning, e.g. online learning of image or video features based on feedback from supervisors
    • G06V10/7788—Active pattern-learning, e.g. online learning of image or video features based on feedback from supervisors the supervisor being a human, e.g. interactive learning with a human teacher
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/94—Hardware or software architectures specially adapted for image or video understanding
    • G06V10/945—User interactive design; Environments; Toolboxes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174—Facial expression recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/0035—User-machine interface; Control console
    • H04N1/00405—Output means
    • H04N1/00408—Display of information to the user, e.g. menus
    • H04N1/0044—Display of information to the user, e.g. menus for image preview or review, e.g. to help the user position a sheet
    • H04N1/00442—Simultaneous viewing of a plurality of images, e.g. using a mosaic display arrangement of thumbnails
    • H04N1/00453—Simultaneous viewing of a plurality of images, e.g. using a mosaic display arrangement of thumbnails arranged in a two dimensional array
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/0035—User-machine interface; Control console
    • H04N1/00405—Output means
    • H04N1/00408—Display of information to the user, e.g. menus
    • H04N1/0044—Display of information to the user, e.g. menus for image preview or review, e.g. to help the user position a sheet
    • H04N1/00458—Sequential viewing of a plurality of images, e.g. browsing or scrolling
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/0035—User-machine interface; Control console
    • H04N1/00405—Output means
    • H04N1/00408—Display of information to the user, e.g. menus
    • H04N1/0044—Display of information to the user, e.g. menus for image preview or review, e.g. to help the user position a sheet
    • H04N1/00461—Display of information to the user, e.g. menus for image preview or review, e.g. to help the user position a sheet marking or otherwise tagging one or more displayed image, e.g. for selective reproduction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/21—Intermediate information storage
    • H04N1/2104—Intermediate information storage for one or a few pictures
    • H04N1/2112—Intermediate information storage for one or a few pictures using still video cameras
    • H04N1/215—Recording a sequence of still pictures, e.g. burst mode
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/63—Control of cameras or camera modules by using electronic viewfinders
    • H04N23/631—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/63—Control of cameras or camera modules by using electronic viewfinders
    • H04N23/633—Control of cameras or camera modules by using electronic viewfinders for displaying additional information relating to control or operation of the camera
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
    • G06F3/04817—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
    • G06F3/0482—Interaction with lists of selectable items, e.g. menus
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N2101/00—Still video cameras
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N2201/00—Indexing scheme relating to scanning, transmission or reproduction of documents or the like, and to details thereof
    • H04N2201/0077—Types of the still picture apparatus
    • H04N2201/0084—Digital still camera

Definitions

  • This application relates to the field of terminal technology, and in particular to an image selection method and electronic equipment.
  • Continuous shooting is a shooting function that continuously shoots multiple images in a short period of time and stores the captured images in the cache.
  • more and more electronic devices such as smart phones, tablet computers, etc.
  • the electronic device can select the optimal image from the multiple images obtained by continuous shooting according to the parameters such as the sharpness of the captured image, the composition, and the expression of the person image, and display it as the preferred image.
  • the preferred image displayed by the electronic device is often not the user's favorite image among the multiple images obtained by continuous shooting.
  • the user needs to reselect a preferred image from a plurality of images, thereby reducing convenience.
  • This application provides an image selection method and electronic device.
  • the electronic device can update the decision model according to the feedback information related to the user operation, and perform image selection according to the updated decision model, and the selected preferred image is more in line with the user's habits, thereby Can improve convenience.
  • the present application provides an image selection method, the method includes: an electronic device detects first feedback information, the first feedback information includes multiple images and user operations acting on the images in the multiple images; The electronic device adjusts the parameters of the decision model according to the first feedback information to obtain an updated decision model; the electronic device selects the first image from the first image group as the first image group according to the updated decision model Preferred image.
  • the electronic device can adjust the parameters in the decision model for selecting a preferred image from a plurality of images according to user operations.
  • the preferred image selected by the updated decision model is more in line with the user's habits, reducing the user's manual reselection from multiple images, thereby improving convenience.
  • the first feedback information may include: (1) the preferred image selected by the decision model and the modified preferred image. (2) Images that have been deleted, browsed, favorited and shared. (3) The proportion of facial features in the gallery and images containing facial features in the gallery.
  • the method further includes: the electronic device displays a first user interface, the first user interface includes a second image group, and the second image group is an image obtained by continuous shooting, The second image group includes a second image and a third image, and the second image is a preferred image of the second image group selected by the electronic device according to the decision model; the electronic device detects the first feedback information, including: The electronic device detects a first user operation on the first user interface, and in response to the first user operation, the electronic device modifies the preferred image of the second image group to the third image; the first feedback information includes the second image A user operation, the second image, and the third image.
  • the electronic device may detect that the preferred image selected by the decision model contains the "smile” image feature, and the modified preferred image contains the "big laugh” image feature. Then the electronic device adjusts the weight of the "big laugh” image feature in the decision model to be larger, and adjusts the weight of the "smile” image feature to be smaller.
  • the electronic device can select an image that contains the image feature of "laughing".
  • the electronic device can detect that the preferred image selected by the decision model contains the image features of the diagonal composition, and the modified preferred image contains the image features of the central composition. Then the electronic device adjusts the weight of the image feature of the central composition in the decision model to be larger, and adjusts the weight of the image feature of the diagonal composition to be smaller.
  • the electronic device can select an image that contains the image characteristics of the central composition.
  • the first user interface may be a continuous shooting image interface
  • the continuous shooting image interface may include images obtained by continuous shooting.
  • the first user operation may include a touch operation acting on a selected mark on the second image, a touch sliding operation acting on an image display area, a touch operation acting on an unselected mark on the third image, and a user operation acting on a certain control.
  • the electronic device modifies the preferred image of the images obtained by continuous shooting to the third image.
  • the preferred image before modification may be referred to as the second image
  • the preferred image after modification may be referred to as the third image.
  • the images obtained by continuous shooting may be obtained by the electronic device in response to a long-press operation on the shooting control on the camera application interface.
  • the electronic device can respond to the touch operation on the thumbnail control on the continuous shooting image interface to display the images obtained by the continuous shooting.
  • the electronic device may display a prompt interface to prompt the user to adjust the decision model according to the feedback information. For example, you can prompt: "We have received your modification feedback, and we will recommend photos that are more in line with your preferences based on the modification.”
  • the first feedback information includes an operation record of an image in the gallery and an image corresponding to the operation record, and the operation record indicates one or more of the following operations: delete operation, browse operation , Collection operation and sharing operation.
  • the deleted, browsed, favorited, and shared images can be deleted, browsed, favorited, and shared images in the gallery, and can also be deleted, browsed, and shared images in other applications such as instant messaging applications (WeChat). Favorite and share images.
  • Feedback information can also include images that have been edited, printed, remarks, and reminders.
  • the edited image includes, for example, an image whose parameters such as color and brightness are adjusted.
  • the image to be printed may be an image that the electronic device requests the printer to print.
  • the annotated image may be, for example, an image that is annotated on the user interface.
  • the reminded image is set on the user interface, for example.
  • the electronic device can periodically (for example, every 24 hours) record the number of deletions, the number of browsing, and the number of collections and sharing of images in the gallery.
  • the electronic device can respectively set corresponding tag values for deletion, browsing, collection, and sharing. After that, the electronic device can identify the shooting scene of the operated image, and adjust the weight of the corresponding image feature according to the operated image and the corresponding label value of the image.
  • the first feedback information includes the first facial feature and the proportion of the image containing the first facial feature in the gallery; wherein: the first facial feature is the The gallery contains the facial features with the largest number of images, and the gallery contains the images stored in the electronic device.
  • the face feature a indicates the face image of Lisa
  • the face image B indicates the face image of Rechel
  • the face image C indicates the face image of Kate.
  • the electronic device adjusts the parameters of the decision model according to the first feedback information to obtain an updated decision model, including: the electronic device scores the facial expression of the first facial feature The weight occupied in the decision model is increased; the facial expression score is used to score the expression of facial features in the image; wherein, each image in the first image group contains one or more facial features, and The one or more facial features include the first facial feature.
  • the electronic device may use image semantic features and/or image parameters to determine the expression score of the human face. For example, a face detected by an electronic device contains image features of “smiling” and “eyes open”, and the sharpness, uniformity of illumination, and richness of details have reached the set threshold. The electronic device can be based on the detected image semantics. The features and image parameters get the facial expression score.
  • the preferred image may include a face image with the largest number of corresponding images in the gallery, and the face image has the highest expression score.
  • the image selected in this way is more in line with the user's habit, reducing the user's manual reselection from multiple images, thereby improving convenience.
  • updating the decision model may be that after detecting the user's operation to start the continuous shooting function and detecting the end of the long-press operation acting on the shooting control, the parameters of the decision model are adjusted according to the face image in the gallery. And according to the adjusted decision-making model, the preferred image in the image obtained by this continuous shooting is selected. Because the face images in the gallery and the number of corresponding images of each face image vary according to the accumulation of collected images. After the continuous shooting function is executed, the parameters of the decision model are adjusted in real time, which can improve the accuracy of the adjusted decision model for continuous shooting.
  • the electronic device may also periodically update the decision model.
  • the electronic device adjusts the parameters of the decision model according to the first feedback information to obtain the updated decision model, including: the electronic device scores the proportion of the first face feature of the figure to the body The weight of the decision model is increased; the figure-to-body ratio score is used to score the figure ratio of the facial features in the image; wherein, each image in the first image group contains one or more facial features, The one or more facial features include the first facial feature.
  • the electronic device may also use image semantic features and/or image parameters to determine the profile scale score of the face image. For example, the electronic device detects features of various parts of a complete portrait of a certain face image (such as "arm” image features, "leg” image features, etc.), and then calculates the body proportion score of the complete portrait based on each part of the complete portrait.
  • the electronic device adjusts the weight of the facial features in the decision model according to the number of corresponding images. Specifically, the greater the number of corresponding images in the gallery, the greater the weight of the face feature, and the smaller the number of corresponding images in the gallery, the smaller the weight of the face feature. The larger the proportion of the corresponding image in the gallery, the greater the weight of the face feature, and the smaller the proportion of the corresponding image in the gallery, the smaller the weight of the face feature.
  • the electronic device may use the original training sample set to train the decision model.
  • the trained decision model can be used as a teacher network.
  • the electronic equipment can use some features of the teacher network in the process of training the adjusted decision model.
  • the electronic device can perform a softmax transformation on the teacher network to obtain a soft target.
  • the soft target can represent some features in the original training sample set, and is used to train the decision model to obtain an adjusted decision model.
  • the updated decision-making model can be used for continuous shooting to select the best scene, and can also be used for the display scene of thumbnails in the gallery.
  • the updated decision model is used to select the best scene for continuous shooting
  • the method further includes: the electronic device displays a camera application interface, and the camera The application interface includes a shooting control; in response to a second user operation acting on the shooting control, the electronic device continuously shoots the first image group; the electronic device selects the first image group from the first image group according to the updated decision model
  • the method further includes: in response to a third user operation for displaying the first image group, the electronic device displays a continuous shooting image interface, and the continuous shooting image interface includes the first image group. An image and a thumbnail of each image in the first image group.
  • the first image (for example, an image containing the image feature of "Laughing") is selected from the first image group according to the first feedback information, which is more in line with the user's habits and preferences, and improves the recommendation for the user.
  • the accuracy of the image is more in line with the user's habits and preferences, and improves the recommendation for the user.
  • the electronic image display area may also include a prompt for prompting the image selected according to the first feedback information, for example, it may prompt "recommend a face with a laughing expression based on feedback".
  • the updated decision model is used for the display scene of thumbnails in the gallery
  • the method further includes: the electronic device detects the first image from the gallery Image group; wherein the thumbnails of the first image group are displayed adjacently on the gallery application interface, each image in the first image group includes a first image feature, and the first image feature includes a second face feature or The first shooting scene; after the electronic device selects the first image from the first image group as the preferred image of the first image group according to the updated decision model, the method further includes: responding to the first image in the gallery icon Four user operations, the electronic device displays the gallery application interface, and the gallery application interface contains thumbnails of the images in the first image group; wherein the size of the thumbnails of the first image is larger than other images in the first image group The size of the thumbnail.
  • the images in the first image group may include the same image feature, for example, the same face feature, that is, the second face feature. It is not limited that the first image group contains the same facial features, and may also contain the same shooting scene, such as the first shooting scene.
  • the first shooting scene is, for example, a landscape shooting scene.
  • the electronic device may also display a recommendation mark on the thumbnail of the first image, indicating that the image corresponding to the thumbnail is a preferred image selected from a plurality of images (first image group).
  • the method further includes: the electronic device The device displays a second user interface, and the second user interface includes a plurality of image feature options and determination controls; wherein, each image feature option of the plurality of image feature options corresponds to an image feature; in response to the second user interface acting on the first option Five user operations, the electronic device displays the first option from an unselected state to a selected state; the multiple image feature options include the first option; in response to the sixth user operation acting on the determining control, the electronic device The image feature corresponding to the first option adjusts the parameters of the decision model to obtain the updated decision model.
  • the second user interface may be a prompt box.
  • the prompt box contains multiple image feature options: one set of options is no smile option, smile option, and big laugh option, another set of options is front face option and side face option, and another set of options is closed eyes option and Eyes open option.
  • each option can include a selected state and an unselected state.
  • the electronic device may respond to a user operation acting on the option, such as a touch operation, to switch and display the state of the option between a selected state and an unselected state.
  • the weight corresponding to the "non-smiling" image feature can be increased, and when the non-smiling option is in the unselected state, the weight corresponding to the "non-smile” image feature can be decreased.
  • the smile option corresponds to the "smile” image feature
  • the big laugh option corresponds to the "big laugh” image feature.
  • the electronic device can obtain options in a selected state, such as a laugh option, a face-up option, and an eye-opening option.
  • the user operation that is used to determine the control can be called the sixth user operation.
  • an embodiment of the present application provides an electronic device, the electronic device includes: one or more processors, a memory, and a display screen; the memory is coupled with the one or more processors, and the memory is used to store the computer Program code, the computer program code includes computer instructions, the one or more processors call the computer instructions to cause the electronic device to execute: detect first feedback information, the first feedback information includes multiple images and acts on the multiple images User operation of the image in the image; according to the first feedback information, adjust the parameters of the decision model to obtain an updated decision model; according to the updated decision model, select the first image from the first image group as the first image The preferred image of the group.
  • the electronic device provided by the second aspect can realize: adjusting the parameters in the decision model for selecting a preferred image from a plurality of images according to user operations.
  • the preferred image selected by the updated decision model is more in line with the user's habits, reducing the user's manual reselection from multiple images, thereby improving convenience.
  • the one or more processors are further configured to invoke the computer instructions to cause the electronic device to execute: display a first user interface, the first user interface including a second image group,
  • the second image group is an image obtained by continuous shooting, the second image group includes a second image and a third image, and the second image is a preferred image of the second image group selected by the electronic device according to the decision model;
  • the one or more processors are specifically configured to call the computer instructions to cause the electronic device to execute: detect a first user operation on the first user interface, and respond to the first user operation to perform the operation of the second image group
  • the image is modified to the third image;
  • the first feedback information includes the first user operation, the second image, and the third image.
  • the first feedback information includes an operation record of an image in the gallery and an image corresponding to the operation record, and the operation record indicates one or more of the following operations: delete operation, browse operation , Collection operation and sharing operation.
  • the first feedback information includes the first facial feature and the proportion of the image containing the first facial feature in the gallery; wherein: the first facial feature is the The gallery contains the facial features with the largest number of images, and the gallery contains the images stored in the electronic device.
  • the one or more processors are specifically configured to invoke the computer instruction to make the electronic device execute: score the facial expression of the first facial feature in the decision model The weight accounted for is increased; the facial expression score is used to score the expression of the facial features in the image; wherein, each image in the first image group contains one or more facial features, and the one or more facial features The feature includes the first face feature.
  • the one or more processors are specifically configured to invoke the computer instructions to cause the electronic device to execute: score the portrait and body proportions of the first facial feature in the decision model The weight of the account is adjusted to be larger; the figure-to-body ratio score is used to score the figure ratio of the facial features in the image; wherein, each image in the first image group contains one or more facial features, and the one or more people
  • the face feature includes the first face feature.
  • the one or more processors are also used to call the computer instructions to make the electronic device execute: display a camera application interface, the camera application interface containing shooting controls;
  • the second user operation of the shooting control obtains the first image group by continuous shooting; in response to the third user operation for displaying the first image group, the continuous shooting image interface is displayed, and the continuous shooting image interface includes the first image and A thumbnail of each image in the first image group.
  • the one or more processors are further configured to invoke the computer instructions to make the electronic device execute: detect the first image group from the gallery; wherein, the first image group The thumbnails of are displayed next to each other on the gallery application interface.
  • Each image in the first image group includes a first image feature, and the first image feature includes a second face feature or a first shooting scene;
  • the one or more The processor is further configured to call the computer instruction to make the electronic device execute: in response to a fourth user operation acting on the gallery icon, display the gallery application interface, the gallery application interface containing the thumbnails of the images in the first image group Thumbnail; wherein the size of the thumbnail of the first image is larger than the size of the thumbnails of other images in the first image group.
  • the one or more processors are further configured to invoke the computer instruction to cause the electronic device to execute: display a second user interface, the second user interface including a plurality of image feature options And a determination control; wherein each of the plurality of image feature options corresponds to an image feature; in response to a fifth user operation acting on the first option, the first option is displayed from an unselected state to a selected state;
  • the multiple image feature options include the first option; in response to a sixth user operation acting on the determining control, the parameters of the decision model are adjusted according to the image features corresponding to the first option to obtain the updated decision model.
  • the embodiments of the present application provide a chip that is applied to an electronic device.
  • the chip includes one or more processors for invoking computer instructions to make the electronic device execute the first aspect and the first aspect.
  • the embodiments of the present application provide a computer program product containing instructions.
  • the computer program product is run on an electronic device, the electronic device is caused to execute the first aspect and any one of the possible implementation manners in the first aspect. Described method.
  • an embodiment of the present application provides a computer-readable storage medium, including instructions, which when the instructions are executed on an electronic device, cause the electronic device to execute the first aspect and any possible implementation manner in the first aspect Described method.
  • the electronic equipment provided in the second aspect, the chip provided in the third aspect, the computer program product provided in the fourth aspect, and the computer storage medium provided in the fifth aspect are all used to implement the methods provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.
  • FIGS 1-12 are schematic diagrams of some application interfaces provided by embodiments of the present application.
  • FIG. 13 is a flowchart of a method for adjusting parameters of a decision model provided by an embodiment of the present application.
  • FIG. 14 is a schematic diagram of a training principle of a decision model provided by an embodiment of the present application.
  • FIG. 15 is a schematic structural diagram of an electronic device 100 provided by an embodiment of the present application.
  • FIG. 16 is a software structure block diagram of an electronic device 100 provided by an embodiment of the present application.
  • the electronic device can use the neural network to construct a decision model, and use the decision model to select one image from the multiple images as the preferred image.
  • the decision model can be used to select a preferred image based on the shooting scene, image semantic features and image parameters (such as sharpness, brightness, etc.).
  • the electronic device can recognize the shooting scene and the semantic features of the image through image recognition.
  • the shooting scene includes, for example, portraits, animals, landscapes, sports scenes, and the like.
  • the electronic device can also recognize the semantic features of the captured images in different shooting scenarios. For example, when it is recognized that the shooting scene is a portrait scene, the electronic device can also recognize expressions, frontal faces/side faces, eyes open/closed, etc. For another example, when it is recognized that it is a sports scene, the electronic device can also recognize indoor sports/outdoor sports.
  • the semantic features of the image recognized by the electronic device can also include the composition of the captured image, such as the diagonal composition, the central composition, and the "Tic Tac Toe" composition. It is understandable that the examples are only used to explain the embodiments of the present application and should not constitute a limitation, and the identified shooting scenes and image semantic features are not limited to the above examples.
  • the electronic device can also identify the image parameters of each of the multiple images taken.
  • the image parameters may include any one or more of the following: clarity, uniformity of illumination, contrast, saturation, brightness, whether it is overexposed or too dark, whether there are color blocks, whether it is color cast, and whether it is too cold.
  • the embodiment of the present application does not limit the algorithm used by the electronic device to recognize the image parameter.
  • a neural network can be composed of neural units.
  • a neural unit can refer to an arithmetic unit that takes x s and intercept 1 as inputs.
  • the output of the arithmetic unit can be:
  • s 1, 2,...n, n is a natural number greater than 1
  • W s is the weight of x s
  • b is the bias of the neural unit.
  • f is the activation function of the neural unit, which is used to introduce nonlinear characteristics into the neural network to convert the input signal in the neural unit into an output signal.
  • the output signal of the activation function can be used as the input of the next convolutional layer.
  • the activation function can be a sigmoid function.
  • a neural network is a network formed by connecting many of the above-mentioned single neural units together, that is, the output of one neural unit can be the input of another neural unit.
  • the input of each neural unit can be connected with the local receptive field of the previous layer to extract the characteristics of the local receptive field.
  • the local receptive field can be a region composed of several neural units.
  • Deep neural network also known as multi-layer neural network
  • DNN can be understood as a neural network with multiple hidden layers.
  • the neural network inside DNN can be divided into three categories: input layer, hidden layer, and output layer.
  • the first layer is the input layer
  • the last layer is the output layer
  • the number of layers in the middle are all hidden layers.
  • the layers are fully connected, that is to say, any neuron in the i-th layer must be connected to any neuron in the i+1th layer.
  • the relationship between its input and output is:
  • Is the input vector Is the output vector
  • Is the offset vector W is the weight matrix (also called coefficient)
  • ⁇ is the activation function
  • the linear coefficient from the fourth neuron in the second layer to the second neuron in the third layer is defined as.
  • the superscript 3 represents the number of layers where the coefficient W is located, and the subscript corresponds to the output third-level index 2 and the input second-level index 4. That is, the coefficient from the kth neuron of the L-1 layer to the jth neuron of the Lth layer is defined as Among them, the input layer has no W parameter.
  • a deep neural network In a deep neural network, more hidden layers make the deep neural network more capable of portraying complex situations in the real world.
  • the model with more parameters is more complex, and the model can complete more complex tasks.
  • the input vector of the input layer may represent an image, for example, multiple images obtained by continuous shooting in this application.
  • the process of computing the hidden layer may include the process of extracting the image features of each image in multiple images.
  • the image features include different expressions in a portrait scene (not smiling, smiling, laughing, etc.), whether the eyes are closed, the face is facing sideways, and so on.
  • the image feature also includes the depth of field of the image in the macro shooting scene of bees and butterflies.
  • the characteristics of the image include the composition of the image in a landscape shooting scene, including a diagonal composition, a central composition, and a "Tic Tac Toe" composition. Different features have different weights.
  • the weight when the expression is a big laugh is less than the weight when the expression is a smile (that is, the image feature of "smile").
  • the weight when the expression is closed eyes is less than the weight when the eyes are open. The greater the weight of the image feature, the greater the probability that the image containing the image feature is selected as the preferred image.
  • the output layer may output an image selection result, and the selection result indicates a preferred image selected from multiple images.
  • the output layer can calculate the probability of each image being selected, and then select the image with the highest probability as the selected preferred image.
  • the selection probability of each image is determined by the image characteristics of the hidden layer and the corresponding weight. For example, since the weight corresponding to the "not smiling" image feature is smaller than the weight of the "smiling" image feature, the selection probability of the image containing the "not smiling" image feature is less than the selection probability of the image containing the "smiling" image feature.
  • Convolutional neural network (convolutional neuron network, CNN) is a deep neural network with a convolutional structure.
  • the convolutional neural network contains a feature extractor composed of a convolutional layer and a sub-sampling layer.
  • the feature extractor can be seen as a filter, and the convolution process can be seen as using a trainable filter to convolve with an input image or convolution feature map.
  • the convolutional layer refers to the neuron layer that performs convolution processing on the input signal in the convolutional neural network.
  • a neuron can only be connected to a part of the neighboring neurons.
  • a convolutional layer usually contains several feature planes, and each feature plane can be composed of some rectangularly arranged neural units. Neural units in the same feature plane share weights, and the shared weights here are the convolution kernels. Sharing weight can be understood as the way of extracting image information has nothing to do with location.
  • the underlying principle is that the statistical information of a certain part of the image is the same as that of other parts. This means that the image information learned in one part can also be used in another part.
  • the image information obtained by the same learning can be used for all positions on the image.
  • multiple convolution kernels can be used to extract different image information.
  • the more the number of convolution kernels the richer the image information reflected by the convolution operation.
  • the convolution kernel can be initialized in the form of a matrix of random size, and the convolution kernel can obtain reasonable weights through learning during the training process of the convolutional neural network.
  • the direct benefit of sharing weights is to reduce the connections between the layers of the convolutional neural network, and at the same time reduce the risk of overfitting.
  • the algorithm model used to select the preferred image may also be CNN.
  • Training a deep neural network is the process of learning the weight matrix.
  • the ultimate goal of training is to obtain the weight matrix of all layers of the trained deep neural network.
  • the weight matrix of all layers is a weight matrix formed by the vector W of each layer.
  • the electronic device needs to predefine "how to compare the difference between the predicted value and the target value", which is the loss function or objective function.
  • Loss function and objective function are important equations used to measure the difference between the predicted value and the target value. Among them, taking the loss function as an example, the higher the output value (loss) of the loss function, the greater the difference.
  • the training process of the deep neural network is the process of minimizing this loss as much as possible.
  • the deep neural network can use the loss function back propagation (BP) algorithm to modify the initial weight matrix during the training process, so that the difference between the predicted value and the target value becomes smaller and smaller. Specifically, forwarding the input signal to the output will cause error loss, and the initial weight matrix is adjusted by backpropagating the error loss information, so that the error loss is converged.
  • the back-propagation algorithm is a back-propagation motion dominated by error loss, aiming to obtain the optimal weight matrix, for example.
  • the electronic device can detect user feedback.
  • the user feedback may include the preferred image and the modified preferred image selected by the decision model in the process of continuous shooting.
  • User feedback can also include images that have been deleted, browsed, favorited, and shared.
  • the user feedback may also include face images in the gallery obtained by the statistics of the electronic device.
  • the electronic device can adjust the parameters in the decision-making model for continuous shooting based on the user feedback to obtain the adjusted decision-making model.
  • the electronic device can perform continuous shooting selection based on the adjusted decision model, and display the optimized image.
  • the first feedback information mentioned in the embodiment of the present application may include the above-mentioned user feedback, and the updated decision model is the adjusted decision model.
  • the electronic device can adjust the parameters in the decision model for selecting a preferred image from a plurality of images according to user operations.
  • the preferred image selected through the decision model is more in line with the user's habits, reducing the user's manual reselection from multiple images, thereby improving convenience.
  • FIG. 1 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device displays a main screen interface 10.
  • the main screen interface 10 includes a calendar widget 101, a weather widget 102, an application icon 103, a status bar 104 and a navigation bar 105. among them:
  • the calendar widget 101 can be used to indicate the current time, such as date, day of the week, hour and minute information, and so on.
  • the weather widget 102 can be used to indicate the type of weather, such as cloudy to clear, light rain, etc., can also be used to indicate information such as temperature, and can also be used to indicate a location.
  • the application icon 103 may include, for example, the icon of Wechat, the icon of Twitter, the icon of Facebook (Facebook), the icon of Weibo (Sina Weibo), the icon of QQ (Tencent QQ), the icon of Youtu ( YouTube) icons, gallery (Gallery) icons, camera (camera) icons 1031, etc., may also include other application icons, which are not limited in the embodiment of the present application.
  • the icon of any application can be used to respond to a user's operation, such as a touch operation, so that the electronic device starts the application corresponding to the icon.
  • the status bar 104 may include the name of the operator (for example, China Mobile), time, WI-FI icon, signal strength, and current remaining power.
  • the navigation bar 105 may include system navigation keys such as a return button 1051, a home screen button 1052, and a call out task history button 1053.
  • the main screen interface 10 is an interface displayed after the electronic device 100 detects a user operation on the main interface button 1052 on any user interface. When it is detected that the user clicks the return button 1051, the electronic device 100 may display the previous user interface of the current user interface. When it is detected that the user clicks the main interface button 1052, the electronic device 100 may display the main screen interface 10. When it is detected that the user clicks on the outgoing task history button 1053, the electronic device 100 may display the task recently opened by the first user.
  • the naming of each navigation key can also be other. For example, 1051 can be called Back Button, 1052 can be called Home button, and 1053 can be called Menu Button, which is not limited in this application.
  • the navigation keys in the navigation bar 105 are not limited to virtual keys, and can also be implemented as physical keys.
  • the electronic device may display the camera application interface 20.
  • the camera application interface 20 may also include a thumbnail control 201, a shooting control 202, a camera switching control 203, a viewfinder 205, a focus control 206A, a setting control 206B, and a flash switch 206C. among them:
  • the thumbnail control 201 is used for the user to view the pictures and videos that have been taken.
  • the shooting control 202 is used to enable the electronic device to shoot a picture or video in response to a user's operation.
  • the camera switching control 203 is used to switch the camera that collects the image between the front camera and the rear camera.
  • the viewfinder frame 205 is used for real-time preview and display of the collected pictures.
  • the focusing control 206A is used to adjust the focus of the camera.
  • the setting control 206B is used to set various parameters when collecting images.
  • the flash switch 206C is used to turn on/off the flash.
  • the user can press the shooting control 202 for a long time.
  • the electronic device can activate the continuous shooting function to collect and store multiple images in a short time.
  • the electronic device can stop storing images, that is, the current continuous image shooting process ends.
  • the electronic device may also implement the triggering of the continuous shooting function through other control designs, which is not limited in the embodiment of the present application.
  • FIG. 2 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the user interface 30 may include a sharing control 301, a favorite control 302, an editing control 303, a delete control 304, a more control 305, a gallery control 306, a selection control 307, and a shooting parameter control 308 And image preview box 309. among them:
  • the image preview frame 309 is used to display the preferred image selected by the electronic device according to the decision model among the multiple images obtained by continuous shooting.
  • the preferred image is the preferred image 4031 shown in (A) in FIG. 3, and the example is described with reference to FIG. 3 in detail.
  • the sharing control 301 is used to share the image displayed in the image preview box 309 to other applications, such as sharing to WeChat, QQ, etc.
  • the favorite control 302 is used to add the image displayed in the image preview box 309 to the favorite group.
  • the user can view the image displayed in the image preview box 309 in the favorite group.
  • the edit control 303 is used to edit the image displayed in the image preview frame 309, such as cropping, adjusting brightness, adding filters, and so on.
  • Delete control used to delete multiple images obtained by continuous shooting.
  • More controls 305 are used to perform other functional operations on the image displayed in the image preview box 309, such as printing functional operations, functional operations set as desktop backgrounds, and so on.
  • the gallery control 306 is used to open the gallery application, and the gallery application contains the captured images.
  • the shooting parameter control 308 is used to enable the electronic device to display the shooting parameters of the preferred image, such as the shooting focal length, the storage path, the size of the occupied memory, etc., in response to user operations.
  • the optimal control 307 is used to modify the optimal image obtained by continuous shooting. Specifically, as shown in (B) of FIG. 2, in response to a user operation on the preferred control 307, the electronic device may display the user interface 40. A preferred image that the user can modify on the user interface 40.
  • the user interface 40 includes a return control 401, a prompt 402, an image display area 403, a thumbnail display area 404, and a save control 405.
  • the return control 401 is used to return to the upper level interface of the user interface 40.
  • the electronic device may display the user interface 30.
  • the prompt 402 can be used to prompt the number of images taken in this continuous image capturing process and the number of selected preferred images.
  • the prompt 402 may prompt "1/8", which means that the total number of images taken during this continuous image capturing process is 8 and the number of selected preferred images is 1 image. These 8 images can be called the second image group.
  • the preferred image 4031 can be displayed in the image display area 403 by default, and as shown in (B) of FIG. 2, the preferred image 4031 includes a selected mark 4031a by default, indicating that the preferred image 4031 is selected.
  • the user can touch and slide left and right in the image display area 403 to view other images in the continuous shooting image. In response to the touch sliding operation acting on the image display area 403, the electronic device can display more images in the image display area 403.
  • the electronic device may select the preferred image 4031 from the continuously shot images according to the decision model.
  • the image 4031 is displayed in the image preview frame 309 by default.
  • the thumbnail display area 404 may contain thumbnails of images obtained by continuous shooting. Exemplarily, in the embodiment of the present application, the thumbnail display area 404 may include thumbnails of 8 consecutively shot images.
  • the thumbnail 4041 of the preferred image 4031 may include a recommendation identifier 4041a.
  • the thumbnail display area 404 can display thumbnails of 4 images. The user can touch and slide left and right in the thumbnail display area 404 to view other thumbnails. In response to the touch sliding operation on the thumbnail display area 404, the electronic device can display more thumbnails in the thumbnail display area 404.
  • the first user interface may be the user interface 40.
  • the user can modify the preferred images obtained by continuous shooting.
  • the preferred image 4031 contains the selected mark 4031a, which is a preferred image selected by the electronic device according to the decision model.
  • FIG. 3 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device may display an unselected logo 4031b on the image 4031, indicating that the image 4031 has not been selected.
  • the electronic device in response to a touch sliding operation acting on the image display area 403, the electronic device can display an image 4032 in the image display area 403.
  • the image 4032 contains an unselected mark.
  • the electronic device may display the selected mark 4032a on the image 4032, indicating that the image 4032 is selected.
  • Image 4031 is a preferred image selected by the electronic device, and image 4032 is a modified preferred image.
  • the user can touch the save control 405 so that the electronic device saves the preferred image modified by the user.
  • FIG. 4 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device in response to a user operation (for example, a touch operation) acting on the save control 405, the electronic device may display the user interface 50.
  • the user interface 50 may include a control 501, a control 502, and a control 503. among them:
  • the control 501 may prompt "Cancel”, and in response to a user operation acting on the control 501, the electronic device may display the user interface 40 shown in (B) of FIG. 3.
  • the control 502 may prompt "Keep all”.
  • the electronic device may store the selected preferred image 4032 and still save other unselected images, for example, still save the images other than the image 4032 7 other images.
  • the control 503 may prompt "only keep the selected one photo".
  • the electronic device may store the selected preferred image 4032 and delete other unselected images, for example, delete 7 images other than image 4032. After the preferred image 4032 is stored, the user can view the preferred image 4032 in the user interface of the gallery application.
  • the electronic device may receive a user operation for modifying a preferred image obtained by continuous shooting, for example, the user operation for modifying a preferred image from an image 4031 to an image 4032 in FIG. 3. Then, the electronic device can respond to the user operation on the control 502 or the control 503 and display the prompt box 504.
  • the prompt box 504 may include a prompt 5041, a control 5042, and an option 5043.
  • Prompt 5041 can prompt: "have received your modification feedback, we will recommend photos more in line with your preferences based on the modification.”
  • the electronic device may no longer display the prompt box 504, display the user interface of the gallery, and preview the preferred image 4032.
  • Option 5043 can prompt: "Don't show again".
  • Option 5043 is in an unselected state, and in response to a user operation acting on option 5043, option 5043 is in a selected state.
  • the prompt box 504 no longer appears.
  • the preferred image 4031 selected by the decision model and the modified preferred image 4032 shown in FIG. 3 can be used as user feedback to adjust Continuous shooting selects the parameters in the optimal decision-making model to obtain the adjusted decision-making model.
  • the first user operation may include the touch operation on the selected logo 4031a shown in Figure 3 (A), the touch slide operation on the image display area 403, and the unselected logo on the image 4032.
  • the touch operation which acts on the control 502 and the user operation of the control 503.
  • the electronic device modifies the preferred image of the images obtained by continuous shooting to image 4032.
  • the preferred image 4031 before modification may be referred to as the second image
  • the preferred image 4032 after modification may be referred to as the third image.
  • the electronic device detects that the preferred image 4031 is modified to the preferred image 4032, the preferred image 4031 contains the "smile” image feature, and the preferred image 4032 contains the "big laugh” image feature. Then the electronic device can adjust the parameters of the decision model, reduce the weight of the "smile” image feature in the decision model, and increase the weight of the "big laugh” image feature, to obtain the adjusted decision model.
  • the electronic device can modify the preferred image
  • the user interface 40 can also check a certain group of images (the second image group) obtained by continuous shooting.
  • One or several images can be deleted, browsed, collected and shared.
  • Users can delete, browse, favorite and share images in the user interface of the gallery application.
  • the deleted, browsed, favorited, and shared images can also be used as user feedback to adjust the parameters in the decision-making model used for continuous shooting to obtain the adjusted decision-making model.
  • the following describes the user interface related to deleting, browsing, collecting and sharing images.
  • FIG. 5 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the user interface 60 may be displayed by the electronic device in response to a touch operation of an icon on the gallery.
  • the gallery application can be used to display images stored in the electronic device, and the user interface 60 can contain thumbnails of these images. It is not limited to this way to display the user interface 60, but may also be other ways.
  • the electronic device in response to a user operation on the selection control 307, the electronic device may display the user Interface 60.
  • the user interface 60 may include a thumbnail display area 601, a photo option 602, an album option 603, a discovery option 604, a search control 605, and more options 606. among them:
  • the thumbnail display area 601 may contain thumbnails of multiple images stored in the electronic device.
  • the album option 603 and the discovery option 604 different options correspond to different thumbnail display areas.
  • the currently selected option shown in (A) in FIG. 5 is the photo option 602. That is, the thumbnail displayed in the thumbnail display area 601 is the thumbnail under the photo option 602.
  • the search control 605 is used to search for images.
  • More options 606 can be used to open more functions, for example, hide albums, settings, and so on.
  • the user can delete, browse, bookmark, and share images on the user interface 60.
  • the electronic device may display edit controls on the user interface 60, including a sharing control 608, a delete control 609, and more Control 611.
  • the thumbnail 6011 can be any thumbnail, and the thumbnail 6011 also includes a selection mark 6011a, which indicates that the image corresponding to the thumbnail 6011 is selected.
  • the user interface 60 may also include a select all control 610 and an exit control 607. among them:
  • the exit control 607 is used to exit the editing state.
  • the electronic device can display the user interface 60 shown in (A) in FIG. 5.
  • the sharing control 608 is used to share the selected image to other applications, for example, to a WeChat application or a Weibo application.
  • the delete control 609 is used to delete the selected image.
  • the select all control 610 is used to select all the images corresponding to the thumbnails. As shown in (B) in FIG. 5, the thumbnail 6011 contains a selected mark 6011a, and the other thumbnails contain an unselected mark. In response to the user's operation on the select all control 610, the electronic device displays a selected mark on all thumbnails, that is, all stored images are selected.
  • More controls 611 perform more operations on the selected image, such as executing printing, viewing detailed information, collecting, and so on.
  • the electronic device can display an image corresponding to the thumbnail.
  • the corresponding user interface is analogous to (A) in FIG. ) Shows an example.
  • This touch operation on the thumbnail can be regarded as a user operation for browsing images.
  • the electronic device can count the number or frequency of browsing each image, and use the browsed image as user feedback to adjust the parameters in the decision-making model.
  • the user interface of the image corresponding to the thumbnail is similar to (A) in FIG. 2, and may also include a share control, a delete control, and a favorite control.
  • the electronic device adds the image corresponding to the thumbnail to the favorite group. Users can view the images in the favorite group.
  • the collected images can be used as user feedback to adjust the parameters in the decision-making model.
  • the collection record of the image in the gallery may indicate the user operation acting on the collection control.
  • the favorite control can refer to the favorite control 302 described in FIG. 2.
  • the image corresponding to the favorite record is the favorite image.
  • FIG. 6 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device in response to a user operation on the delete control 6123, deletes the selected image, that is, deletes the image corresponding to the thumbnail 6011.
  • the image corresponding to the thumbnail 6011 is the deleted image, which can be used as user feedback to adjust the parameters in the decision model.
  • the electronic device may also display a prompt box 612.
  • the electronic device deletes the images obtained by continuous shooting
  • the preferred image 4031 can be used as the deleted image
  • the deleted image 4031 can be used as user feedback to adjust the parameters in the decision model.
  • all images obtained by continuous shooting are deleted images, which can be used as user feedback to adjust the parameters in the decision model.
  • the deleted image includes, for example, an image corresponding to the thumbnail 6011.
  • the deletion record of the image in the gallery may include, for example, a long press operation acting on the thumbnail 6011 and a user operation acting on the delete control 6123.
  • the image corresponding to the deletion record is the image corresponding to the thumbnail 6011.
  • the deleted image is not limited to the image corresponding to the thumbnail 6011, and, for example, also includes the following image: an image that is caused by the electronic device to be deleted by a user operation detected by the delete control 304 shown in (A) in FIG. 2.
  • FIG. 7 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device may display a prompt box 613.
  • the prompt box 613 may include an icon display area 6131.
  • the icon display area 6131 may contain multiple application icons, such as WeChat icons, QQ icons, Twitter icons, Facebook icons, mail icons, cloud sharing icons, memo icons, and information icons.
  • the user can touch the sliding icon display area 6131, and in response to the touch and sliding operation, the electronic device can display more application icons.
  • the electronic device may display the user interface 70.
  • the user interface 70 is an interface of a WeChat application.
  • the user interface 70 includes a contact list 701 and a search box 702.
  • the contact list 701 may include multiple contact identifiers.
  • the search box 702 can be used to search for contacts.
  • the electronic device may display a user interface 80 and share the selected image shown in FIG. 7(A) to the user Interface 80 shows a contact dialog box. Sharing the selected image to the contact dialog box means that the electronic device sends the selected image to the terminal corresponding to the contact.
  • the user interface 80 may include a thumbnail 801, a user ID 802, a voice control 803, an input box 804, a function control area 805, and a return control 806. among them:
  • the thumbnail 801 which corresponds to the thumbnail 6011 including the selected mark 6011a shown in (A) in FIG. 7, indicates that the corresponding image is shared with the user in the WeChat application.
  • the user ID 802 indicates the user logged in by the current WeChat application.
  • the voice control 803 is used to send voice information.
  • the electronic device can detect the voice information and send the voice information to the corresponding user, for example, to the user Lisa corresponding to the contact icon 7011.
  • the input box 804 is used to send text messages.
  • the electronic device can receive text information through the input box 804 and send the text information to the corresponding user.
  • the function control area 805 can include photo option 8051, shooting option 8052, video call option 8053, location option 8054, red envelope option 8055, transfer option 8056, voice input option 8057, and favorite option 8058. among them:
  • the photo option 8051 is used to send an image to the user (for example, the user Lisa corresponding to the contact icon 7011).
  • the capture option 8052 is used to capture images and send the captured images to the user.
  • the video call option 8053 is used to send a voice call request or a video call request to the user.
  • the location option 8054 is used to send location information to the user.
  • Red envelope option 8055 and transfer option 8056 are used to send red envelopes to users or make transfers.
  • the voice input option 8057 is used to send voice messages.
  • Collection option 8058 used to send the content of the collection.
  • the return control 806 is used to return to the upper level interface of the user interface 80.
  • the return control 806 is used to return to the upper level interface of the user interface 80.
  • the electronic device when a user operation acting on the contact icon 7011 is detected, the electronic device can determine that the image corresponding to the thumbnail 6011 shown in (A) in FIG. 7 is a shared image.
  • the image corresponding to the thumbnail 6011 can be used as user feedback to adjust the parameters in the decision model.
  • the image to be shared is not limited to the example shown in FIG. 7, and the user can also share the image through the picture option 8051 and the shooting option 8052 shown in (C) in FIG. 7.
  • the images shared through the picture option 8051 and the shooting option 8052 can also be used as user feedback to adjust the parameters in the decision-making model.
  • the sharing record of the image in the gallery may indicate the user operation of the sharing control 608 shown in (B) in FIG. 5.
  • the image corresponding to the shared record may indicate the image corresponding to the thumbnail 6011.
  • the images that are deleted, browsed, favorited, and shared are not limited to the examples described in FIGS. 5 to 7.
  • the following describes the deleted, browsed, favorited, and shared images involved in other scenarios in the embodiments of the present application.
  • the electronic device may display an image corresponding to the thumbnail 801.
  • the image corresponding to the thumbnail 801 is the image to be viewed, which can be used as user feedback to adjust the parameters in the decision model.
  • the browsing record of the image in the gallery is, for example, the browsing record of the image corresponding to the thumbnail 801.
  • the image corresponding to the browsing history is, for example, an image corresponding to the thumbnail 801.
  • FIG. 8 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device in response to a long press operation on the thumbnail 801, the electronic device can display an option box 807, which includes a sending option 8071, a favorite option 8072, a reminder option 8073, an edit option 8074, and a delete option 8075.
  • option box 807 which includes a sending option 8071, a favorite option 8072, a reminder option 8073, an edit option 8074, and a delete option 8075.
  • multi-select option 8076 among them:
  • the sending option 8071 is used to send the image corresponding to the thumbnail 801 to other users.
  • the favorite option 8072 is used to favorite the image corresponding to the thumbnail 801 in the WeChat application.
  • the reminder option 8073 is used to remind the image corresponding to the thumbnail 801.
  • the editing option 8074 is used to edit the image corresponding to the thumbnail 801.
  • the delete option 8075 is used to delete the thumbnail 801 on the user interface 80.
  • Multi-select option 8076 is used to select multiple pieces of information.
  • the electronic device in response to a user operation acting on the sending option 8071, such as a touch operation, the electronic device may record the image corresponding to the thumbnail 801 as the shared image, and use the shared image as user feedback to adjust the decision. Parameters in the model.
  • the electronic device may record the image corresponding to the thumbnail 801 as a favorited image, and use the favorited image as user feedback to adjust the parameters in the decision model.
  • the electronic device may record the image corresponding to the thumbnail 801 as the deleted image, and use the deleted image as user feedback to adjust the parameters in the decision model.
  • user feedback can also include images that are edited, printed, remarks, and reminders.
  • the edited image includes, for example, an image whose parameters such as color and brightness are adjusted.
  • the image to be printed may be an image in which printing is performed through more controls 611 in the user interface 60.
  • the annotated image may also be an image annotated through more controls 611 in the user interface 60, for example.
  • the reminded image may be, for example, an image reminded through the reminder option 8073 in the option box 807.
  • the electronic device may also calculate the face images in the gallery obtained by statistics, and use the face images obtained by the statistics to adjust the parameters in the decision-making model for continuous shooting.
  • FIG. 9 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device may display the thumbnail under the discovery option 604 in the thumbnail display area 601, as shown in FIG. 9 .
  • the thumbnails under the discovery option 604 may include categories recognized by the electronic device: portrait category 6012, place category 6013, and thing category 6014. among them:
  • Portrait category 6012 contains thumbnails of recognized facial images.
  • Portrait category 6012 also includes more controls 6012a.
  • the electronic device can display more thumbnails of recognized facial images.
  • Portrait category 6012 is used to classify images in the gallery according to facial features.
  • each thumbnail corresponds to a facial feature.
  • the electronic device may display thumbnails of multiple images in the gallery that match the facial features.
  • the electronic device may display a thumbnail of the image corresponding to the thumbnail 6012b that matches the facial features.
  • the matching of the facial features and the image means that the similarity between the facial features and the facial features contained in the image is greater than a set threshold, for example, 80%.
  • the location category 6013 is used to classify the images in the gallery according to the geographic location where the image was taken.
  • the geographic location includes, for example, Shenzhen, Wuhan, Dongguan, and so on.
  • the location category 6013 also includes more controls 6013a.
  • the electronic device can display more thumbnail images of images classified by geographic location. Each thumbnail corresponds to a geographic location.
  • the electronic device may display the thumbnail of the image in the gallery that is the same as the geographic location.
  • the thing category 6014 is used to classify the images in the gallery according to the type of things.
  • Types of things include, for example, scenery, documents, sports, vehicles, and so on.
  • the thing category 6014 also includes more controls 6014a.
  • the electronic device can display more thumbnails of images classified according to the type of things. Each thumbnail corresponds to a type of thing.
  • the electronic device may display a thumbnail of an image of the same type as the thing in the gallery.
  • the face image included in the face category 6012 can be used to adjust the parameters in the decision model for continuous shooting.
  • the face image can also be updated according to the update of the captured image.
  • the electronic device can select a preferred image from the continuously shot images according to the adjusted decision model after executing the continuous shooting function next time.
  • the first image group may include the continuous shot image, and the first image may include a preferred image selected from the first image group according to the adjusted decision model (ie, the updated decision model).
  • FIG. 10 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the preferred image 4061 can be displayed in the image display area 403 by default, and as shown in FIG. 10, the preferred image 4061 includes a selected mark 4061a by default, indicating that the preferred image 4061 is selected.
  • the user can touch and slide left and right in the image display area 403 to view other images in the continuous shooting image.
  • the electronic device can display more images in the image display area 403.
  • the thumbnail display area 404 may contain thumbnails of 11 consecutive images.
  • the thumbnail 4071 of the preferred image 4061 may include a recommendation mark 4071a.
  • the first image group includes a group of images that can be displayed in the image display area 403, and the first image may include a preferred image 4061.
  • the third user operation for displaying the first image group may include, for example, the user operation acting on the control 307 in (A) in FIG. 2.
  • the continuous shooting image interface may include, for example, the user interface 40 described in FIG. 10.
  • the electronic device can adjust the parameters of the decision model according to the preferred images obtained by modifying the continuous shooting, and reduce the weight of the "smile” image feature in the decision model, and the weight of the "big laugh” image feature Increase to get the adjusted decision model.
  • the electronic device when the electronic device selects from the 11 images continuously shot according to the adjusted decision model, it can select the image that contains the feature of the “laughing” image, that is, the image corresponding to the thumbnail 4071.
  • the electronic device displays the image 4061 corresponding to the thumbnail 4071 in the image display area 4061.
  • the images containing the image feature of "big laugh” are selected based on user feedback, which is more in line with the user's habits and preferences, and improves the accuracy of recommending images for the user.
  • the electronic image display area 403 may also include a prompt 4062, which may prompt "recommend a face with a laughing expression based on feedback”.
  • the electronic device may receive user input for adjusting the feature weight.
  • the electronic device also displays a control 4063 on the user interface 40, prompting "click to select personal preference".
  • the electronic device in response to a user operation acting on the control 4063, the electronic device may display a prompt box 408.
  • the prompt box 408 may be referred to as a second user interface.
  • the prompt box 408 contains multiple image feature options: one set of options is no smile option 4081, smile option 4082, and laugh option 4083, another set of options is front face option 4084 and side face option 4085, and another set of options is closed eyes Option 4086 and open eye option 4087.
  • each option can include a selected state and an unselected state.
  • the electronic device may respond to a user operation acting on the option, such as a touch operation, to switch and display the state of the option between a selected state and an unselected state.
  • the weight corresponding to the "not smiling” image feature can be increased, and when the non-smiling option 4081 is in the unselected state, the weight corresponding to the "not smiling” image feature can be decreased.
  • the smile option 4082 corresponds to the "smile” image feature
  • the big laugh option 4083 corresponds to the "big laugh” image feature.
  • the front face option 4084 corresponds to the "front face” image feature
  • the side face option 4085 corresponds to the "side face” image feature.
  • the closed eye option 4086 corresponds to the "closed eye” image feature
  • the open eye option 4087 corresponds to the "open eye” image feature.
  • Smile option 4082, big laugh option 4083, front face option 4084, side face option 4085, closed eyes option 4086 and open eyes option 4087 are similar.
  • the weight of the corresponding image feature can be adjusted.
  • the weight of the corresponding image feature can be adjusted down.
  • the prompt box 408 also includes a cancel control 408a and a confirm control 408b.
  • the cancel control 408a is used to return to the previous interface.
  • the electronic device may display the interface shown in (A) in FIG. 11.
  • the determining control 408b is used to determine the image feature whose weight needs to be adjusted.
  • the electronic device can obtain options in a selected state, such as a laugh option 4083, a face option 4084, and an eye open option 4087.
  • the user operation that acts on the determining control 408b, such as a touch operation may be referred to as a sixth user operation.
  • the electronic device can determine the image feature whose weight needs to be adjusted according to the option in the selected state. For example, the electronic device determines that the image features whose weights need to be adjusted are the "big laugh" image feature, the "front face” image feature, and the "eye open” image feature. Among them, the "big laugh” option 4083, the "face up” option 4084, and the “eyes open” option 4087 can be referred to as the first option.
  • the first option may be displayed from an unselected state to a selected state in response to a fifth user operation, such as a touch operation, acting on the first option.
  • the electronic device then adjusts the weights of these image features to be larger. Since these image features are image features selected by the user according to personal preferences, they are more in line with the user's habits, reducing the user's manual reselection from multiple images, thereby improving convenience.
  • the embodiment of the present application is not limited to the example option shown in (B) in FIG. 11, and may also include other options.
  • it is not limited to portrait scenes.
  • the electronic device can also recognize shooting scenes and provide feature options for users to choose.
  • the electronic device adjusts the parameters of the decision model according to user feedback to obtain the adjusted decision model.
  • the electronic device can also select a preferred image from the images in the gallery according to the adjusted decision model, and display it separately from other images.
  • FIG. 12 is a schematic diagram of a user interface provided by an embodiment of the present application.
  • the electronic device stores multiple face images
  • the multiple face images can be displayed in the form of thumbnails, that is, thumbnails 6011, on the user interface 60 corresponding to the gallery. Contains thumbnails 6011a, 6011b, 6011c, and 6011d.
  • the multiple face images may be the first image group, and these images may include the same image feature, for example, the same face feature, that is, the second face feature. It is not limited that the first image group contains the same facial features, and may also contain the same shooting scene, such as the first shooting scene.
  • the first shooting scene is, for example, a landscape shooting scene.
  • the electronic device may detect a fourth user operation, such as a touch operation, acting on the gallery icon, and display the gallery application interface 60.
  • a fourth user operation such as a touch operation, acting on the gallery icon
  • display the gallery application interface 60 For the gallery icon, please refer to 1 description example.
  • the electronic device may select an image from the image corresponding to the thumbnail 6011a, the image corresponding to the thumbnail 6011b, the image corresponding to the thumbnail 6011c, and the image corresponding to the thumbnail 6011d according to the adjusted decision model. For example, the image corresponding to the thumbnail 6011d is selected, and the thumbnail 6011d is displayed in a larger size than the thumbnail 6011a.
  • the electronic device can adjust the parameters of the decision model according to the preferred images obtained by modifying the continuous shooting, reduce the weight of the "smile" image feature in the decision model, and "laugh.”
  • the weight of the image feature is increased, and the adjusted decision model is obtained.
  • the electronic device selects from the image corresponding to the thumbnail 6011 according to the adjusted decision model, it can select the image that contains the feature of the “laughing” image, that is, the image corresponding to the thumbnail 6011d, and The thumbnail 6011d is displayed in a larger size.
  • the electronic device may also display a recommendation mark 6011d-1 on the thumbnail 6011d, indicating that the image corresponding to the thumbnail 6011d is a preferred image selected from multiple images.
  • the thumbnail 6011d of the image selected by the electronic device according to the adjusted decision model may also be the same size as other thumbnails, with different frames
  • the weight adjustment can also be based on other image features, such as “front face” and “side face” image features, “open eyes”, “closed” “Eyes”, “Laughing Eyes” image features, etc.
  • the adjustment of the weight can also be aimed at image characteristics in other scenes, for example, the depth of field of the image in a macro shooting scene of a bee or a butterfly, and another example, the composition of an image in a landscape shooting scene.
  • Image features include image semantic features, shooting scenes and image parameters.
  • the adjustment of weights is not limited to these image semantic features, but can also target image parameters, such as sharpness, illumination uniformity, contrast, saturation, brightness, richness of detail, whether it is overexposed or too dark, whether there are color blocks, whether it is biased or not. Color and whether it is too cold.
  • image parameters such as sharpness, illumination uniformity, contrast, saturation, brightness, richness of detail, whether it is overexposed or too dark, whether there are color blocks, whether it is biased or not. Color and whether it is too cold.
  • the embodiment of the present application does not limit the image feature for which the weight is adjusted.
  • the first image group may also include images corresponding to thumbnails 6011a, 6011b, 6011c, and 6011d.
  • the first image may include a preferred image, that is, an image corresponding to the thumbnail 6011d.
  • FIG. 13 is a flowchart of a method for adjusting parameters of a decision model provided by an embodiment of the present application. As shown in Fig. 13, the method includes steps S101 to S108.
  • the electronic device shoots multiple images through the continuous shooting function.
  • the electronic device selects a preferred image from the multiple images according to the decision model.
  • the electronic device detects and records the preferred image selected by the decision model and the modified preferred image.
  • steps S101 to S103 reference may be made to the related description of the user interface provided in FIGS. 1 to 4, which will not be repeated here.
  • the electronic device detects and records the deleted, browsed, favorited, and shared images.
  • images that are deleted, browsed, favorited, and shared may also include images that are edited, printed, remarks, and reminders.
  • the electronic device detects and records the face image in the gallery.
  • the face image in the gallery may also be updated according to the update of the captured image.
  • the embodiment of the present application does not limit the execution sequence of steps S103, S104, and S105.
  • S106 The electronic device adjusts the parameters of the decision model according to the user feedback every preset time or detects a preset number of user feedback records.
  • the electronic device selects a preferred image from the multiple images obtained by the continuous shooting function according to the adjusted decision model.
  • the electronic device selects a preferred image from the images in the gallery according to the adjusted decision model, and displays the selected preferred image separately from other images.
  • steps S107 to S108 reference may be made to the related description of the user interface provided in FIGS. 10 to 12, which will not be repeated here.
  • the decision model may include any one or more of the following parameters: 1 Different image features between the preferred image selected by the decision model and the modified preferred image, 2 Deleted, browsed, favorited, and shared Image feature, 3The image feature of the face image in the gallery.
  • the decision model also contains the weights corresponding to the included parameters. The following specifically introduces the process of adjusting the parameters of the decision model in step S106.
  • the electronic device can detect different image features between the preferred image selected by the decision model and the modified preferred image. For example, the electronic device may detect that the preferred image selected by the decision model contains the "smile” image feature, and the modified preferred image contains the "big laugh” image feature. Then the electronic device adjusts the weight of the "big laugh” image feature in the decision model to be larger, and adjusts the weight of the "smile” image feature to be smaller. When using the adjusted decision model to select the best continuous shooting in a portrait scene, the electronic device can select an image that contains the image feature of "laughing".
  • the electronic device can detect that the preferred image selected by the decision model contains the image features of the diagonal composition, and the modified preferred image contains the image features of the central composition. Then the electronic device adjusts the weight of the image feature of the central composition in the decision model to be larger, and adjusts the weight of the image feature of the diagonal composition to be smaller.
  • the electronic device can select an image that contains the image characteristics of the central composition.
  • the electronic device may input the label value (for example, a numerical value) indicating the operation of the first user, the preferred image (second image) selected by the decision model, and the modified preferred image (third image) into the decision model,
  • the decision model may adjust the decision model according to the label indicating the operation of the first user, the second image, and the third image.
  • the electronic device can periodically (for example, every 24 hours) record the number of deletions, the number of browsing, and the number of collections and sharing of images in the gallery.
  • the electronic device can respectively set corresponding tag values for deletion, browsing, collection, and sharing. After that, the electronic device can identify the shooting scene of the operated image, and adjust the weight of the corresponding image feature according to the operated image and the tag value corresponding to the image.
  • An example of the tag value corresponding to a user operation is given below.
  • the electronic device assigns a tag value of 0 to the image.
  • the electronic device assigns a tag value of 1 to the image.
  • An image is viewed multiple times, and the label value is the product of 1 and the number of times.
  • the electronic device assigns a tag value of 2 to the image.
  • the electronic device assigns a tag value of 3 to the image.
  • An image is shared multiple times, and the tag value is the product of 3 and the number of times.
  • image a, image b, and image c are all portrait scenes.
  • Image a contains the image feature of "not smiling", and when image a receives the delete operation, the label value 0 is assigned to image a.
  • the image b contains the "smile" image feature. If the image b receives two browsing operations, the label value 2 is assigned to the image a.
  • the image c contains the image feature of "Laughing”. If the image c receives two sharing operations, the label value 6 is assigned to the image c.
  • the electronic device can adjust the parameters of the decision-making model according to the deleted, browsed, favorited, and shared images and corresponding tag values.
  • the tag value may indicate the user operation performed on the image.
  • the tag value may be proportional to the weight corresponding to the image feature of the image. That is, the larger the label value, the larger the weight of the image feature corresponding to the image, and the smaller the label value, the smaller the weight of the image feature corresponding to the image.
  • the tag value of the image a is 0, and the electronic device may reduce the weight of the "not smiling" image feature contained in it.
  • the label value of the image b is 2, and the electronic device can keep the weight of the "smile" image feature contained in it unchanged.
  • the label value of the image c is 6, and the electronic device can increase the weight of the "laughing" image feature contained in it.
  • the electronic device can select an image that contains the image feature of “laughing”.
  • the embodiment of the present application takes a portrait scene as an example for description, but the embodiment of the present application is not limited to a portrait scene, and may also be corresponding image features in other scenes.
  • the composition features in a landscape shooting scene the embodiment of the present application does not limit the specific shooting scene and image features.
  • the electronic device adjusts the parameters in the decision-making model.
  • the decision model can also include multiple facial features and weights corresponding to the facial features.
  • the electronic device may use the decision model to detect the expression score of the face in the image, for example, obtain the expression score of the face through face recognition.
  • Each face feature corresponds to a face image, and the electronic device can count the number (or proportion) of each face image corresponding to the image in the gallery, that is, count the number (or proportion) of the corresponding image of each face feature in the gallery ).
  • the electronic device adjusts the weight of the facial features in the decision model according to the number of corresponding images. Specifically, the greater the number of corresponding images in the gallery, the greater the weight of the first face feature, and the smaller the number of corresponding images in the gallery, the smaller the weight of the first face feature.
  • the proportion of images containing the first face feature in the gallery refers to the proportion of the number of images containing the first face feature in all images in the gallery.
  • the first facial feature is the facial feature that contains the largest number of images in the gallery, and the gallery contains the images stored in the electronic device.
  • the stored images include, for example, images taken by a camera.
  • the stored images may also include images downloaded locally and images received, sent, favorited, edited, printed, and remarked in an application (for example, a WeChat application).
  • the greater the expression score of the face in the image the greater the probability that the image will be selected as the preferred image.
  • the greater the weight of a face feature the greater the probability that an image containing the face feature will be selected as the preferred image.
  • the electronic device performs continuous shooting selection according to the adjusted decision model to obtain a preferred image.
  • the preferred image may include a face image with the largest number of corresponding images in the gallery, and the face image has the highest expression score.
  • face feature a indicates Lisa's face image
  • face image B indicates Rechel's face image
  • face image C indicates Kate's face image.
  • the electronic device obtains through face recognition that the images in the gallery include face image A, face image B, and face image C, and detects the number of images corresponding to each face image in the gallery.
  • the face image A, the face image B, and the face image C correspond to the face feature a, the face feature b, and the face feature c, respectively.
  • the number of images corresponding to the face image A in the gallery is 50, that is, the 50 images all contain the face image A, that is, the face feature a is included.
  • the number of images corresponding to face image B (face feature b) in the gallery is 30, and the number of images corresponding to face image C (face feature c) in the gallery is 10.
  • the electronic device adjusts the parameters of the decision model according to the face images in the gallery, the weight of the face feature a corresponding to the face image A is the largest, and the weight of the face feature b corresponding to the face image B is the second largest, and the face image The face feature c corresponding to C has the smallest weight.
  • the electronic device performs continuous shooting selection according to the adjusted decision model to obtain a preferred image.
  • the adjusted decision model may also include only the face feature a corresponding to the face image A and the face feature b corresponding to the face image B.
  • the electronic device adjusts the parameters of the decision model according to the face images in the gallery, the weight of the face feature a corresponding to the face image A is the largest, and the weight of the face feature b corresponding to the face image B is the smallest.
  • the first face feature may be the face feature that contains the largest number of images in the gallery.
  • the number of the first face feature in the previous example may be multiple, including the person with the largest number of images in the gallery.
  • the face feature a and the face feature b are the face feature a corresponding to Lisa's face image and the face feature b corresponding to Rechel's face image.
  • the electronic device may use image semantic features and/or image parameters to determine the facial expression score.
  • a face detected by an electronic device contains image features of “smiling” and “eyes open”, and the sharpness, uniformity of illumination, and richness of details have reached the set threshold.
  • the electronic device can be based on the detected image semantics.
  • the features and image parameters get the facial expression score.
  • the expression score of the face can also be determined according to the composition of the face image in the image.
  • the adjusted decision model may also include the facial expression score and corresponding weight corresponding to each face image.
  • the process of updating the decision model may be to combine the face image (for example, the face image A in the previous example, corresponding to The weight of the facial expression score of the face image A (face feature) in the decision model is adjusted to be larger.
  • the updated decision model is used for image selection, and the electronic device can select from a set of images according to the updated decision model.
  • the image with the highest facial expression score is the facial image A.
  • the electronic device uses the face images in the gallery to adjust the parameters of the decision-making model, and uses the adjusted decision-making model to perform continuous shooting selection in a portrait scene to obtain a preferred image.
  • the preferred image may include a face image with the largest number of corresponding images in the gallery, and the face image has the highest expression score. The image selected in this way is more in line with the user's habit, reducing the user's manual reselection from multiple images, thereby improving convenience.
  • the electronic device obtains the face image in the gallery through face recognition.
  • the electronic device can also adjust the decision according to the face image in the gallery after detecting the user operation to start the continuous shooting function, for example, as shown in (B) in Figure 1 when the long-press operation of the shooting control 202 ends.
  • the parameters of the model are selected according to the adjusted decision-making model to obtain the preferred image in this continuous shooting.
  • the electronic device detects that the continuous shooting function is activated to obtain multiple images, it can obtain the three face images that contain the most images in the gallery.
  • the electronic device can detect whether any of the three facial images is included in the multiple images obtained by continuous shooting.
  • the electronic device can increase the weights of the three facial images corresponding to the facial features in the decision model.
  • the electronic device uses the adjusted decision model to select a preferred image from a plurality of images, and the three facial images in the preferred images have the highest expression scores.
  • the parameters of the decision model are adjusted in real time, which can improve the accuracy of the adjusted decision model for continuous shooting.
  • the adjusted decision model can also determine the proportion of the figure and body corresponding to the facial image.
  • the electronic device uses the face images in the gallery to adjust the parameters of the decision-making model, and uses the adjusted decision-making model to perform continuous shooting selection in a portrait scene to obtain a preferred image.
  • the preferred image may include the face image with the largest number of images in the gallery, and the face image corresponding to the face image has the highest score for the proportion of the figure to the body.
  • the electronic device can also use image semantic features and/or image parameters to determine the portrait-to-body ratio score of the facial image. For example, the electronic device detects features of various parts of a complete portrait of a certain face image (such as "arm” image features, "leg” image features, etc.), and then calculates the body proportion score of the complete portrait based on each part of the complete portrait. Not limited to the above examples, the electronic device may also determine the body proportion score of the complete portrait according to other algorithms.
  • user feedback can be used as a training sample to train the decision model to obtain an adjusted decision model.
  • the decision model may be obtained by training through the original training sample set, and the original training sample set may contain multiple images.
  • the electronic device can use user feedback as a new training sample set to retrain the decision model to obtain an adjusted decision model.
  • the process of adjusting the parameters of the decision model described in 123 can be performed separately, or two or more update processes can be performed in the process of adjusting the parameters of the decision model at a time. Not limited.
  • FIG. 14 is a schematic diagram of a training principle of a decision model provided by an embodiment of the present application.
  • Figure 14 provides an example of using knowledge distillation to train the adjusted decision model.
  • the electronic device uses the original training sample set to train the decision model.
  • the trained decision model can be used as a teacher network.
  • the electronic equipment can use some features of the teacher network in the process of training the adjusted decision model.
  • the electronic device can perform a softmax transformation on the teacher network to obtain a soft target.
  • the soft target can represent some features in the original training sample set, and is used to train the decision model to obtain an adjusted decision model.
  • the electronic device can jointly train the decision model through the soft target and the new training sample set to obtain the adjusted decision model.
  • the training process can be implemented using the back propagation algorithm, that is, the method of back propagation of the loss function is trained. For details, please refer to the concept description part, which will not be repeated here.
  • the embodiment of the present application uses knowledge distillation as an example to introduce the decision model training process, but the embodiment of the present application is not limited to the knowledge distillation method for training, and other methods may also be used.
  • FIG. 15 is a schematic structural diagram of an electronic device 100 provided by an embodiment of the present application.
  • the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, and an antenna 2.
  • Mobile communication module 150 wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, earphone jack 170D, sensor module 180, buttons 190, motor 191, indicator 192, camera 193, display screen 194, and Subscriber identification module (subscriber identification module, SIM) card interface 195, etc.
  • SIM Subscriber identification module
  • the sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, and ambient light Sensor 180L, bone conduction sensor 180M, etc.
  • the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100.
  • the electronic device 100 may include more or fewer components than shown, or combine certain components, or split certain components, or arrange different components.
  • the illustrated components can be implemented in hardware, software, or a combination of software and hardware.
  • the processor 110 may include one or more processing units.
  • the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), and an image signal processor. (image signal processor, ISP), controller, memory, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (NPU) Wait.
  • AP application processor
  • modem processor modem processor
  • GPU graphics processing unit
  • image signal processor image signal processor
  • ISP image signal processor
  • controller memory
  • video codec digital signal processor
  • DSP digital signal processor
  • NPU neural-network processing unit
  • the different processing units may be independent devices or integrated in one or more processors.
  • the controller may be the nerve center and command center of the electronic device 100.
  • the controller can generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.
  • a memory may also be provided in the processor 110 to store instructions and data.
  • the memory in the processor 110 is a cache memory.
  • the memory can store instructions or data that the processor 110 has just used or used cyclically. If the processor 110 needs to use the instruction or data again, it can be directly called from the memory. Repeated accesses are avoided, the waiting time of the processor 110 is reduced, and the efficiency of the system is improved.
  • the processor 110 may include one or more interfaces.
  • Interfaces can include integrated circuit (I2C) interfaces, integrated circuit built-in audio (inter-integrated circuit sound, I2S) interfaces, pulse code modulation (PCM) interfaces, universal asynchronous transmitters receiver/transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and / Or Universal Serial Bus (USB) interface, etc.
  • I2C integrated circuit
  • I2S integrated circuit built-in audio
  • PCM pulse code modulation
  • UART mobile industry processor interface
  • MIPI mobile industry processor interface
  • GPIO general-purpose input/output
  • SIM subscriber identity module
  • USB Universal Serial Bus
  • the I2C interface is a bidirectional synchronous serial bus, which includes a serial data line (SDA) and a serial clock line (SCL).
  • the processor 110 may include multiple sets of I2C buses.
  • the processor 110 may couple the touch sensor 180K, the charger, the flash, the camera 193, etc., respectively through different I2C bus interfaces.
  • the processor 110 may couple the touch sensor 180K through an I2C interface, so that the processor 110 and the touch sensor 180K communicate through an I2C bus interface to implement the touch function of the electronic device 100.
  • the I2S interface can be used for audio communication.
  • the processor 110 may include multiple sets of I2S buses.
  • the processor 110 may be coupled with the audio module 170 through an I2S bus to implement communication between the processor 110 and the audio module 170.
  • the audio module 170 may transmit audio signals to the wireless communication module 160 through an I2S interface, so as to realize the function of answering calls through a Bluetooth headset.
  • the PCM interface can also be used for audio communication to sample, quantize and encode analog signals.
  • the audio module 170 and the wireless communication module 160 may be coupled through a PCM bus interface.
  • the audio module 170 may also transmit audio signals to the wireless communication module 160 through the PCM interface, so as to realize the function of answering calls through the Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.
  • the UART interface is a universal serial data bus used for asynchronous communication.
  • the bus can be a two-way communication bus. It converts the data to be transmitted between serial communication and parallel communication.
  • the UART interface is generally used to connect the processor 110 and the wireless communication module 160.
  • the processor 110 communicates with the Bluetooth module in the wireless communication module 160 through the UART interface to realize the Bluetooth function.
  • the audio module 170 may transmit audio signals to the wireless communication module 160 through a UART interface, so as to realize the function of playing music through a Bluetooth headset.
  • the MIPI interface can be used to connect the processor 110 with the display screen 194, the camera 193 and other peripheral devices.
  • the MIPI interface includes a camera serial interface (camera serial interface, CSI), a display serial interface (display serial interface, DSI), and so on.
  • the processor 110 and the camera 193 communicate through a CSI interface to implement the shooting function of the electronic device 100.
  • the processor 110 and the display screen 194 communicate through a DSI interface to realize the display function of the electronic device 100.
  • the GPIO interface can be configured through software.
  • the GPIO interface can be configured as a control signal or as a data signal.
  • the GPIO interface can be used to connect the processor 110 with the camera 193, the display screen 194, the wireless communication module 160, the audio module 170, the sensor module 180, and so on.
  • the GPIO interface can also be configured as an I2C interface, I2S interface, UART interface, MIPI interface, etc.
  • the USB interface 130 is an interface that complies with the USB standard specification, and specifically may be a Mini USB interface, a Micro USB interface, a USB Type C interface, and so on.
  • the USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used to transfer data between the electronic device 100 and peripheral devices. It can also be used to connect headphones and play audio through the headphones. This interface can also be used to connect to other electronic devices, such as AR devices.
  • the interface connection relationship between the modules illustrated in the embodiment of the present invention is merely a schematic description, and does not constitute a structural limitation of the electronic device 100.
  • the electronic device 100 may also adopt different interface connection modes in the foregoing embodiments, or a combination of multiple interface connection modes.
  • the charging management module 140 is used to receive charging input from the charger.
  • the charger can be a wireless charger or a wired charger.
  • the charging management module 140 may receive the charging input of the wired charger through the USB interface 130.
  • the charging management module 140 may receive the wireless charging input through the wireless charging coil of the electronic device 100. While the charging management module 140 charges the battery 142, it can also supply power to the electronic device through the power management module 141.
  • the power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110.
  • the power management module 141 receives input from the battery 142 and/or the charge management module 140, and supplies power to the processor 110, the internal memory 121, the external memory, the display screen 194, the camera 193, and the wireless communication module 160.
  • the power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle times, and battery health status (leakage, impedance).
  • the power management module 141 may also be provided in the processor 110.
  • the power management module 141 and the charging management module 140 may also be provided in the same device.
  • the wireless communication function of the electronic device 100 can be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor, and the baseband processor.
  • the antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals.
  • Each antenna in the electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization.
  • Antenna 1 can be multiplexed as a diversity antenna of a wireless local area network.
  • the antenna can be used in combination with a tuning switch.
  • the mobile communication module 150 can provide a wireless communication solution including 2G/3G/4G/5G and the like applied to the electronic device 100.
  • the mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc.
  • the mobile communication module 150 can receive electromagnetic waves by the antenna 1, and perform processing such as filtering, amplifying and transmitting the received electromagnetic waves to the modem processor for demodulation.
  • the mobile communication module 150 can also amplify the signal modulated by the modem processor, and convert it into electromagnetic wave radiation via the antenna 1.
  • at least part of the functional modules of the mobile communication module 150 may be provided in the processor 110.
  • at least part of the functional modules of the mobile communication module 150 and at least part of the modules of the processor 110 may be provided in the same device.
  • the modem processor may include a modulator and a demodulator.
  • the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal.
  • the demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor.
  • the application processor outputs a sound signal through an audio device (not limited to the speaker 170A, the receiver 170B, etc.), or displays an image or video through the display screen 194.
  • the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be provided in the same device as the mobile communication module 150 or other functional modules.
  • the wireless communication module 160 can provide applications on the electronic device 100 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), and global navigation satellites.
  • WLAN wireless local area networks
  • BT wireless fidelity
  • GNSS global navigation satellite system
  • FM frequency modulation
  • NFC near field communication technology
  • infrared technology infrared, IR
  • the wireless communication module 160 may be one or more devices integrating at least one communication processing module.
  • the wireless communication module 160 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110.
  • the wireless communication module 160 may also receive the signal to be sent from the processor 110, perform frequency modulation, amplify it, and convert it into electromagnetic waves to radiate through the antenna 2.
  • the antenna 1 of the electronic device 100 is coupled with the mobile communication module 150, and the antenna 2 is coupled with the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology.
  • the wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), broadband Code division multiple access (wideband code division multiple access, WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC , FM, and/or IR technology, etc.
  • the GNSS may include global positioning system (GPS), global navigation satellite system (GLONASS), Beidou navigation satellite system (BDS), quasi-zenith satellite system (quasi -zenith satellite system, QZSS) and/or satellite-based augmentation systems (SBAS).
  • GPS global positioning system
  • GLONASS global navigation satellite system
  • BDS Beidou navigation satellite system
  • QZSS quasi-zenith satellite system
  • SBAS satellite-based augmentation systems
  • the electronic device 100 implements a display function through a GPU, a display screen 194, an application processor, and the like.
  • the GPU is a microprocessor for image processing, connected to the display 194 and the application processor.
  • the GPU is used to perform mathematical and geometric calculations for graphics rendering.
  • the processor 110 may include one or more GPUs, which execute program instructions to generate or change display information.
  • the display screen 194 is used to display images, videos, and the like.
  • the display screen 194 includes a display panel.
  • the display panel can use liquid crystal display (LCD), organic light-emitting diode (OLED), active matrix organic light-emitting diode or active-matrix organic light-emitting diode (active-matrix organic light-emitting diode).
  • LCD liquid crystal display
  • OLED organic light-emitting diode
  • active-matrix organic light-emitting diode active-matrix organic light-emitting diode
  • AMOLED flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diode (QLED), etc.
  • the electronic device 100 may include one or N display screens 194, and N is a positive integer greater than one.
  • the electronic device 100 can realize a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, and an application processor.
  • the ISP is used to process the data fed back by the camera 193. For example, when taking a picture, the shutter is opened, the light is transmitted to the photosensitive element of the camera through the lens, the light signal is converted into an electrical signal, and the photosensitive element of the camera transmits the electrical signal to the ISP for processing and is converted into an image visible to the naked eye.
  • ISP can also optimize the image noise, brightness, and skin color. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene.
  • the ISP may be provided in the camera 193.
  • the camera 193 is used to capture still images or videos.
  • the object generates an optical image through the lens and is projected to the photosensitive element.
  • the photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor.
  • CMOS complementary metal-oxide-semiconductor
  • the photosensitive element converts the optical signal into an electrical signal, and then transfers the electrical signal to the ISP to convert it into a digital image signal.
  • ISP outputs digital image signals to DSP for processing.
  • DSP converts digital image signals into standard RGB, YUV and other formats of image signals.
  • the electronic device 100 may include one or N cameras 193, and N is a positive integer greater than one.
  • Digital signal processors are used to process digital signals. In addition to digital image signals, they can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the energy of the frequency point.
  • Video codecs are used to compress or decompress digital video.
  • the electronic device 100 may support one or more video codecs. In this way, the electronic device 100 can play or record videos in multiple encoding formats, such as: moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, and so on.
  • MPEG moving picture experts group
  • MPEG2 MPEG2, MPEG3, MPEG4, and so on.
  • NPU is a neural-network (NN) computing processor.
  • NN neural-network
  • applications such as intelligent cognition of the electronic device 100 can be realized, such as image recognition, face recognition, voice recognition, text understanding, and so on.
  • the NPU can also implement the decision model provided in the embodiments of the present application.
  • the external memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100.
  • the external memory card communicates with the processor 110 through the external memory interface 120 to realize the data storage function. For example, save music, video and other files in an external memory card.
  • the internal memory 121 may be used to store computer executable program code, where the executable program code includes instructions.
  • the processor 110 executes various functional applications and data processing of the electronic device 100 by running instructions stored in the internal memory 121.
  • the internal memory 121 may include a storage program area and a storage data area.
  • the storage program area can store an operating system, at least one application program (such as a sound playback function, an image playback function, etc.) required by at least one function.
  • the data storage area can store data (such as audio data, phone book, etc.) created during the use of the electronic device 100.
  • the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), and the like.
  • UFS universal flash storage
  • the electronic device 100 can implement audio functions through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the earphone interface 170D, and the application processor. For example, music playback, recording, etc.
  • the audio module 170 is used to convert digital audio information into an analog audio signal for output, and is also used to convert an analog audio input into a digital audio signal.
  • the audio module 170 can also be used to encode and decode audio signals.
  • the audio module 170 may be provided in the processor 110, or part of the functional modules of the audio module 170 may be provided in the processor 110.
  • the speaker 170A also called “speaker” is used to convert audio electrical signals into sound signals.
  • the electronic device 100 can listen to music through the speaker 170A, or listen to a hands-free call.
  • the receiver 170B also called “earpiece” is used to convert audio electrical signals into sound signals.
  • the electronic device 100 answers a call or voice message, it can receive the voice by bringing the receiver 170B close to the human ear.
  • the microphone 170C also called “microphone”, “microphone”, is used to convert sound signals into electrical signals.
  • the user can make a sound by approaching the microphone 170C through the human mouth, and input the sound signal into the microphone 170C.
  • the electronic device 100 may be provided with at least one microphone 170C. In other embodiments, the electronic device 100 may be provided with two microphones 170C, which can implement noise reduction functions in addition to collecting sound signals. In other embodiments, the electronic device 100 may also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, and realize directional recording functions.
  • the earphone interface 170D is used to connect wired earphones.
  • the earphone interface 170D may be a USB interface 130, or a 3.5mm open mobile terminal platform (OMTP) standard interface, and a cellular telecommunications industry association (cellular telecommunications industry association of the USA, CTIA) standard interface.
  • OMTP open mobile terminal platform
  • CTIA cellular telecommunications industry association of the USA, CTIA
  • the pressure sensor 180A is used to sense the pressure signal and can convert the pressure signal into an electrical signal.
  • the pressure sensor 180A may be provided on the display screen 194.
  • the capacitive pressure sensor may include at least two parallel plates with conductive materials.
  • the electronic device 100 determines the intensity of the pressure based on the change in capacitance.
  • the electronic device 100 detects the intensity of the touch operation according to the pressure sensor 180A.
  • the electronic device 100 may also calculate the touched position according to the detection signal of the pressure sensor 180A.
  • touch operations that act on the same touch position but have different touch operation strengths may correspond to different operation instructions. For example, when a touch operation whose intensity of the touch operation is less than the first pressure threshold is applied to the short message application icon, an instruction to view the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, an instruction to create a new short message is executed.
  • the gyro sensor 180B may be used to determine the movement posture of the electronic device 100.
  • the angular velocity of the electronic device 100 around three axes ie, x, y, and z axes
  • the gyro sensor 180B can be used for image stabilization.
  • the gyro sensor 180B detects the shake angle of the electronic device 100, calculates the distance that the lens module needs to compensate according to the angle, and allows the lens to counteract the shake of the electronic device 100 through reverse movement to achieve anti-shake.
  • the gyro sensor 180B can also be used for navigation and somatosensory game scenes.
  • the air pressure sensor 180C is used to measure air pressure.
  • the electronic device 100 calculates the altitude based on the air pressure value measured by the air pressure sensor 180C to assist positioning and navigation.
  • the magnetic sensor 180D includes a Hall sensor.
  • the electronic device 100 may use the magnetic sensor 180D to detect the opening and closing of the flip holster.
  • the electronic device 100 can detect the opening and closing of the flip according to the magnetic sensor 180D.
  • features such as automatic unlocking of the flip cover are set.
  • the acceleration sensor 180E can detect the magnitude of the acceleration of the electronic device 100 in various directions (generally three axes). When the electronic device 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of electronic devices, and be used in applications such as horizontal and vertical screen switching, pedometers and so on.
  • the electronic device 100 can measure the distance by infrared or laser. In some embodiments, when shooting a scene, the electronic device 100 may use the distance sensor 180F to measure the distance to achieve fast focusing.
  • the proximity light sensor 180G may include, for example, a light emitting diode (LED) and a light detector such as a photodiode.
  • the light emitting diode may be an infrared light emitting diode.
  • the electronic device 100 emits infrared light to the outside through the light emitting diode.
  • the electronic device 100 uses a photodiode to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is an object near the electronic device 100. When insufficient reflected light is detected, the electronic device 100 can determine that there is no object near the electronic device 100.
  • the electronic device 100 can use the proximity light sensor 180G to detect that the user holds the electronic device 100 close to the ear to talk, so as to automatically turn off the screen to save power.
  • the proximity light sensor 180G can also be used in leather case mode, and the pocket mode will automatically unlock and lock the screen.
  • the ambient light sensor 180L is used to sense the brightness of the ambient light.
  • the electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived brightness of the ambient light.
  • the ambient light sensor 180L can also be used to automatically adjust the white balance when taking pictures.
  • the ambient light sensor 180L can also cooperate with the proximity light sensor 180G to detect whether the electronic device 100 is in the pocket to prevent accidental touch.
  • the fingerprint sensor 180H is used to collect fingerprints.
  • the electronic device 100 can use the collected fingerprint characteristics to realize fingerprint unlocking, access application locks, fingerprint photographs, fingerprint answering calls, and so on.
  • the temperature sensor 180J is used to detect temperature.
  • the electronic device 100 uses the temperature detected by the temperature sensor 180J to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor 180J exceeds a threshold value, the electronic device 100 reduces the performance of the processor located near the temperature sensor 180J, so as to reduce power consumption and implement thermal protection.
  • the electronic device 100 when the temperature is lower than another threshold, the electronic device 100 heats the battery 142 to avoid abnormal shutdown of the electronic device 100 due to low temperature.
  • the electronic device 100 boosts the output voltage of the battery 142 to avoid abnormal shutdown caused by low temperature.
  • Touch sensor 180K also called “touch panel”.
  • the touch sensor 180K may be disposed on the display screen 194, and the touch screen is composed of the touch sensor 180K and the display screen 194, which is also called a “touch screen”.
  • the touch sensor 180K is used to detect touch operations acting on or near it.
  • the touch sensor can pass the detected touch operation to the application processor to determine the type of touch event.
  • the visual output related to the touch operation can be provided through the display screen 194.
  • the touch sensor 180K may also be disposed on the surface of the electronic device 100, which is different from the position of the display screen 194.
  • the bone conduction sensor 180M can acquire vibration signals.
  • the bone conduction sensor 180M can obtain the vibration signal of the vibrating bone mass of the human voice.
  • the bone conduction sensor 180M can also contact the human pulse and receive the blood pressure pulse signal.
  • the bone conduction sensor 180M may also be provided in the earphone, combined with the bone conduction earphone.
  • the audio module 170 can parse the voice signal based on the vibration signal of the vibrating bone block of the voice obtained by the bone conduction sensor 180M, and realize the voice function.
  • the application processor may analyze the heart rate information based on the blood pressure beating signal obtained by the bone conduction sensor 180M, and realize the heart rate detection function.
  • the button 190 includes a power-on button, a volume button, and so on.
  • the button 190 may be a mechanical button. It can also be a touch button.
  • the electronic device 100 may receive key input, and generate key signal input related to user settings and function control of the electronic device 100.
  • the motor 191 can generate vibration prompts.
  • the motor 191 can be used for incoming call vibration notification, and can also be used for touch vibration feedback.
  • touch operations that act on different applications can correspond to different vibration feedback effects.
  • Acting on touch operations in different areas of the display screen 194, the motor 191 can also correspond to different vibration feedback effects.
  • Different application scenarios for example: time reminding, receiving information, alarm clock, games, etc.
  • the touch vibration feedback effect can also support customization.
  • the indicator 192 may be an indicator light, which may be used to indicate the charging status, power change, or to indicate messages, missed calls, notifications, and so on.
  • the SIM card interface 195 is used to connect to the SIM card.
  • the SIM card can be inserted into the SIM card interface 195 or pulled out from the SIM card interface 195 to achieve contact and separation with the electronic device 100.
  • the electronic device 100 may support 1 or N SIM card interfaces, and N is a positive integer greater than 1.
  • the SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, etc.
  • the same SIM card interface 195 can insert multiple cards at the same time. The types of the multiple cards can be the same or different.
  • the SIM card interface 195 can also be compatible with different types of SIM cards.
  • the SIM card interface 195 may also be compatible with external memory cards.
  • the electronic device 100 interacts with the network through the SIM card to implement functions such as call and data communication.
  • the electronic device 100 adopts an eSIM, that is, an embedded SIM card.
  • the eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100.
  • the software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture.
  • the embodiment of the present invention takes an Android system with a layered architecture as an example to illustrate the software structure of the electronic device 100 by way of example.
  • FIG. 16 is a software structure block diagram of an electronic device 100 provided by an embodiment of the present application.
  • the layered architecture divides the software into several layers, and each layer has a clear role and division of labor. Communication between layers through software interface.
  • the Android system is divided into four layers, from top to bottom, the application layer, the application framework layer, the Android runtime and system library, and the kernel layer.
  • the application layer can include a series of application packages.
  • the application package may include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message, etc.
  • the application framework layer provides an application programming interface (application programming interface, API) and a programming framework for applications in the application layer.
  • the application framework layer includes some predefined functions.
  • the application framework layer can include a window manager, a content provider, a view system, a phone manager, a resource manager, and a notification manager.
  • the window manager is used to manage window programs.
  • the window manager can obtain the size of the display, determine whether there is a status bar, lock the screen, take a screenshot, etc.
  • the content provider is used to store and retrieve data and make these data accessible to applications.
  • the data may include videos, images, audios, phone calls made and received, browsing history and bookmarks, phone book, etc.
  • the view system includes visual controls, such as controls that display text, controls that display pictures, and so on.
  • the view system can be used to build applications.
  • the display interface can be composed of one or more views.
  • a display interface that includes a short message notification icon may include a view that displays text and a view that displays pictures.
  • the phone manager is used to provide the communication function of the electronic device 100. For example, the management of the call status (including connecting, hanging up, etc.).
  • the resource manager provides various resources for the application, such as localized strings, icons, pictures, layout files, video files, and so on.
  • the notification manager enables the application to display notification information in the status bar, which can be used to convey notification-type messages, and it can disappear automatically after a short stay without user interaction.
  • the notification manager is used to notify download completion, message reminders, and so on.
  • the notification manager can also be a notification that appears in the status bar at the top of the system in the form of a chart or a scroll bar text, such as a notification of an application running in the background, or a notification that appears on the screen in the form of a dialog window. For example, text messages are prompted in the status bar, prompt sounds, electronic devices vibrate, and indicator lights flash.
  • Android Runtime includes core libraries and virtual machines. Android runtime is responsible for the scheduling and management of the Android system.
  • the core library consists of two parts: one part is the function functions that the java language needs to call, and the other part is the core library of Android.
  • the application layer and the application framework layer run in a virtual machine.
  • the virtual machine executes the java files of the application layer and the application framework layer as binary files.
  • the virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.
  • the system library can include multiple functional modules. For example: surface manager (surface manager), media library (Media Libraries), three-dimensional graphics processing library (for example: OpenGL ES), 2D graphics engine (for example: SGL), etc.
  • the surface manager is used to manage the display subsystem and provides a combination of 2D and 3D layers for multiple applications.
  • the media library supports playback and recording of a variety of commonly used audio and video formats, as well as still image files.
  • the media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.
  • the 3D graphics processing library is used to realize 3D graphics drawing, image rendering, synthesis, and layer processing.
  • the 2D graphics engine is a drawing engine for 2D drawing.
  • the kernel layer is the layer between hardware and software.
  • the kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.
  • the corresponding hardware interrupt is sent to the kernel layer.
  • the kernel layer processes the touch operation into the original input event (including touch coordinates, time stamp of the touch operation, etc.).
  • the original input events are stored in the kernel layer.
  • the application framework layer obtains the original input event from the kernel layer and identifies the control corresponding to the input event. Taking the touch operation as a touch click operation, and the control corresponding to the click operation is the control of the camera application icon as an example, the camera application calls the interface of the application framework layer to start the camera application, and then starts the camera driver by calling the kernel layer.
  • the camera 193 captures still images or videos.
  • the term “when” can be interpreted as meaning “if" or “after” or “in response to determining" or “in response to detecting".
  • the phrase “when determining" or “if detected (statement or event)” can be interpreted as meaning “if determined" or “in response to determining" or “when detected (Condition or event stated)” or “in response to detection of (condition or event stated)”.
  • the computer may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer instructions may be transmitted from a website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium may be a magnetic medium, (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state hard disk).
  • the process can be completed by a computer program instructing relevant hardware.
  • the program can be stored in a computer readable storage medium. , May include the processes of the foregoing method embodiments.
  • the aforementioned storage media include: ROM or random storage RAM, magnetic disks or optical discs and other media that can store program codes.

Abstract

一种图像选优方法和电子设备。在该方法中，电子设备可检测与用户操作相关的反馈信息。该反馈信息可包含利用决策模型选出的优选图像和修改的优选图像。反馈信息还可包含被删除、被浏览、被收藏和被分享的图像和操作记录。反馈信息还可以包含图库中的人脸特征和包含人脸特征的图像在图库中的占比。电子设备根据这些反馈信息来调整用于进行图像选优的决策模型中的参数，以得到更新的决策模型。电子设备可根据更新的决策模型来进行图像选优。实施本技术方案，选出的优选图像更加符合用户习惯，从而可提高便利性。

Description

图像选优方法及电子设备
本申请要求于2019年9月29日提交中国专利局、申请号为201910936462.7、申请名称为“图像选优方法及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及终端技术领域，尤其涉及图像选优方法及电子设备。
背景技术
连拍功能(continuous shooting)是在短时间内连续拍摄多张图像，并将拍摄的图像存储在缓存的一种拍摄功能。现有技术中，越来越多电子设备(如智能手机、平板电脑等)支持连拍功能。电子设备可根据所拍摄图像的清晰度、构图、人物图像的表情等参数，从连拍得到的多张图像中选出最优的图像，并显示为优选图像。
然而，电子设备显示的优选图像往往并非连拍得到的多张图像中用户最喜欢的图像。用户需要从多张图像中重新选择优选图像，从而降低了便利性。
发明内容
本申请提供了一种图像选优方法及电子设备，电子设备可根据用户操作相关的反馈信息更新决策模型，并根据更新的决策模型进行图像选优，选出的优选图像更加符合用户习惯，从而可提高便利性。
第一方面，本申请提供了一种图像选优方法，该方法包括：电子设备检测第一反馈信息，该第一反馈信息包含多张图像和作用在该多张图像中的图像的用户操作；该电子设备根据该第一反馈信息，调整决策模型的参数以得到更新的决策模型；该电子设备根据该更新的决策模型，从第一图像组中选出第一图像作为该第一图像组的优选图像。
实施第一方面提供的方法，电子设备可依据用户操作来调整用于从多张图像中选出优选图像的决策模型中的参数。这样，通过更新的决策模型选出的优选图像更加符合用户习惯，减少用户手动从多张图像中重新选择的情况，从而可提高便利性。
本申请实施例中，第一反馈信息可包含：(1)决策模型选出的优选图像和修改的优选图像。(2)被删除、浏览、收藏和分享的图像。(3)图库中的人脸特征和包含人脸特征的图像在图库中的占比。
(1)决策模型选出的优选图像和修改的优选图像
具体的，该电子设备检测第一反馈信息之前，该方法还包括：该电子设备显示第一用户界面，该第一用户界面包含第二图像组，该第二图像组是连拍得到的图像，该第二图像组包含第二图像和第三图像，该第二图像是该电子设备根据该决策模型选出的该第二图像组的优选图像；该电子设备检测第一反馈信息，包括：该电子设备在该第一用户界面上检测第一用户操作，响应于该第一用户操作，该电子设备将该第二图像组的优选图像修改为 该第三图像；该第一反馈信息包括该第一用户操作、该第二图像和该第三图像。
例如，电子设备可检测到决策模型选出的优选图像包含“微笑”图像特征，而修改的优选图像包含“大笑”图像特征。则电子设备将决策模型中“大笑”图像特征的权重调大，将“微笑”图像特征的权重调小。使用调整后的决策模型进行人像场景下连拍选优时，电子设备可选出包含“大笑”图像特征的图像。
再例如，在风景拍摄场景下，电子设备可检测到决策模型选出的优选图像包含对角线构图的图像特征，而修改的优选图像包含中央构图的图像特征。则电子设备将决策模型中中央构图的图像特征的权重调大，将对角线构图的图像特征的权重调小。使用调整后的决策模型进行风景拍摄场景下连拍选优时，电子设备可选出包含中央构图的图像特征的图像。
其中，第一用户界面可以是连拍图像界面，在连拍图像界面上可包含连拍得到的图像。第一用户操作可包含作用在第二图像上选中标识的触摸操作、作用在图像展示区的触摸滑动操作、作用在第三图像的未选中标识的触摸操作、作用在确定控件的用户操作。响应于该第一用户操作，电子设备将连拍得到的图像的优选图像修改为第三图像。其中，修改前的优选图像可称为第二图像，修改后的优选图像可称为第三图像。
该连拍得到的图像可以是在相机应用界面上，响应于作用在拍摄控件上的长按操作，电子设备连拍得到的。电子设备可在连拍图像界面上响应于作用在缩略图控件的触摸操作，显示连拍得到的图像。
在电子设备将连拍得到的图像的优选图像修改为第三图像之后，电子设备可显示提示界面，以提示用户将根据反馈信息调整决策模型。例如，可提示：“已收到您的修改反馈，我们会根据修改推荐更符合您喜好的照片。”
(2)被删除、浏览、收藏和分享的图像
结合第一方面，在一些实施例中，该第一反馈信息包括对图库中的图像的操作记录和该操作记录对应的图像，该操作记录指示以下一项或多项操作：删除操作、浏览操作、收藏操作和分享操作。
本申请实施例中，被删除、浏览、收藏和分享的图像可以是图库中被删除、浏览、收藏和分享的图像，还可以是在其他应用例如即时通信应用(微信)中被删除、浏览、收藏和分享的图像。
不限于被删除、浏览、收藏和分享的图像，反馈信息还可以包含被编辑、打印、备注、提醒的图像。被编辑的图像例如包含被调整颜色、亮度等参数的图像。被打印的图像可以是电子设备请求打印机打印的图像。被备注的图像例如可以是在用户界面上被备注的图像。被提醒的图像例如在用户界面上设置被提醒的图像。
电子设备可周期性的(例如每隔24小时)记录图库中图像被删除、浏览的次数、收藏和分享的次数。电子设备可针对于删除、浏览、收藏和分享分别设置对应的标签值。之后，电子设备可识别被操作的图像的拍摄场景，根据被操作的图像和图像对应的标签值调整对应的图像特征的权重大小。
(3)图库中的人脸特征和包含人脸特征的图像在图库中的占比
结合第一方面，在一些实施例中，该第一反馈信息包括，第一人脸特征和包含该第一人脸特征的图像在图库中的占比；其中：该第一人脸特征是该图库中包含图像数量最多的 人脸特征，该图库中包含该电子设备中已存储的图像。
示例性的，人脸特征a指示Lisa的人脸图像，人脸图像B指示Rechel的人脸图像，人脸图像C指示Kate的人脸图像。
结合第一方面，在一些实施例中，该电子设备根据该第一反馈信息，调整决策模型的参数以得到更新的决策模型，包括：该电子设备将该第一人脸特征的人脸表情评分在该决策模型中所占的权重调大；该人脸表情评分用于对图像内人脸特征的表情进行评分；其中，该第一图像组中每张图像包含一个或多个人脸特征，该一个或多个人脸特征包含该第一人脸特征。
本申请实施例中，电子设备可以利用图像语义特征和/或图像参数确定人脸的表情评分。例如电子设备检测到的某一个人脸包含“微笑”图像特征、“睁眼”图像特征，且清晰度、光照均匀度和细节丰富程度均达到设定阈值，电子设备可根据检测到的图像语义特征和图像参数得到人脸的表情评分。
该优选图像中可包含图库中对应的图像数量最多的人脸图像，且该人脸图像的表情评分最高。这样选出的图像更加符合用户习惯，减少用户手动从多张图像中重新选择的情况，从而可提高便利性。
本申请实施例中，更新决策模型可以是检测到启动连拍功能的用户操作后，检测到作用在拍摄控件的长按操作结束时，才根据图库中的人脸图像来调整决策模型的参数，并根据调整的决策模型选择本次连拍得到图像中的优选图像。由于图库中的人脸图像和每个人脸图像的对应的图像数量根据所采集图像的累积而变化。在连拍功能执行后实时调整决策模型的参数，这样可提高调整后的决策模型进行连拍选优的精确度。
本申请实施例中，电子设备还可以是周期性的更新决策模型。
结合第一方面，在一些实施例中，该电子设备根据该第一反馈信息，调整决策模型的参数以得到更新的决策模型，包括：该电子设备将该第一人脸特征的人像身材比例评分在该决策模型中所占的权重调大；该人像身材比例评分用于对图像内人脸特征的身材比例进行评分；其中，该第一图像组中每张图像包含一个或多个人脸特征，该一个或多个人脸特征包含该第一人脸特征。
电子设备也可以利用图像语义特征和/或图像参数确定人脸图像的人像身材比例评分。例如电子设备检测到的某一个人脸图像的完整人像各部分特征(例如“胳膊”图像特征、“腿”图像特征等等)，然后根据完整人像各部分计算该完整人像的身材比例评分。
电子设备根据对应的图像的数量调整决策模型中人脸特征的权重。具体的，在图库中对应的图像的数量越多，人脸特征的权重越大，在图库中对应的图像的数量越少，人脸特征的权重越小。在图库中对应的图像的占比越大，人脸特征的权重越大，在图库中对应的图像的占比越小，人脸特征的权重越小。
本申请实施例中，电子设备可利用原始训练样本集对决策模型进行训练。训练得到的决策模型可作为教师网络。电子设备在训练调整后的决策模型过程中可使用教师网络的一些特征。具体的，电子设备可对教师网络进行softmax变换，获得软目标。该软目标可代表原始训练样本集中的一些特征，用于训练决策模型，得到调整后的决策模型。
其中，更新的决策模型可用于连拍选优场景，也可用于图库中缩略图的显示场景。
一、更新的决策模型用于连拍选优场景
具体的，该电子设备根据该更新的决策模型，从第一图像组中选出第一图像作为该第一图像组的优选图像之前，该方法还包括：该电子设备显示相机应用界面，该相机应用界面包含拍摄控件；响应于作用在该拍摄控件的第二用户操作，该电子设备连拍得到第一图像组；该电子设备根据该更新的决策模型，从第一图像组中选出第一图像作为该第一图像组的优选图像之后，该方法还包括：响应于用于显示该第一图像组的第三用户操作，该电子设备显示连拍图像界面，该连拍图像界面包含该第一图像和该第一图像组中每张图像的缩略图。
本申请实施例中，第一图像(例如包含“大笑”图像特征的图像)是根据第一反馈信息从第一图像组中选出的，更加符合用户的习惯和喜好，提高了为用户推荐图像的准确性。
其中，电子图像展示区还可以包含提示，用于提示根据第一反馈信息选出的图像，例如可提示“根据反馈推荐大笑表情的人脸”。
二、更新的决策模型用于图库中缩略图的显示场景
具体的，该电子设备根据该更新的决策模型，从第一图像组中选出第一图像作为该第一图像组的优选图像之前，该方法还包括：该电子设备从该图库中检测第一图像组；其中，该第一图像组的缩略图在图库应用界面上相邻显示，该第一图像组中每张图像均包含第一图像特征，该第一图像特征包含第二人脸特征或者第一拍摄场景；该电子设备根据该更新的决策模型，从第一图像组中选出第一图像作为该第一图像组的优选图像之后，该方法还包括：响应于作用在图库图标的第四用户操作，该电子设备显示该图库应用界面，该图库应用界面上包含该第一图像组中图像的缩略图；其中，该第一图像的缩略图的尺寸大于该第一图像组中其他图像的缩略图的尺寸。
本申请实施例中，第一图像组中的图像可包含相同图像特征，例如相同的人脸特征，即第二人脸特征。不限于第一图像组包含相同的人脸特征，还可以是包含相同的拍摄场景，例如第一拍摄场景。第一拍摄场景例如是风景拍摄场景。
可选的，电子设备还可以在第一图像的缩略图上还可以显示推荐标识，表示该缩略图对应的图像是从多张图像(第一图像组)中选出的优选图像。
结合第一方面，在一些实施例中，该电子设备根据该更新的决策模型，从第一图像组中选出第一图像作为该第一图像组的优选图像之前，该方法还包括：该电子设备显示第二用户界面，该第二用户界面包含多个图像特征选项和确定控件；其中，该多个图像特征选项中每个图像特征选项对应有图像特征；响应于作用在第一选项的第五用户操作，该电子设备将该第一选项由未选中状态显示为选中状态；该多个图像特征选项包含该第一选项；响应于作用在该确定控件的第六用户操作，该电子设备根据该第一选项对应的图像特征调整该决策模型的参数，以得到该更新的决策模型。
本申请实施例中，第二用户界面可以是提示框。示例性的，提示框包含多个图像特征选项：一组选项为不笑选项、微笑选项和大笑选项，另一组选项为正脸选项和侧脸选项，又一组选项为闭眼选项和睁眼选项。其中，每个选项均可包含选中状态和未选中状态。电子设备可响应于作用在选项上的用户操作，例如触摸操作，将选项的状态在选中状态和未选中状态之间切换显示。当不笑选项处于选中状态时，对应“不笑”图像特征的权重可被 调大，当不笑选项处于未选中状态时，对应“不笑”图像特征的权重可被调小。微笑选项对应“微笑”图像特征，大笑选项对应“大笑”图像特征。响应于作用在确定控件的用户操作，如触摸操作，电子设备可获得处于选中状态的选项，例如大笑选项、正脸选项和睁眼选项。作用在确定控件的用户操作，可称为第六用户操作。
本申请实施例中，由于这些图像特征是用户根据个人喜好选出的图像特征，更加符合用户习惯，减少用户手动从多张图像中重新选择的情况，从而可提高便利性。
第二方面，本申请实施例提供了一种电子设备，该电子设备包括：一个或多个处理器、存储器和显示屏；该存储器与该一个或多个处理器耦合，该存储器用于存储计算机程序代码，该计算机程序代码包括计算机指令，该一个或多个处理器调用该计算机指令以使得该电子设备执行：检测第一反馈信息，该第一反馈信息包含多张图像和作用在该多张图像中的图像的用户操作；根据该第一反馈信息，调整决策模型的参数以得到更新的决策模型；根据该更新的决策模型，从第一图像组中选出第一图像作为该第一图像组的优选图像。
第二方面提供的电子设备，可实现：依据用户操作来调整用于从多张图像中选出优选图像的决策模型中的参数。这样，通过更新的决策模型选出的优选图像更加符合用户习惯，减少用户手动从多张图像中重新选择的情况，从而可提高便利性。
结合第二方面，在一些实施例中，该一个或多个处理器，还用于调用该计算机指令以使得该电子设备执行：显示第一用户界面，该第一用户界面包含第二图像组，该第二图像组是连拍得到的图像，该第二图像组包含第二图像和第三图像，该第二图像是该电子设备根据该决策模型选出的该第二图像组的优选图像；该一个或多个处理器，具体用于调用该计算机指令以使得该电子设备执行：在该第一用户界面上检测第一用户操作，响应于该第一用户操作，将该第二图像组的优选图像修改为该第三图像；该第一反馈信息包括该第一用户操作、该第二图像和该第三图像。
结合第二方面，在一些实施例中，该第一反馈信息包括对图库中的图像的操作记录和该操作记录对应的图像，该操作记录指示以下一项或多项操作：删除操作、浏览操作、收藏操作和分享操作。
结合第二方面，在一些实施例中，该第一反馈信息包括，第一人脸特征和包含该第一人脸特征的图像在图库中的占比；其中：该第一人脸特征是该图库中包含图像数量最多的人脸特征，该图库中包含该电子设备中已存储的图像。
结合第二方面，在一些实施例中，该一个或多个处理器，具体用于调用该计算机指令以使得该电子设备执行：将该第一人脸特征的人脸表情评分在该决策模型中所占的权重调大；该人脸表情评分用于对图像内人脸特征的表情进行评分；其中，该第一图像组中每张图像包含一个或多个人脸特征，该一个或多个人脸特征包含该第一人脸特征。
结合第二方面，在一些实施例中，该一个或多个处理器，具体用于调用该计算机指令以使得该电子设备执行：将该第一人脸特征的人像身材比例评分在该决策模型中所占的权重调大；该人像身材比例评分用于对图像内人脸特征的身材比例进行评分；其中，该第一图像组中每张图像包含一个或多个人脸特征，该一个或多个人脸特征包含该第一人脸特征。
结合第二方面，在一些实施例中，该一个或多个处理器，还用于调用该计算机指令以 使得该电子设备执行：显示相机应用界面，该相机应用界面包含拍摄控件；响应于作用在该拍摄控件的第二用户操作，连拍得到第一图像组；响应于用于显示该第一图像组的第三用户操作，显示连拍图像界面，该连拍图像界面包含该第一图像和该第一图像组中每张图像的缩略图。
结合第二方面，在一些实施例中，该一个或多个处理器，还用于调用该计算机指令以使得该电子设备执行：从该图库中检测第一图像组；其中，该第一图像组的缩略图在图库应用界面上相邻显示，该第一图像组中每张图像均包含第一图像特征，该第一图像特征包含第二人脸特征或者第一拍摄场景；该一个或多个处理器，还用于调用该计算机指令以使得该电子设备执行：响应于作用在图库图标的第四用户操作，显示该图库应用界面，该图库应用界面上包含该第一图像组中图像的缩略图；其中，该第一图像的缩略图的尺寸大于该第一图像组中其他图像的缩略图的尺寸。
结合第二方面，在一些实施例中，该一个或多个处理器，还用于调用该计算机指令以使得该电子设备执行：显示第二用户界面，该第二用户界面包含多个图像特征选项和确定控件；其中，该多个图像特征选项中每个图像特征选项对应有图像特征；响应于作用在第一选项的第五用户操作，将该第一选项由未选中状态显示为选中状态；该多个图像特征选项包含该第一选项；响应于作用在该确定控件的第六用户操作，根据该第一选项对应的图像特征调整该决策模型的参数，以得到该更新的决策模型。
第三方面，本申请实施例提供了一种芯片，该芯片应用于电子设备，该芯片包括一个或多个处理器，该处理器用于调用计算机指令以使得该电子设备执行如第一方面以及第一方面中任一可能的实现方式描述的方法。
第四方面，本申请实施例提供一种包含指令的计算机程序产品，当上述计算机程序产品在电子设备上运行时，使得上述电子设备执行如第一方面以及第一方面中任一可能的实现方式描述的方法。
第五方面，本申请实施例提供一种计算机可读存储介质，包括指令，当上述指令在电子设备上运行时，使得上述电子设备执行如第一方面以及第一方面中任一可能的实现方式描述的方法。
可以理解地，上述第二方面提供的电子设备、第三方面提供的芯片、第四方面提供的计算机程序产品和第五方面提供的计算机存储介质均用于执行本申请实施例所提供的方法。因此，其所能达到的有益效果可参考对应方法中的有益效果，此处不再赘述。
附图说明
图1～图12是本申请实施例提供的一些应用界面示意图；
图13是本申请实施例提供的一种调整决策模型参数的方法流程图；
图14是本申请实施例提供的一种决策模型训练原理示意图；
图15是本申请实施例提供的电子设备100的结构示意图；
图16是本申请实施例提供的电子设备100的软件结构框图。
具体实施方式
本申请以下实施例中所使用的术语只是为了描述特定实施例的目的，而并非旨在作为对本申请的限制。如在本申请的说明书和所附权利要求书中所使用的那样，单数表达形式“一个”、“一种”、“所述”、“上述”、“该”和“这一”旨在也包括复数表达形式，除非其上下文中明确地有相反指示。还应当理解，本申请中使用的术语“和/或”是指并包含一个或多个所列出项目的任何或所有可能组合。
由于本申请实施例涉及神经网络的应用，为了便于理解，下面先对本申请实施例涉及的相关术语及神经网络等相关概念进行介绍。
(1)连拍选优
在连续拍摄多张图像后，电子设备可利用神经网络构建决策模型，利用决策模型从多张图像中选出一张图像作为优选图像。决策模型可用于根据拍摄场景、图像语义特征和图像参数(例如清晰度、亮度等)，选出优选图像。
电子设备通过图像识别可识别得到拍摄场景和图像语义特征。拍摄场景例如包含人像、动物、风景、运动场景等。电子设备还可以识别得到不同拍摄场景下，所拍摄图像的语义特征。例如当识别得到拍摄场景为人像场景时，电子设备还可以识别得到表情、正脸/侧脸、睁眼/闭眼等等。再例如，当识别到是运动场景时，电子设备还可以识别得到室内运动/室外运动。利用图像识别，电子设备识别到的图像语义特征还可以包含所拍摄图像的构图，例如对角线构图、中央构图和“井”字构图等。可以理解的，示例仅用于解释本申请实施例，不应构成限定，所识别到的拍摄场景和图像语义特征不限于上述举例。
电子设备还可以识别所拍摄多张图像中每张图像的图像参数。图像参数可包含以下任一个或多个：清晰度、光照均匀度、对比度、饱和度、亮度、是否过曝或过暗、是否有色块、是否偏色和是否过冷。本申请实施例对电子设备识别图像参数所使用的算法不作限定。
(2)神经网络
神经网络可以是由神经单元组成的，神经单元可以是指以x s和截距1为输入的运算单元，该运算单元的输出可以为：
Figure PCTCN2020116963-appb-000001
其中，s＝1、2、……n，n为大于1的自然数，W s为x s的权重，b为神经单元的偏置。f为神经单元的激活函数(activation functions)，用于将非线性特性引入神经网络中，来将神经单元中的输入信号转换为输出信号。该激活函数的输出信号可以作为下一层卷积层的输入。激活函数可以是sigmoid函数。神经网络是将许多个上述单一的神经单元联结在一起形成的网络，即一个神经单元的输出可以是另一个神经单元的输入。每个神经单元的输入可以与前一层的局部接受域相连，来提取局部接受域的特征，局部接受域可以是由若干个神经单元组成的区域。
(3)深度神经网络
深度神经网络(deep neural network，DNN)，也称多层神经网络，可以理解为具有多层隐含层的神经网络。从DNN按不同层的位置划分，DNN内部的神经网络可以分为三类：输入层，隐含层，输出层。一般来说第一层是输入层，最后一层是输出层，中间的层数都 是隐含层。层与层之间是全连接的，也就是说，第i层的任意一个神经元一定与第i+1层的任意一个神经元相连。对于每一层来说，其输入输出之间的关系为：
Figure PCTCN2020116963-appb-000002
其中，
Figure PCTCN2020116963-appb-000003
是输入向量，
Figure PCTCN2020116963-appb-000004
是输出向量，
Figure PCTCN2020116963-appb-000005
是偏移向量，W是权重矩阵(也称系数)，α是激活函数。
下面介绍系数W，在一个三层的DNN中，第二层的第4个神经元到第三层的第2个神经元的线性系数定义为。其中，上标3代表系数W所在的层数，而下标对应的是输出的第三层索引2和输入的第二层索引4。即第L-1层的第k个神经元到第L层的第j个神经元的系数定义为
Figure PCTCN2020116963-appb-000006
其中，输入层是没有W参数的。
在深度神经网络中，更多的隐含层让深度神经网络更能够刻画现实世界中的复杂情形。参数越多的模型复杂度越高，模型能完成越复杂的任务。
下面介绍本申请实施例涉及的连拍选优场景下DNN各层的功能。
a.输入层
输入层的输入向量可表征图像，例如本申请中连拍得到的多张图像。
b.隐含层
隐含层进行运算的过程，可包含提取多张图像中每张图像的图像特征的过程。例如，图像特征包含人像场景下不同表情(不笑、微笑、大笑等等)、是否闭眼、正脸侧脸等等。再例如，图像特征还包含在蜜蜂、蝴蝶微距拍摄场景下图像的景深。又例如，图像的特征包含在风景拍摄场景下图像的构图，包含对角线构图、中央构图和“井”字构图等。不同特征对应的权重也不同。示例性的，表情为大笑时(即“大笑”图像特征)的权重小于为微笑时(即“微笑”图像特征)的权重。表情为闭眼时的权重小于为睁眼时的权重。图像特征的权重越大，表明包含该图像特征的图像被选出作为优选图像的概率越大。
c.输出层
输出层可输出图像选中结果，选中结果指示从多张图像选出的优选图像。例如，输出层可计算每张图像被选出的概率，然后将选出概率最高的图像作为选出的优选图像。每张图像的选出概率由隐含层的图像特征和对应的权重确定。例如，由于“不笑”图像特征对应的权重小于“微笑”图像特征的权重，包含“不笑”图像特征的图像的选出概率小于包含“微笑”图像特征的图像的选出概率。
(4)卷积神经网络
卷积神经网络(convolutional neuron network，CNN)是一种带有卷积结构的深度神经网络。卷积神经网络包含了一个由卷积层和子采样层构成的特征抽取器。该特征抽取器可以看作是滤波器，卷积过程可以看作是使用一个可训练的滤波器与一个输入的图像或者卷积特征平面(feature map)做卷积。
卷积层是指卷积神经网络中对输入信号进行卷积处理的神经元层。在卷积神经网络的卷积层中，一个神经元可以只与部分邻层神经元连接。一个卷积层中，通常包含若干个特征平面，每个特征平面可以由一些矩形排列的神经单元组成。同一特征平面的神经单元共享权重，这里共享的权重就是卷积核。共享权重可以理解为提取图像信息的方式与位置无 关。这其中隐含的原理是：图像的某一部分的统计信息与其他部分是一样的。即意味着在某一部分学习的图像信息也能用在另一部分上。所以对于图像上的所有位置，都能使用同样的学习得到的图像信息。在同一卷积层中，可以使用多个卷积核来提取不同的图像信息，一般地，卷积核数量越多，卷积操作反映的图像信息越丰富。
卷积核可以以随机大小的矩阵的形式初始化，在卷积神经网络的训练过程中卷积核可以通过学习得到合理的权重。另外，共享权重带来的直接好处是减少卷积神经网络各层之间的连接，同时又降低了过拟合的风险。
电子设备在连续拍摄多张图像后，所使用的用于选取优选图像的算法模型也可以是CNN。
(5)损失函数
训练深度神经网络的也就是学习权重矩阵的过程，训练的最终目的是得到训练好的深度神经网络的所有层的权重矩阵，所有层的权重矩阵是由每层的向量W形成的权重矩阵。
在训练深度神经网络的过程中，因为希望深度神经网络的输出尽可能的接近真正想要预测的值，电子设备可以通过比较当前网络的预测值和真正想要的目标值，再根据两者之间的差异情况来调整每一层神经网络的权重向量。当然，在第一次调整之前通常会有初始化的过程，即为深度神经网络中的各层预先配置参数。示例性的，如果网络的预测值偏高，电子设备就调整权重向量让它预测低一些，不断的调整，直到深度神经网络能够预测出真正想要的目标值或与真正想要的目标值非常接近的值。
因此，电子设备需要预先定义“如何比较预测值和目标值之间的差异”，这便是损失函数(loss function)或目标函数(objective function)。损失函数和目标函数是用于衡量预测值和目标值的差异的重要方程。其中，以损失函数举例，损失函数的输出值(loss)越高表示差异越大。深度神经网络的训练过程即为尽可能缩小这个loss的过程。
(6)反向传播算法
深度神经网络可以采用损失函数反向传播(back propagation，BP)算法在训练过程中修正初始的权重矩阵，使得预测值和目标值的差异越来越小。具体地，前向传递输入信号直至输出会产生误差损失，通过反向传播误差损失信息来调整初始的权重矩阵，从而使误差损失收敛。反向传播算法是以误差损失为主导的反向传播运动，旨在得到最优的例如权重矩阵。
本申请实施例提供的图像显示方法中，电子设备可检测用户反馈。用户反馈可包含连拍选优过程中利用决策模型选出的优选图像和修改的优选图像。用户反馈还可包含被删除、浏览、收藏和分享的图像。用户反馈还可以包含电子设备统计得到的图库中的人脸图像。电子设备可根据这些用户反馈来调整用于连拍选优的决策模型中的参数，以得到调整后的决策模型。电子设备可根据调整后的决策模型来进行连拍选优，并将优选图像显示出来。
本申请实施例提到的第一反馈信息可包含上述用户反馈，更新的决策模型即为调整后的决策模型。
上述的图像显示方法中，电子设备可依据用户操作来调整用于从多张图像中选出优选图像的决策模型中的参数。这样，通过决策模型选出的优选图像更加符合用户习惯，减少 用户手动从多张图像中重新选择的情况，从而可提高便利性。
下面介绍本申请实施例提供的用户界面。
首先，介绍开启连拍功能所涉及的用户界面。请参阅图1，图1是本申请实施例提供的一种用户界面的示意图。如图1中的(A)所示，电子设备显示主屏幕界面10。如图1中的(A)所示，主屏幕界面10包括日历小工具(widget)101、天气小工具102、应用程序图标103、状态栏104以及导航栏105。其中：
日历小工具101可用于指示当前时间，例如日期、星期几、时分信息等。
天气小工具102可用于指示天气类型，例如多云转晴、小雨等，还可以用于指示气温等信息，还可以用于指示地点。
应用程序图标103可以包含例如微信(Wechat)的图标、推特(Twitter)的图标、脸书(Facebook)的图标、微博(Sina Weibo)的图标、QQ(Tencent QQ)的图标、优兔(YouTube)的图标、图库(Gallery)的图标和相机(camera)的图标1031等，还可以包含其他应用的图标，本申请实施例对此不作限定。任一个应用的图标可用于响应用户的操作，例如触摸操作，使得电子设备启动图标对应的应用。
状态栏104中可以包括运营商的名称(例如中国移动)、时间、WI-FI图标、信号强度和当前剩余电量。
导航栏105可以包括：返回按键1051、主界面(home screen)按键1052、呼出任务历史按键1053等系统导航键。其中，主屏幕界面10为电子设备100在任何一个用户界面检测到作用于主界面按键1052的用户操作后显示的界面。当检测到用户点击返回按键1051时，电子设备100可显示当前用户界面的上一个用户界面。当检测到用户点击主界面按键1052时，电子设备100可显示主屏幕界面10。当检测到用户点击呼出任务历史按键1053时，电子设备100可显示第一用户最近打开过的任务。各导航键的命名还可以为其他，比如，1051可以叫Back Button，1052可以叫Home button，1053可以叫Menu Button，本申请对此不做限制。导航栏105中的各导航键不限于虚拟按键，也可以实现为物理按键。
如图1中的(A)和(B)所示，响应于作用在相机的图标1031的用户操作，例如触摸操作，电子设备可显示相机应用界面20。相机应用界面20还可以包含缩略图控件201、拍摄控件202、摄像头切换控件203、取景框205、调焦控件206A、设置控件206B和闪光灯开关206C。其中：
缩略图控件201，用于供用户查看已拍摄的图片和视频。
拍摄控件202，用于响应于用户的操作，使得电子设备拍摄图片或者视频。
摄像头切换控件203，用于将采集图像的摄像头在前置摄像头和后置摄像头之间切换。
取景框205，用于对所采集图片进行实时预览显示。
调焦控件206A，用于对摄像头进行调焦。
设置控件206B，用于设置采集图像时的各类参数。
闪光灯开关206C，用于开启/关闭闪光灯。
用户可长按拍摄控件202，响应于该第二用户操作，即作用在拍摄控件202的长按操作，电子设备可启动连拍功能，在短时间内采集并存储多张图像。当作用在拍摄控件202 的长按操作结束时，电子设备可停止存储图像，即本次连拍图像过程结束。
本申请实施例中，不限于通过长按拍摄控件202来触发连拍功能，电子设备还可以通过其他控件设计来实现连拍功能的触发，本申请实施例对此不作限定。
当通过连拍功能采集到多张图像后，电子设备可响应于作用在缩略图控件201的触摸操作，显示这多张图像。请参阅图2，图2是本申请实施例提供的用户界面的示意图。如图2中的(A)所示，用户界面30可包含分享控件301、收藏控件302、编辑控件303、删除控件304、更多控件305、图库控件306、选优控件307、拍摄参数控件308和图像预览框309。其中：
图像预览框309，用于显示连拍得到的多张图像中电子设备根据决策模型选出的优选图像。该优选图像为图3中的(A)所示出的优选图像4031，具体参考图3描述示例。
分享控件301，用于将图像预览框309中显示的图像分享到其他应用，例如分享到微信、QQ等。
收藏控件302，用于将图像预览框309中显示的图像添加到收藏分组中。用户可在收藏分组中查看到该图像预览框309中显示的图像。
编辑控件303，用于对图像预览框309中显示的图像进行编辑，例如裁剪、调节亮度、添加滤镜等等。
删除控件，用于删除连拍得到的多张图像。
更多控件305，用于对图像预览框309中显示的图像执行其他功能操作，例如打印功能操作、设置为桌面背景的功能操作等等。
图库控件306，用于打开图库应用，图库应用中包含已拍摄的图像。
拍摄参数控件308，用于响应于用户操作，使得电子设备显示优选图像的拍摄参数，例如拍摄焦距、存储路径、占用内存大小等等。
选优控件307，用于修改连拍得到的优选图像。具体的，如图2中的(B)所示，响应于作用在优选控件307的用户操作，电子设备可显示用户界面40。用户可在用户界面40上修改的优选图像。用户界面40包含返回控件401、提示402、图像展示区403、缩略图显示区404和保存控件405。
返回控件401，用于返回用户界面40的上一级界面。响应于作用在返回控件401的用户操作，电子设备可显示用户界面30。
提示402，可用于提示本次连拍图像过程中共拍摄的图像数量和选出的优选图像的数量。示例性的，提示402可提示“1/8”，表示本次连拍图像过程中共拍摄图像数量为8张，选出的优选图像的数量为1张。这8张图像可称为第二图像组。优选图像4031可被默认显示在图像展示区403，且如图2中的(B)所示，优选图像4031上默认包含选中标识4031a，表示优选图像4031被选出。用户可在图像展示区403左右触摸滑动来查看连拍图像中的其它图像。响应于作用在图像展示区403的触摸滑动操作，电子设备可在图像展示区403显示更多的图像。
本申请实施例中，电子设备可以根据决策模型，从连拍的图像中选出优选图像4031。
如图2中的(A)所示，优选图像4031默认显示在图像预览框309中。
缩略图显示区404，可包含连拍得到的图像的缩略图。示例性的，本申请实施例中，缩略图显示区404可包含连拍的8张图像的缩略图。优选图像4031的缩略图4041可包含推荐标识4041a。如图2中的(B)所示，缩略图显示区404可显示4张图像的缩略图。用户可在缩略图显示区404左右触摸滑动来查看其它缩略图。响应于作用在缩略图显示区404的触摸滑动操作，电子设备可在缩略图显示区404显示更多的缩略图。
本申请实施例中，第一用户界面可以是用户界面40。
用户可修改连拍得到的优选图像。优选图像4031上包含选中标识4031a，为电子设备根据决策模型选出的优选图像。具体的，请参阅图3，图3是本申请实施例提供的用户界面的示意图。如图3中的(A)所示，响应于作用在选中标识4031a的触摸操作，电子设备可在图像4031上显示未选中标识4031b，表示图像4031未被选出。如图3中的(B)所示，响应于作用在图像展示区403的触摸滑动操作，电子设备可在图像展示区403显示图像4032。图像4032上包含未选中标识，响应于作用在未选中标识的触摸操作，电子设备可在图像4032上显示选中标识4032a，表示图像4032被选出。图像4031为电子设备选出的优选图像，图像4032为修改的优选图像。
用户可触摸保存控件405，使得电子设备保存用户修改的优选图像。具体的，请参阅图4，图4是本申请实施例提供的用户界面的示意图。如图4中的(A)所示，响应于作用在保存控件405的用户操作(例如触摸操作)，电子设备可显示用户界面50。用户界面50可包含控件501、控件502和控件503。其中：
控件501，可提示“取消”，响应于作用在控件501的用户操作，电子设备可显示图3中的(B)所示出的用户界面40。
控件502，可提示“全部保留”，响应于作用在控件502的用户操作，电子设备可存储选出的优选图像4032，并仍然保存其他未被选出的图像，例如仍然保存图像4032之外的其他7张图像。
控件503，可提示“仅保留所选一张照片”，响应于作用在控件503的用户操作，电子设备可存储选出的优选图像4032，并将其他未被选出的图像删除，例如删除除图像4032之外的其他7张图像。优选图像4032被存储之后，用户可在图库应用的用户界面中查看该优选图像4032。
本申请实施例中，电子设备可接收到修改连拍得到的优选图像的用户操作，例如图3中将优选图像从图像4031修改为图像4032的用户操作。则电子设备可响应于作用在控件502或者控件503的用户操作，并显示提示框504。如图4中的(B)所示，提示框504可包含提示5041、控件5042和选项5043。
提示5041，可提示：“已收到您的修改反馈，我们会根据修改推荐更符合您喜好的照片。”。
响应于作用在控件5042的用户操作，电子设备可不再显示提示框504，显示图库的用户界面，并预览优选图像4032。
选项5043，可提示：“不再显示”。选项5043为未选中状态，响应于作用在选项5043的用户操作，选项5043为选中状态。当选项5043为选中状态时，则用户再修改连拍得到的优选图像时，不再出现提示框504。
经过图3和图4所描述的修改连拍得到的优选图像的过程，图3所示出的利用决策模型选出的优选图像4031，以及修改的优选图像4032可作为用户反馈，来调整用于连拍选优的决策模型中的参数，以得到调整后的决策模型。本申请实施例中，第一用户操作可包含图3中的(A)所示的作用在选中标识4031a的触摸操作、作用在图像展示区403的触摸滑动操作、作用在图像4032的未选中标识的触摸操作、作用在控件502、控件503的用户操作。响应于该第一用户操作，电子设备将连拍得到的图像的优选图像修改为图像4032。其中，修改前的优选图像4031可称为第二图像，修改后的优选图像4032可称为第三图像。
示例性的，如图3和图4所示，电子设备检测到优选图像4031被修改为优选图像4032，优选图像4031包含“微笑”图像特征，优选图像4032包含“大笑”图像特征。则电子设备可调整决策模型的参数，将决策模型中“微笑”图像特征的权重减小，“大笑”图像特征的权重增加，得到调整后的决策模型。
本申请实施例中，不限于在用户界面40上检测第一用户界面，使得电子设备修改优选图像，用户界面40上还可以对连拍得到的一组图像(第二图像组)中的某一张或几张图像进行删除、浏览、收藏和分享，具体的界面设计和描述可参考图5～图7相关描述，这里不再赘述。
用户可在图库应用的用户界面中对图像进行删除、浏览、收藏和分享。被删除、浏览、收藏和分享的图像，也可作为用户反馈，来调整用于连拍选优的决策模型中的参数，以得到调整后的决策模型。下面介绍删除、浏览、收藏和分享图像相关的用户界面。
请参阅图5，图5是本申请实施例提供的用户界面的示意图。如图5中的(A)所示，为图库的用户界面60的示意图。用户界面60可以是响应于作用在图库的图标的触摸操作，电子设备显示的。图库应用可用于显示电子设备存储的图像，用户界面60上可包含这些图像的缩略图。不限于该方式来显示用户界面60，还可以是其他方式，例如在图2中的(A)所示出用户界面30中，响应于作用在选优控件307的用户操作，电子设备可显示用户界面60。用户界面60可包含缩略图显示区601、照片选项602、相册选项603、发现选项604、搜索控件605和更多选项606。其中：
缩略图显示区601，可包含电子设备存储的多张图像的缩略图。
照片选项602、相册选项603、发现选项604中，不同的选项对应不同的缩略图显示区。图5中的(A)示出的当前选择的选项为照片选项602。即缩略图显示区601中显示的缩略图是照片选项602下的缩略图。
搜索控件605，用于搜索图像。
更多选项606，可用于打开更多功能，例如，隐藏相册、设置等。
用户可在用户界面60上对图像进行删除、浏览、收藏和分享。示例性的，如图5中的(B)所示，响应于作用在缩略图6011的长按操作，电子设备可在用户界面60上显示编辑控件，包含分享控件608、删除控件609、更多控件611。其中，缩略图6011可以是任意一个缩略图，缩略图6011还包括选中标识6011a，表示缩略图6011对应的图像被选出。如图5中的(B)所示，用户界面60还可以包含全选控件610和退出控件607。其中：
退出控件607，用于退出编辑状态，响应于作用在退出控件607的用户操作，电子设 备可显示图5中的(A)所示出的用户界面60。
分享控件608，用于将选出的图像分享到其他应用，例如分享到微信应用、微博应用。
删除控件609，用于将选出的图像删除。
全选控件610，用于将缩略图对应的图像全部选出。如图5中的(B)所示，缩略图6011包含选中标识6011a，其他缩略图包含未选中标识。响应于作用在全选控件610的用户操作，电子设备在所有的缩略图上显示选中标识，即已存储的全部图像均被选出。
更多控件611，对选出的图像执行更多操作，例如执行打印、查看详细信息、收藏等等。
本申请实施例中，不限于在图库的用户界面60中对图像进行删除、收藏和分享，还可以是在其他界面上，例如在电子设备显示图像的用户界面，参考图2中的(A)所示示例。
在图5中的(A)所示出的用户界面60上，响应于作用在缩略图上的触摸操作，电子设备可显示缩略图对应的图像，所对应的用户界面类比图2中的(A)所示出示例。该作用在缩略图上的触摸操作，可看作是用于浏览图像的用户操作。电子设备可统计每张图像被浏览的次数或频率，并将浏览的图像作为用户反馈调整决策模型中的参数。缩略图对应的图像的用户界面上类似图2中的(A)，也可包含分享控件、删除控件、收藏控件。响应于作用在收藏控件的用户操作，电子设备将缩略图对应的图像添加到收藏分组中。用户可在收藏分组中查看到图像。该被收藏的图像可作为用户反馈来调整决策模型中的参数。
本申请实施例中，对图库中的图像的收藏记录可指示作用在收藏控件的用户操作。收藏控件可参考图2所描述的收藏控件302。收藏记录对应的图像即收藏的图像。
下面介绍几种删除图像的示例。如图5中的(B)所示，响应于作用在删除控件609的用户操作，电子设备可显示提示框612。请参阅图6，图6是本申请实施例提供的一种用户界面示意图。如图6所示，响应于作用在删除控件6123的用户操作，电子设备删除选出的图像，即删除缩略图6011对应的图像。缩略图6011对应的图像即为删除的图像，可作为用户反馈来调整决策模型中的参数。
不限于在图5中的(B)所示出的用户界面删除图像，如图2中的(A)所示，响应于作用在删除控件304的用户操作，电子设备也可显示提示框612。电子设备删除连拍得到的图像后，可将优选图像4031作为删除的图像，该删除的图像4031可作为用户反馈来调整决策模型中的参数。在另一种可能的实现中，连拍得到的所有图像(例如连拍得到的8张图像)均为删除的图像，可作为用户反馈来调整决策模型中的参数。
本申请实施例中，被删除的图像，例如包含缩略图6011对应的图像。对图库中的图像的删除记录，例如可包含作用在缩略图6011的长按操作和作用在删除控件6123的用户操作，该删除记录对应的图像即缩略图6011对应的图像。被删除的图像不限于缩略图6011对应的图像，例如还包括以下图像：在图2中的(A)所示的删除控件304检测到的用户操作，使得电子设备删除的图像。
下面介绍一种分享图像的示例。请参阅图7，图7是本申请实施例提供的一种用户界面的示意图。如图7中的(A)所示，响应于作用在图5中的(B)所示出的分享控件608的用户操作，电子设备可显示提示框613。提示框613可包含图标显示区6131。图标显示区6131可包含多个应用图标，例如微信的图标、QQ的图标、推特的图标、脸书的图标、邮件的图标、云共享的图标、备忘录的图标和信息的图标。用户可触摸滑动图标显示区6131， 响应于该触摸滑动操作，电子设备可显示更多应用图标。
如图7中的(B)所示，响应于作用在微信的图标6131a的用户操作，电子设备可显示用户界面70。用户界面70为微信应用的界面。用户界面70包含联系人列表701和搜索框702。联系人列表701可包含多个联系人标识。搜索框702可用于搜索联系人。
如图7中的(C)所示，响应于作用在联系人图标7011的用户操作，电子设备可显示用户界面80，并将图7中的(A)所示的选出的图像分享到用户界面80所示出联系人对话框。将选出的图像分享到联系人对话框，表示电子设备将选出的图像发送给该联系人对应的终端。用户界面80可包含缩略图801、用户标识802、语音控件803、输入框804、功能控件区805和返回控件806。其中：
缩略图801，对应图7中的(A)所示的包含选中标识6011a的缩略图6011，表示将对应的图像分享给微信应用中的用户。
用户标识802，表示当前微信应用所登陆的用户。
语音控件803，用于发送语音信息。响应于作用在语音控件803的用户操作，电子设备可检测语音信息，并将语音信息发送给对应的用户，例如发送给联系人图标7011对应的用户Lisa。
输入框804，用于发送文本信息。电子设备可通过输入框804接收文本信息，并将文本信息发送给对应的用户。
功能控件区805，可包含照片选项8051、拍摄选项8052、视频通话选项8053、位置选项8054、红包选项8055、转账选项8056、语音输入选项8057和收藏选项8058。其中：
照片选项8051，用于向用户(例如联系人图标7011对应的用户Lisa)发送图像。
拍摄选项8052，用于拍摄图像并将拍摄的图像发送给该用户。
视频通话选项8053，用于向用户发送语音通话请求或者视频通话请求。
位置选项8054，用于向用户发送位置信息。
红包选项8055和转账选项8056，用于向用户发送红包或者进行转账。
语音输入选项8057，用于发送语音信息。收藏选项8058，用于发送收藏的内容。
返回控件806，用于返回用户界面80的上一级界面。本领域技术人员可以理解，一个界面的逻辑上一级界面是固定的，在应用程序设计时便已确定。
本申请实施例中，当检测到作用在联系人图标7011的用户操作时，电子设备可确定图7中的(A)所示出的缩略图6011对应的图像为被分享的图像。该缩略图6011对应的图像，可作为用户反馈来调整决策模型中的参数。
被分享的图像不限于图7所示示例，用户还可以通过图7中的(C)所示图片选项8051、拍摄选项8052来分享图像。通过图片选项8051、拍摄选项8052分享的图像，也可作为用户反馈来调整决策模型中的参数。
本申请实施例中，对图库中的图像的分享记录可指示作用在图5中的(B)所示出的分享控件608的用户操作。分享记录对应的图像可指示缩略图6011对应的图像。
本申请实施例中，被删除、浏览、收藏和分享的图像不限于图5～图7所描述示例。下面介绍本申请实施例中，其他场景下所涉及的被删除、浏览、收藏和分享的图像。如图7中的(C)所示，响应于作用在缩略图801的用户操作，例如触摸操作，电子设备可显示缩 略图801对应的图像。则缩略图801对应的图像即为被浏览的图像，可作为用户反馈来调整决策模型中的参数。本申请实施例中，对图库中的图像的浏览记录，例如为缩略图801对应的图像的浏览记录。浏览记录对应的图像例如为缩略图801对应的图像。
请参阅图8，图8是本申请实施例提供的一种用户界面的示意图。如图8所示，响应于作用在缩略图801上的长按操作，电子设备可显示选项框807，选项框807包含发送选项8071、收藏选项8072、提醒选项8073、编辑选项8074、删除选项8075和多选选项8076。其中：
发送选项8071，用于将缩略图801对应的图像发送给其他用户。
收藏选项8072，用于将缩略图801对应的图像在微信应用中进行收藏。
提醒选项8073，用于对缩略图801对应的图像进行提醒。
编辑选项8074，用于对缩略图801对应的图像进行编辑。
删除选项8075，用于在用户界面80上将缩略图801删除。
多选选项8076，用于选择多条信息。
本申请实施例中，响应于作用在发送选项8071的用户操作，例如触摸操作，电子设备可记录缩略图801对应的图像作为被分享的图像，以将该被分享的图像作为用户反馈来调整决策模型中的参数。响应于作用在收藏选项8072的用户操作，例如触摸操作，电子设备可记录缩略图801对应的图像作为被收藏的图像，以将该被收藏的图像作为用户反馈来调整决策模型中的参数。响应于作用在删除选项8075的用户操作，例如触摸操作，电子设备可记录缩略图801对应的图像作为被删除的图像，以将该被删除的图像作为用户反馈来调整决策模型中的参数。
不限于被删除、浏览、收藏和分享的图像，用户反馈还可以包含被编辑、打印、备注、提醒的图像。被编辑的图像例如包含被调整颜色、亮度等参数的图像。被打印的图像可以是通过用户界面60中的更多控件611执行打印的图像。被备注的图像例如也可以是通过用户界面60中的更多控件611被备注的图像。被提醒的图像例如可以是通过选项框807中的提醒选项8073被提醒的图像。
本申请实施例中，电子设备还可统计得到的图库中的人脸图像，并利用统计得到的人脸图像来调整用于连拍选优的决策模型中的参数。请参阅图9，图9是本申请实施例提供的一种用户界面的示意图。如图5中的(A)所示的用户界面60中，响应于作用在发现选项604的用户操作，电子设备可在缩略图显示区601显示发现选项604下的缩略图，如图9所示。发现选项604下的缩略图可包含电子设备所识别出的类别：人像类别6012、地点类别6013和事物类别6014。其中：
人像类别6012，包含所识别到的人脸图像的缩略图。人像类别6012还包括更多控件6012a。响应于作用在更多控件6012a的用户操作，电子设备可显示更多所识别到的人脸图像的缩略图。
人像类别6012，用于将图库中图像按照人脸特征分类。人像类别6012包含的缩略图中，每个缩略图对应一个人脸特征。对任一个缩略图来说，响应于作用在该缩略图的用户操作，电子设备可显示图库中与该人脸特征匹配的多张图像的缩略图。例如，响应于作用 在缩略图6012b的用户操作，电子设备可显示缩略图6012b对应的人脸特征相匹配的图像的缩略图。
其中，人脸特征与图像匹配是指，该人脸特征与图像中包含的人脸的特征之间相似度大于设定阈值，例如80％。
地点类别6013，用于将图库中图像按照图像拍摄时所在的地理位置进行分类。地理位置例如包含深圳市、武汉市、东莞市等等。地点类别6013还包括更多控件6013a。响应于作用在更多控件6013a的用户操作，电子设备可显示更多按照地理位置分类得到的图像的缩略图。每个缩略图对应一个地理位置。响应于作用在该缩略图的用户操作，电子设备可显示图库中与该地理位置相同的图像的缩略图。
事物类别6014，用于将图库中图像按照事物类型进行分类。事物类型例如包含风景、文档、运动、交通工具等等。事物类别6014还包括更多控件6014a。响应于作用在更多控件6014a的用户操作，电子设备可显示更多按照事物类型分类得到的图像的缩略图。每个缩略图对应一种事物类型。响应于作用在该缩略图的用户操作，电子设备可显示图库中与该事物类型相同的图像的缩略图。
本申请实施例中，人脸类别6012中包含的人脸图像可用来调整用于连拍选优的决策模型中的参数。其中的人脸图像还可以根据所拍摄图像的更新而更新。
在调整完决策模型的参数后，下次执行连拍功能后，电子设备可根据该调整后的决策模型，从连拍的图像中选出优选图像。其中，第一图像组可包含该连拍图像，第一图像可包含根据调整后的决策模型(即更新的决策模型)从该第一图像组中选出的优选图像。具体的，请参阅图10，图10是本申请实施例提供的一种用户界面的示意图。如图10所示，优选图像4061可被默认显示在图像展示区403，且如图10所示，优选图像4061上默认包含选中标识4061a，表示优选图像4061被选出。用户可在图像展示区403左右触摸滑动来查看连拍图像中的其它图像。响应于作用在图像展示区403的触摸滑动操作，电子设备可在图像展示区403显示更多的图像。缩略图显示区404可包含连拍的11张图像的缩略图。优选图像4061的缩略图4071可包含推荐标识4071a。
如图10所示，第一图像组包含图像展示区403可显示的一组图像，第一图像可包含优选图像4061。在连拍选优场景中，用于显示所述第一图像组的第三用户操作例如可包含图2中的(A)中作用在控件307的用户操作。连拍图像界面例如可包含图10所描述用户界面40。
经过图3～图4所描述示例，电子设备可根据修改连拍得到的优选图像，调整决策模型的参数，将决策模型中“微笑”图像特征的权重减小，“大笑”图像特征的权重增加，得到调整后的决策模型。在本申请实施例中，电子设备根据该调整后的决策模型从连拍的11张图像进行选择时，可选出包含“大笑”图像特征的图像，即缩略图4071对应的图像。电子设备将缩略图4071对应的图像4061显示在图像展示区4061。本申请实施例中，包含“大笑”图像特征的图像是根据用户反馈选出的，更加符合用户的习惯和喜好，提高了为用户推荐图像的准确性。
在本申请实施例的另一些实施例中，如图10所示，电子图像展示区403还可以包含提 示4062，可提示“根据反馈推荐大笑表情的人脸”。
在本申请的另一些实施例中，电子设备可接收用于调整特征权重的用户输入。示例性的，请参阅图11，如图11中的(A)所示，在用户界面40上电子设备还显示控件4063，提示“点击选择个人喜好”。如图11中的(B)所示，响应于作用在控件4063的用户操作，电子设备可显示提示框408。其中，提示框408可称为第二用户界面。
提示框408包含多个图像特征选项：一组选项为不笑选项4081、微笑选项4082和大笑选项4083，另一组选项为正脸选项4084和侧脸选项4085，又一组选项为闭眼选项4086和睁眼选项4087。其中，每个选项均可包含选中状态和未选中状态。电子设备可响应于作用在选项上的用户操作，例如触摸操作，将选项的状态在选中状态和未选中状态之间切换显示。
当不笑选项4081处于选中状态时，对应“不笑”图像特征的权重可被调大，当不笑选项4081处于未选中状态时，对应“不笑”图像特征的权重可被调小。微笑选项4082对应“微笑”图像特征，大笑选项4083对应“大笑”图像特征。正脸选项4084对应“正脸”图像特征，侧脸选项4085对应“侧脸”图像特征。闭眼选项4086对应“闭眼”图像特征，睁眼选项4087对应“睁眼”图像特征。微笑选项4082、大笑选项4083、正脸选项4084、侧脸选项4085、闭眼选项4086和睁眼选项4087类似，当处于选中状态时，对应的图像特征的权重可被调大，当处于未选中状态时，对应的图像特征的权重可被调小。
提示框408还包含取消控件408a和确定控件408b。取消控件408a，用于返回上一级界面。响应于作用在取消控件408a的用户操作，例如触摸操作，电子设备可显示图11中的(A)所示界面。
确定控件408b，用于确定需调整权重的图像特征。响应于作用在确定控件408b的用户操作，如触摸操作，电子设备可获得处于选中状态的选项，例如大笑选项4083、正脸选项4084和睁眼选项4087。作用在确定控件408b的用户操作，如触摸操作可称为第六用户操作。
电子设备可根据处于选中状态的选项，确定需调整权重的图像特征。例如，电子设备确定需调整权重的图像特征为“大笑”图像特征、“正脸”图像特征和“睁眼”图像特征。其中，“大笑”选项4083、“正脸”选项4084和“睁眼”选项4087可称为第一选项。第一选项可响应于作用在第一选项的第五用户操作，例如触摸操作，由未选中状态显示为选中状态。然后电子设备将这些图像特征的权重调大。由于这些图像特征是用户根据个人喜好选出的图像特征，更加符合用户习惯，减少用户手动从多张图像中重新选择的情况，从而可提高便利性。
可以理解的，本申请实施例不限于图11中的(B)所示出的选项举例，还可以包含其他选项。另外，不限于人像场景，在其他拍摄场景下电子设备也可以识别拍摄场景，并提供特征选项供用户选择。
在本申请的一些实施例中，电子设备根据用户反馈调整决策模型的参数，得到调整后的决策模型。电子设备还可根据该调整后的决策模型，从图库中图像选出优选图像，并与其他图像区分显示。具体的，请参阅图12，图12是本申请实施例提供的一种用户界面的 示意图。如图12中的(A)所示，当电子设备存储多张人脸图像时，可在图库对应的用户界面60上将这多张人脸图像以缩略图的形式显示，即缩略图6011，包含缩略图6011a、6011b、6011c和6011d。其中，这多张人脸图像可以是第一图像组，这些图像可包含相同图像特征，例如相同的人脸特征，即第二人脸特征。不限于第一图像组包含相同的人脸特征，还可以是包含相同的拍摄场景，例如第一拍摄场景。第一拍摄场景例如是风景拍摄场景。
如图12中的(A)所示，电子设备可检测作用在图库图标的第四用户操作，例如触摸操作，并显示图库应用界面60。图库图标可参考1描述示例。
电子设备可根据调整后的决策模型，从缩略图6011a对应的图像、缩略图6011b对应的图像、缩略图6011c对应的图像和缩略图6011d对应的图像中选出一张图像。例如选出缩略图6011d对应的图像，并将缩略图6011d以比缩略图6011a更大的尺寸显示。
示例性的，经过图3～图4所描述示例，电子设备可根据修改连拍得到的优选图像，调整决策模型的参数，将决策模型中“微笑”图像特征的权重减小，“大笑”图像特征的权重增加，得到调整后的决策模型。则在本申请实施例中，电子设备根据该调整后的决策模型从缩略图6011对应的图像选择时，可选出包含“大笑”图像特征的图像，即缩略图6011d对应的图像，并将缩略图6011d以更大的尺寸显示。
可选的，电子设备还可以在缩略图6011d上显示推荐标识6011d-1，表示缩略图6011d对应的图像是从多张图像中选出的优选图像。
在另一种可能的实现方式中，如图12中的(B)所示，电子设备根据该调整后的决策模型选出的图像的缩略图6011d还可以是和其他缩略图尺寸相同，边框不同于其他缩略图，以表示缩略图6011d对应的图像是从多张图像中选出的优选图像，本申请实施例对表示选出的优选图像的形式不作限定。
不限于人脸图像场景中“微笑”图像特征、“大笑”图像特征，权重的调整还可以针对其他图像特征，例如“正脸”、“侧脸”图像特征，“睁眼”、“闭眼”、“笑眼”图像特征等等。权重的调整还可以针对其他场景下的图像特征，例如，在蜜蜂、蝴蝶微距拍摄场景下图像的景深，再例如，在风景拍摄场景下图像的构图。图像特征包含图像语义特征、拍摄场景和图像参数。权重的调整也不限于针对这些图像语义特征，还可以针对图像参数，例如清晰度、光照均匀度、对比度、饱和度、亮度、细节丰富程度、是否过曝或过暗、是否有色块、是否偏色和是否过冷。本申请实施例对权重的调整所针对的图像特征不作限定。
在图库场景中，如图12所示，第一图像组还可包含缩略图6011a、6011b、6011c和6011d对应的图像。相应的，第一图像可包含优选图像，即缩略图6011d对应的图像。
下面具体介绍本申请实施例中，电子设备调整决策模型的参数的过程。请参阅图13，图13是本申请实施例提供的一种调整决策模型的参数的方法流程图。如图13所示，该方法包括步骤S101～S108。
S101、电子设备通过连拍功能拍摄多张图像。
S102、电子设备根据决策模型从多张图像中选出优选图像。
S103、电子设备检测并记录决策模型选出的优选图像和修改的优选图像。
关于步骤S101～S103可参考图1～图4所提供用户界面的相关描述，这里不再赘述。
S104、电子设备检测并记录被删除、浏览、收藏和分享的图像。
关于被删除、浏览、收藏和分享的图像，可参考图5～图8所提供用户界面的相关描述，这里不再赘述。
本申请实施例中，不限于被删除、浏览、收藏和分享的图像，用户反馈还可以包含被编辑、打印、备注、提醒的图像。
S105、电子设备检测并记录图库中的人脸图像。
关于图库中的人脸图像，可参考图9所提供用户界面的相关描述，这里不再赘述。本申请实施例中，图库中的人脸图像还可以根据所拍摄图像的更新而更新。
本申请实施例中，不限于人脸图像场景下的人脸图像，用户反馈还可以包含其他场景下的被摄对象。
本申请实施例对步骤S103、S104和S105的执行先后不作限定。
S106、电子设备每隔预设时间，或者检测到预设数量的用户反馈记录，则根据用户反馈调整决策模型的参数。
S107、电子设备根据调整后的决策模型从连拍功能得到的多张图像中选出优选图像。
S108、电子设备根据调整后的决策模型从图库中图像选出优选图像，并将选出的优选图像与其他图像区分显示。
关于步骤S107～S108可参考图10～图12所提供用户界面的相关描述，这里不再赘述。
本申请实施例中，决策模型中可包含以下任一种或多种参数：①决策模型选出的优选图像和修改的优选图像之间不同的图像特征，②被删除、浏览、收藏和分享的图像特征，③图库中的人脸图像的图像特征。决策模型还包含所包含参数对应的权重。下面具体介绍步骤S106中调整决策模型的参数的过程。
①利用连拍选优调整决策模型参数的过程
电子设备可检测决策模型选出的优选图像和修改的优选图像之间不同的图像特征。例如，电子设备可检测到决策模型选出的优选图像包含“微笑”图像特征，而修改的优选图像包含“大笑”图像特征。则电子设备将决策模型中“大笑”图像特征的权重调大，将“微笑”图像特征的权重调小。使用调整后的决策模型进行人像场景下连拍选优时，电子设备可选出包含“大笑”图像特征的图像。
再例如，在风景拍摄场景下，电子设备可检测到决策模型选出的优选图像包含对角线构图的图像特征，而修改的优选图像包含中央构图的图像特征。则电子设备将决策模型中中央构图的图像特征的权重调大，将对角线构图的图像特征的权重调小。使用调整后的决策模型进行风景拍摄场景下连拍选优时，电子设备可选出包含中央构图的图像特征的图像。
关于图像特征的权重，可参考前述深度神经网络概念的相关描述。
本申请实施例中，电子设备可将指示第一用户操作的标签值(例如一个数值)、决策模型选出的优选图像(第二图像)和修改的优选图像(第三图像)输入决策模型，决策模型可根据指示第一用户操作的标签、第二图像和第三图像调整决策模型。
②利用被删除、浏览、收藏和分享的图像调整决策模型参数的过程
电子设备可周期性的(例如每隔24小时)记录图库中图像被删除、浏览的次数、收藏和分享的次数。电子设备可针对于删除、浏览、收藏和分享分别设置对应的标签值。之后， 电子设备可识别被操作的图像的拍摄场景，根据被操作的图像和图像对应的标签值调整对应的图像特征的权重大小。下面给出一种用户操作对应的标签值的示例。
表一、一种图像操作对应的标签值的示例
用户操作 标签值
删除 0
浏览/次 1
收藏 2
分享/次 3
如表一所示，图像接收到删除操作时，电子设备对该图像赋值标签值为0。图像接收到一次浏览操作时，电子设备对该图像赋值标签值为1。一张图像被多次浏览，标签值为1和次数的乘积。图像接收到收藏操作时，电子设备对该图像赋值标签值为2。图像接收到一次分享操作时，电子设备对该图像赋值标签值为3。一张图像被多次分享，标签值为3和次数的乘积。
例如，在一个统计周期24小时内，图像a、图像b和图像c均是人像场景。图像a包含“不笑”图像特征，图像a接收到删除操作，则对于图像a赋予标签值0。图像b包含“微笑”图像特征，图像b接收到2次浏览操作，则对于图像a赋予标签值2。图像c包含“大笑”图像特征，图像c接收到2次分享操作，则对于图像c赋予标签值6。
电子设备可根据被删除、浏览、收藏和分享的图像和对应的标签值调整决策模型的参数。标签值可指示图像被执行的用户操作。具体的，标签值可和图像的图像特征对应的权重成正比。即标签值越大，图像对应的图像特征的权重越大，标签值越小，图像对应的图像特征的权重越小。示例性的，图像a的标签值为0，电子设备可将其包含的“不笑”图像特征的权重调小。图像b的标签值为2，电子设备可将其包含的“微笑”图像特征的权重保持不变。图像c的标签值为6，电子设备可将其包含的“大笑”图像特征的权重调大。则使用调整后的决策模型进行人像场景下连拍选优时，电子设备可选出包含“大笑”图像特征的图像。
本申请实施例以人像场景为例进行说明，但是本申请实施例不限于人像场景，还可以是其他场景下对应的图像特征。例如，风景拍摄场景下的构图特征，本申请实施例对具体的拍摄场景和图像特征不作限定。
不限于根据被删除的图像、被浏览的图像、被收藏的图像和被分享的图像周期的调整决策模型中的参数，还可以是被删除的图像、被浏览的图像、被收藏的图像或被分享的图像达到设定数量时，电子设备调整决策模型中的参数。
③利用图库中的人脸图像调整决策模型参数的过程
决策模型中还可以包含多个人脸特征和人脸特征对应的权重。电子设备可利用决策模型检测图像中人脸的表情评分，例如通过人脸识别得到人脸的表情评分。每个人脸特征对应一个人脸图像，电子设备可统计每个人脸图像在图库中对应的图像的数量(或占比)，即统计每个人脸特征在图库中对应的图像的数量(或占比)。电子设备根据对应的图像的数量调整决策模型中人脸特征的权重。具体的，在图库中对应的图像的数量越多，第一人脸特征的权重越大，在图库中对应的图像的数量越少，第一人脸特征的权重越小。包含第一人 脸特征的图像在图库中的占比越大，第一人脸特征的权重越大，包含第一人脸特征的图像在图库中的占比越小，人脸特征的权重越小。包含第一人脸特征的图像在图库中的占比是指，包含第一人脸特征的图像的数量在图库中全部图像所占的比例。
本申请实施例中，第一人脸特征是图库中包含图像数量最多的人脸特征，图库中包含电子设备中已存储的图像。已存储的图像例如包含通过摄像头拍摄的图像。已存储的图像还可包含下载到本地的图像以及在应用中(例如微信应用中)接收、发送、收藏、编辑、打印、备注的图像。
对于决策模型来说，图像中的人脸的表情评分越大，图像被选出作为优选图像的概率越大。人脸特征的权重越大，包含该人脸特征的图像被选中作为优选图像的概率越大。针对于包含多个人脸的人像场景，即所拍摄图像中包含多个人脸图像，在图库中对应的图像数量越多的人脸特征，电子设备将其权重调整的越大。电子设备根据调整后的决策模型进行连拍选优得到优选图像。该优选图像中可包含图库中对应的图像数量最多的人脸图像，且该人脸图像的表情评分最高。例如，人脸特征a指示Lisa的人脸图像，人脸图像B指示Rechel的人脸图像，人脸图像C指示Kate的人脸图像。电子设备通过人脸识别得到图库中图像包含人脸图像A、人脸图像B和人脸图像C，且检测到各人脸图像在图库中对应的图像数量。其中，人脸图像A、人脸图像B和人脸图像C分别对应人脸特征a、人脸特征b和人脸特征c。具体的，人脸图像A在图库中对应的图像数量为50张，即这50张图像中均包含人脸图像A，也即包含人脸特征a。人脸图像B(人脸特征b)在图库中对应的图像数量为30张，人脸图像C(人脸特征c)在图库中对应的图像数量为10张。电子设备在根据图库中的人脸图像调整决策模型的参数时，调整人脸图像A对应的人脸特征a的权重最大，人脸图像B对应的人脸特征b的权重次大，人脸图像C对应的人脸特征c的权重最小。电子设备根据调整后的决策模型进行连拍选优得到优选图像。
可选的，调整后的决策模型中还可仅包含人脸图像A对应的人脸特征a和人脸图像B对应的人脸特征b。电子设备在根据图库中的人脸图像调整决策模型的参数时，调整人脸图像A对应的人脸特征a的权重最大，人脸图像B对应的人脸特征b的权重最小。
本申请实施例中，第一人脸特征可以是在图库中包含图像数量最多的人脸特征，例如前例中第一人脸特征数量可以是多个，包括，在图库中包含图像数量最多的人脸特征a和人脸特征b，即Lisa的人脸图像对应的人脸特征a和Rechel的人脸图像对应的人脸特征b。
本申请实施例对人脸识别得到人脸的表情评分所使用的具体算法不作限定。具体的，电子设备可以利用图像语义特征和/或图像参数确定人脸的表情评分。例如电子设备检测到的某一个人脸包含“微笑”图像特征、“睁眼”图像特征，且清晰度、光照均匀度和细节丰富程度均达到设定阈值，电子设备可根据检测到的图像语义特征和图像参数得到人脸的表情评分。不限于上述举例，还可以根据人脸图像在图像中的构图确定人脸的表情评分。
可选的，调整后的决策模型还可以是包含每个人脸图像对应的人脸表情评分和对应的权重，更新决策模型的过程可以是将人脸图像(例如前例中的人脸图像A，对应人脸图像A的人脸特征)的人脸表情评分在决策模型中所占的权重调大。人脸图像A的人脸表情评分在决策模型中所占的权重调大后得到的更新的决策模型在用于图像选优时，电子设备可根据该更新的决策模型从一组图像中选出人脸图像A的人脸表情评分最大的图像。
电子设备利用图库中的人脸图像来调整决策模型的参数，并在人像场景下利用调整后的决策模型进行连拍选优，得到优选图像。该优选图像中可包含图库中对应的图像数量最多的人脸图像，且该人脸图像的表情评分最高。这样选出的图像更加符合用户习惯，减少用户手动从多张图像中重新选择的情况，从而可提高便利性。
在本申请的另一些实施例中，电子设备通过人脸识别得到图库中的人脸图像。电子设备还可以在检测到启动连拍功能的用户操作后，例如图1中的(B)所示出作用在拍摄控件202的长按操作结束时，才根据图库中的人脸图像来调整决策模型的参数，并根据调整的决策模型选择本次连拍得到图像中的优选图像。示例性的，电子设备在检测到启动连拍功能得到多张图像时，可获取图库中包含图像最多的3个人脸图像。电子设备可检测连拍得到的多张图像中是否包含这3个人脸图像中的任一个。若是，电子设备可将决策模型中这3个人脸图像对应人脸特征的权重调大。电子设备利用调整后的决策模型从多张图像中选出优选图像，该优选图像中这3个人脸图像的表情评分最高。
由于图库中的人脸图像和每个人脸图像的对应的图像数量根据所采集图像的累积而变化。在连拍功能执行后实时调整决策模型的参数，这样可提高调整后的决策模型进行连拍选优的精确度。
本申请实施例中，不限于人脸表情评分，调整后的决策模型还可以确定人脸图像所对应人像身材比例。具体的，电子设备利用图库中的人脸图像来调整决策模型的参数，并在人像场景下利用调整后的决策模型进行连拍选优，得到优选图像。该优选图像中可包含图库中图像数量最多的人脸图像，且该人脸图像对应的人像身材比例评分最高。
与人脸表情评分类似，电子设备也可以利用图像语义特征和/或图像参数确定人脸图像的人像身材比例评分。例如电子设备检测到的某一个人脸图像的完整人像各部分特征(例如“胳膊”图像特征、“腿”图像特征等等)，然后根据完整人像各部分计算该完整人像的身材比例评分。不限于上述举例，电子设备还可以根据其他算法确定完整人像的身材比例评分。
本申请实施例中，用户反馈可作为训练样本对决策模型进行训练，以得到调整后的决策模型。决策模型可以是通过原始训练样本集训练得到，原始训练样本集可包含多张图像。电子设备可将用户反馈作为新的训练样本集，来重新对决策模型进行训练，得到调整后的决策模型。
本申请实施例中，上述①②③所描述的调整决策模型参数的过程，可分别单独执行，也可以在一次调整决策模型的参数过程中执行两个或两个以上更新过程，本申请实施例对此不作限定。
具体的，请参阅图14，图14是本申请实施例提供的一种决策模型训练原理示意图。如图14提供了一种利用知识蒸馏(knowledge distillation)的方式训练得到调整后的决策模型的示例。电子设备利用原始训练样本集对决策模型进行训练。训练得到的决策模型可作为教师网络(teacher network)。电子设备在训练调整后的决策模型过程中可使用教师网络的一些特征。具体的，电子设备可对教师网络进行softmax变换，获得软目标(soft target)。该软目标可代表原始训练样本集中的一些特征，用于训练决策模型，得到调整后的决策模型。如图14所示，电子设备可通过软目标和新的训练样本集来共同训练决策模型，得到调 整后的决策模型。训练过程可使用反向传播算法来实现，即将损失函数反向传播的方法进行训练，具体可参考概念描述部分，这里不再赘述。
可以理解的，本申请实施例以知识蒸馏为例介绍了决策模型训练过程，但是本申请实施例不限于知识蒸馏的方式进行训练，还可以是其他方式。
下面首先介绍本申请实施例提供的示例性电子设备100。
图15是本申请实施例提供的电子设备100的结构示意图。
电子设备100可以包括处理器110，外部存储器接口120，内部存储器121，通用串行总线(universal serial bus，USB)接口130，充电管理模块140，电源管理模块141，电池142，天线1，天线2，移动通信模块150，无线通信模块160，音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，传感器模块180，按键190，马达191，指示器192，摄像头193，显示屏194，以及用户标识模块(subscriber identification module，SIM)卡接口195等。其中传感器模块180可以包括压力传感器180A，陀螺仪传感器180B，气压传感器180C，磁传感器180D，加速度传感器180E，距离传感器180F，接近光传感器180G，指纹传感器180H，温度传感器180J，触摸传感器180K，环境光传感器180L，骨传导传感器180M等。
可以理解的是，本发明实施例示意的结构并不构成对电子设备100的具体限定。在本申请另一些实施例中，电子设备100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
处理器110可以包括一个或多个处理单元，例如：处理器110可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器(graphics processing unit，GPU)，图像信号处理器(image signal processor，ISP)，控制器，存储器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。
其中，控制器可以是电子设备100的神经中枢和指挥中心。控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器110中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器110中的存储器为高速缓冲存储器。该存储器可以保存处理器110刚用过或循环使用的指令或数据。如果处理器110需要再次使用该指令或数据，可从所述存储器中直接调用。避免了重复存取，减少了处理器110的等待时间，因而提高了系统的效率。
在一些实施例中，处理器110可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuit sound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口，用户标识模块(subscriber identity module，SIM)接口，和/或通用串行总线(universal serial bus， USB)接口等。
I2C接口是一种双向同步串行总线，包括一根串行数据线(serial data line，SDA)和一根串行时钟线(derail clock line，SCL)。在一些实施例中，处理器110可以包含多组I2C总线。处理器110可以通过不同的I2C总线接口分别耦合触摸传感器180K，充电器，闪光灯，摄像头193等。例如：处理器110可以通过I2C接口耦合触摸传感器180K，使处理器110与触摸传感器180K通过I2C总线接口通信，实现电子设备100的触摸功能。
I2S接口可以用于音频通信。在一些实施例中，处理器110可以包含多组I2S总线。处理器110可以通过I2S总线与音频模块170耦合，实现处理器110与音频模块170之间的通信。在一些实施例中，音频模块170可以通过I2S接口向无线通信模块160传递音频信号，实现通过蓝牙耳机接听电话的功能。
PCM接口也可以用于音频通信，将模拟信号抽样，量化和编码。在一些实施例中，音频模块170与无线通信模块160可以通过PCM总线接口耦合。在一些实施例中，音频模块170也可以通过PCM接口向无线通信模块160传递音频信号，实现通过蓝牙耳机接听电话的功能。所述I2S接口和所述PCM接口都可以用于音频通信。
UART接口是一种通用串行数据总线，用于异步通信。该总线可以为双向通信总线。它将要传输的数据在串行通信与并行通信之间转换。在一些实施例中，UART接口通常被用于连接处理器110与无线通信模块160。例如：处理器110通过UART接口与无线通信模块160中的蓝牙模块通信，实现蓝牙功能。在一些实施例中，音频模块170可以通过UART接口向无线通信模块160传递音频信号，实现通过蓝牙耳机播放音乐的功能。
MIPI接口可以被用于连接处理器110与显示屏194，摄像头193等外围器件。MIPI接口包括摄像头串行接口(camera serial interface，CSI)，显示屏串行接口(display serial interface，DSI)等。在一些实施例中，处理器110和摄像头193通过CSI接口通信，实现电子设备100的拍摄功能。处理器110和显示屏194通过DSI接口通信，实现电子设备100的显示功能。
GPIO接口可以通过软件配置。GPIO接口可以被配置为控制信号，也可被配置为数据信号。在一些实施例中，GPIO接口可以用于连接处理器110与摄像头193，显示屏194，无线通信模块160，音频模块170，传感器模块180等。GPIO接口还可以被配置为I2C接口，I2S接口，UART接口，MIPI接口等。
USB接口130是符合USB标准规范的接口，具体可以是Mini USB接口，Micro USB接口，USB Type C接口等。USB接口130可以用于连接充电器为电子设备100充电，也可以用于电子设备100与外围设备之间传输数据。也可以用于连接耳机，通过耳机播放音频。该接口还可以用于连接其他电子设备，例如AR设备等。
可以理解的是，本发明实施例示意的各模块间的接口连接关系，只是示意性说明，并不构成对电子设备100的结构限定。在本申请另一些实施例中，电子设备100也可以采用上述实施例中不同的接口连接方式，或多种接口连接方式的组合。
充电管理模块140用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。在一些有线充电的实施例中，充电管理模块140可以通过USB接口130接收有线充电器的充电输入。在一些无线充电的实施例中，充电管理模块140可以通过电 子设备100的无线充电线圈接收无线充电输入。充电管理模块140为电池142充电的同时，还可以通过电源管理模块141为电子设备供电。
电源管理模块141用于连接电池142，充电管理模块140与处理器110。电源管理模块141接收电池142和/或充电管理模块140的输入，为处理器110，内部存储器121，外部存储器，显示屏194，摄像头193，和无线通信模块160等供电。电源管理模块141还可以用于监测电池容量，电池循环次数，电池健康状态(漏电，阻抗)等参数。在其他一些实施例中，电源管理模块141也可以设置于处理器110中。在另一些实施例中，电源管理模块141和充电管理模块140也可以设置于同一个器件中。
电子设备100的无线通信功能可以通过天线1，天线2，移动通信模块150，无线通信模块160，调制解调处理器以及基带处理器等实现。
天线1和天线2用于发射和接收电磁波信号。电子设备100中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用，以提高天线的利用率。例如：可以将天线1复用为无线局域网的分集天线。在另外一些实施例中，天线可以和调谐开关结合使用。
移动通信模块150可以提供应用在电子设备100上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块150可以包括至少一个滤波器，开关，功率放大器，低噪声放大器(low noise amplifier，LNA)等。移动通信模块150可以由天线1接收电磁波，并对接收的电磁波进行滤波，放大等处理，传送至调制解调处理器进行解调。移动通信模块150还可以对经调制解调处理器调制后的信号放大，经天线1转为电磁波辐射出去。在一些实施例中，移动通信模块150的至少部分功能模块可以被设置于处理器110中。在一些实施例中，移动通信模块150的至少部分功能模块可以与处理器110的至少部分模块被设置在同一个器件中。
调制解调处理器可以包括调制器和解调器。其中，调制器用于将待发送的低频基带信号调制成中高频信号。解调器用于将接收的电磁波信号解调为低频基带信号。随后解调器将解调得到的低频基带信号传送至基带处理器处理。低频基带信号经基带处理器处理后，被传递给应用处理器。应用处理器通过音频设备(不限于扬声器170A，受话器170B等)输出声音信号，或通过显示屏194显示图像或视频。在一些实施例中，调制解调处理器可以是独立的器件。在另一些实施例中，调制解调处理器可以独立于处理器110，与移动通信模块150或其他功能模块设置在同一个器件中。
无线通信模块160可以提供应用在电子设备100上的包括无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，蓝牙(bluetooth，BT)，全球导航卫星系统(global navigation satellite system，GNSS)，调频(frequency modulation，FM)，近距离无线通信技术(near field communication，NFC)，红外技术(infrared，IR)等无线通信的解决方案。无线通信模块160可以是集成至少一个通信处理模块的一个或多个器件。无线通信模块160经由天线2接收电磁波，将电磁波信号调频以及滤波处理，将处理后的信号发送到处理器110。无线通信模块160还可以从处理器110接收待发送的信号，对其进行调频，放大，经天线2转为电磁波辐射出去。
在一些实施例中，电子设备100的天线1和移动通信模块150耦合，天线2和无线通信模块160耦合，使得电子设备100可以通过无线通信技术与网络以及其他设备通信。所 述无线通信技术可以包括全球移动通讯系统(global system for mobile communications，GSM)，通用分组无线服务(general packet radio service，GPRS)，码分多址接入(code division multiple access，CDMA)，宽带码分多址(wideband code division multiple access，WCDMA)，时分码分多址(time-division code division multiple access，TD-SCDMA)，长期演进(long term evolution，LTE)，BT，GNSS，WLAN，NFC，FM，和/或IR技术等。所述GNSS可以包括全球卫星定位系统(global positioning system，GPS)，全球导航卫星系统(global navigation satellite system，GLONASS)，北斗卫星导航系统(beidou navigation satellite system，BDS)，准天顶卫星系统(quasi-zenith satellite system，QZSS)和/或星基增强系统(satellite based augmentation systems，SBAS)。
电子设备100通过GPU，显示屏194，以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏194和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器110可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。
显示屏194用于显示图像，视频等。显示屏194包括显示面板。显示面板可以采用液晶显示屏(liquid crystal display，LCD)，有机发光二极管(organic light-emitting diode，OLED)，有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrix organic light emitting diode的，AMOLED)，柔性发光二极管(flex light-emitting diode，FLED)，Miniled，MicroLed，Micro-oLed，量子点发光二极管(quantum dot light emitting diodes，QLED)等。在一些实施例中，电子设备100可以包括1个或N个显示屏194，N为大于1的正整数。
电子设备100可以通过ISP，摄像头193，视频编解码器，GPU，显示屏194以及应用处理器等实现拍摄功能。
ISP用于处理摄像头193反馈的数据。例如，拍照时，打开快门，光线通过镜头被传递到摄像头感光元件上，光信号转换为电信号，摄像头感光元件将所述电信号传递给ISP处理，转化为肉眼可见的图像。ISP还可以对图像的噪点，亮度，肤色进行算法优化。ISP还可以对拍摄场景的曝光，色温等参数优化。在一些实施例中，ISP可以设置在摄像头193中。
摄像头193用于捕获静态图像或视频。物体通过镜头生成光学图像投射到感光元件。感光元件可以是电荷耦合器件(charge coupled device，CCD)或互补金属氧化物半导体(complementary metal-oxide-semiconductor，CMOS)光电晶体管。感光元件把光信号转换成电信号，之后将电信号传递给ISP转换成数字图像信号。ISP将数字图像信号输出到DSP加工处理。DSP将数字图像信号转换成标准的RGB，YUV等格式的图像信号。在一些实施例中，电子设备100可以包括1个或N个摄像头193，N为大于1的正整数。
数字信号处理器用于处理数字信号，除了可以处理数字图像信号，还可以处理其他数字信号。例如，当电子设备100在频点选择时，数字信号处理器用于对频点能量进行傅里叶变换等。
视频编解码器用于对数字视频压缩或解压缩。电子设备100可以支持一种或多种视频编解码器。这样，电子设备100可以播放或录制多种编码格式的视频，例如：动态图像专家组(moving picture experts group，MPEG)1，MPEG2，MPEG3，MPEG4等。
NPU为神经网络(neural-network，NN)计算处理器，通过借鉴生物神经网络结构， 例如借鉴人脑神经元之间传递模式，对输入信息快速处理，还可以不断的自学习。通过NPU可以实现电子设备100的智能认知等应用，例如：图像识别，人脸识别，语音识别，文本理解等。通过NPU还可以实现本申请实施例提供的决策模型。
外部存储器接口120可以用于连接外部存储卡，例如Micro SD卡，实现扩展电子设备100的存储能力。外部存储卡通过外部存储器接口120与处理器110通信，实现数据存储功能。例如将音乐，视频等文件保存在外部存储卡中。
内部存储器121可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。处理器110通过运行存储在内部存储器121的指令，从而执行电子设备100的各种功能应用以及数据处理。内部存储器121可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储电子设备100使用过程中所创建的数据(比如音频数据，电话本等)等。此外，内部存储器121可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。
电子设备100可以通过音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，以及应用处理器等实现音频功能。例如音乐播放，录音等。
音频模块170用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转换为数字音频信号。音频模块170还可以用于对音频信号编码和解码。在一些实施例中，音频模块170可以设置于处理器110中，或将音频模块170的部分功能模块设置于处理器110中。
扬声器170A，也称“喇叭”，用于将音频电信号转换为声音信号。电子设备100可以通过扬声器170A收听音乐，或收听免提通话。
受话器170B，也称“听筒”，用于将音频电信号转换成声音信号。当电子设备100接听电话或语音信息时，可以通过将受话器170B靠近人耳接听语音。
麦克风170C，也称“话筒”，“传声器”，用于将声音信号转换为电信号。当拨打电话或发送语音信息时，用户可以通过人嘴靠近麦克风170C发声，将声音信号输入到麦克风170C。电子设备100可以设置至少一个麦克风170C。在另一些实施例中，电子设备100可以设置两个麦克风170C，除了采集声音信号，还可以实现降噪功能。在另一些实施例中，电子设备100还可以设置三个，四个或更多麦克风170C，实现采集声音信号，降噪，还可以识别声音来源，实现定向录音功能等。
耳机接口170D用于连接有线耳机。耳机接口170D可以是USB接口130，也可以是3.5mm的开放移动电子设备平台(open mobile terminal platform，OMTP)标准接口，美国蜂窝电信工业协会(cellular telecommunications industry association of the USA，CTIA)标准接口。
压力传感器180A用于感受压力信号，可以将压力信号转换成电信号。在一些实施例中，压力传感器180A可以设置于显示屏194。压力传感器180A的种类很多，如电阻式压力传感器，电感式压力传感器，电容式压力传感器等。电容式压力传感器可以是包括至少两个具有导电材料的平行板。当有力作用于压力传感器180A，电极之间的电容改变。电子 设备100根据电容的变化确定压力的强度。当有触摸操作作用于显示屏194，电子设备100根据压力传感器180A检测所述触摸操作强度。电子设备100也可以根据压力传感器180A的检测信号计算触摸的位置。在一些实施例中，作用于相同触摸位置，但不同触摸操作强度的触摸操作，可以对应不同的操作指令。例如：当有触摸操作强度小于第一压力阈值的触摸操作作用于短消息应用图标时，执行查看短消息的指令。当有触摸操作强度大于或等于第一压力阈值的触摸操作作用于短消息应用图标时，执行新建短消息的指令。
陀螺仪传感器180B可以用于确定电子设备100的运动姿态。在一些实施例中，可以通过陀螺仪传感器180B确定电子设备100围绕三个轴(即，x，y和z轴)的角速度。陀螺仪传感器180B可以用于拍摄防抖。示例性的，当按下快门，陀螺仪传感器180B检测电子设备100抖动的角度，根据角度计算出镜头模组需要补偿的距离，让镜头通过反向运动抵消电子设备100的抖动，实现防抖。陀螺仪传感器180B还可以用于导航，体感游戏场景。
气压传感器180C用于测量气压。在一些实施例中，电子设备100通过气压传感器180C测得的气压值计算海拔高度，辅助定位和导航。
磁传感器180D包括霍尔传感器。电子设备100可以利用磁传感器180D检测翻盖皮套的开合。在一些实施例中，当电子设备100是翻盖机时，电子设备100可以根据磁传感器180D检测翻盖的开合。进而根据检测到的皮套的开合状态或翻盖的开合状态，设置翻盖自动解锁等特性。
加速度传感器180E可检测电子设备100在各个方向上(一般为三轴)加速度的大小。当电子设备100静止时可检测出重力的大小及方向。还可以用于识别电子设备姿态，应用于横竖屏切换，计步器等应用。
距离传感器180F，用于测量距离。电子设备100可以通过红外或激光测量距离。在一些实施例中，拍摄场景，电子设备100可以利用距离传感器180F测距以实现快速对焦。
接近光传感器180G可以包括例如发光二极管(LED)和光检测器，例如光电二极管。发光二极管可以是红外发光二极管。电子设备100通过发光二极管向外发射红外光。电子设备100使用光电二极管检测来自附近物体的红外反射光。当检测到充分的反射光时，可以确定电子设备100附近有物体。当检测到不充分的反射光时，电子设备100可以确定电子设备100附近没有物体。电子设备100可以利用接近光传感器180G检测用户手持电子设备100贴近耳朵通话，以便自动熄灭屏幕达到省电的目的。接近光传感器180G也可用于皮套模式，口袋模式自动解锁与锁屏。
环境光传感器180L用于感知环境光亮度。电子设备100可以根据感知的环境光亮度自适应调节显示屏194亮度。环境光传感器180L也可用于拍照时自动调节白平衡。环境光传感器180L还可以与接近光传感器180G配合，检测电子设备100是否在口袋里，以防误触。
指纹传感器180H用于采集指纹。电子设备100可以利用采集的指纹特性实现指纹解锁，访问应用锁，指纹拍照，指纹接听来电等。
温度传感器180J用于检测温度。在一些实施例中，电子设备100利用温度传感器180J检测的温度，执行温度处理策略。例如，当温度传感器180J上报的温度超过阈值，电子设备100执行降低位于温度传感器180J附近的处理器的性能，以便降低功耗实施热保护。在另一些实施例中，当温度低于另一阈值时，电子设备100对电池142加热，以避免低温导 致电子设备100异常关机。在其他一些实施例中，当温度低于又一阈值时，电子设备100对电池142的输出电压执行升压，以避免低温导致的异常关机。
触摸传感器180K，也称“触控面板”。触摸传感器180K可以设置于显示屏194，由触摸传感器180K与显示屏194组成触摸屏，也称“触控屏”。触摸传感器180K用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作传递给应用处理器，以确定触摸事件类型。可以通过显示屏194提供与触摸操作相关的视觉输出。在另一些实施例中，触摸传感器180K也可以设置于电子设备100的表面，与显示屏194所处的位置不同。
骨传导传感器180M可以获取振动信号。在一些实施例中，骨传导传感器180M可以获取人体声部振动骨块的振动信号。骨传导传感器180M也可以接触人体脉搏，接收血压跳动信号。在一些实施例中，骨传导传感器180M也可以设置于耳机中，结合成骨传导耳机。音频模块170可以基于所述骨传导传感器180M获取的声部振动骨块的振动信号，解析出语音信号，实现语音功能。应用处理器可以基于所述骨传导传感器180M获取的血压跳动信号解析心率信息，实现心率检测功能。
按键190包括开机键，音量键等。按键190可以是机械按键。也可以是触摸式按键。电子设备100可以接收按键输入，产生与电子设备100的用户设置以及功能控制有关的键信号输入。
马达191可以产生振动提示。马达191可以用于来电振动提示，也可以用于触摸振动反馈。例如，作用于不同应用(例如拍照，音频播放等)的触摸操作，可以对应不同的振动反馈效果。作用于显示屏194不同区域的触摸操作，马达191也可对应不同的振动反馈效果。不同的应用场景(例如：时间提醒，接收信息，闹钟，游戏等)也可以对应不同的振动反馈效果。触摸振动反馈效果还可以支持自定义。
指示器192可以是指示灯，可以用于指示充电状态，电量变化，也可以用于指示消息，未接来电，通知等。
SIM卡接口195用于连接SIM卡。SIM卡可以通过插入SIM卡接口195，或从SIM卡接口195拔出，实现和电子设备100的接触和分离。电子设备100可以支持1个或N个SIM卡接口，N为大于1的正整数。SIM卡接口195可以支持Nano SIM卡，Micro SIM卡，SIM卡等。同一个SIM卡接口195可以同时插入多张卡。所述多张卡的类型可以相同，也可以不同。SIM卡接口195也可以兼容不同类型的SIM卡。SIM卡接口195也可以兼容外部存储卡。电子设备100通过SIM卡和网络交互，实现通话以及数据通信等功能。在一些实施例中，电子设备100采用eSIM，即：嵌入式SIM卡。eSIM卡可以嵌在电子设备100中，不能和电子设备100分离。
电子设备100的软件系统可以采用分层架构，事件驱动架构，微核架构，微服务架构，或云架构。本发明实施例以分层架构的Android系统为例，示例性说明电子设备100的软件结构。
图16是本申请实施例提供的电子设备100的软件结构框图。
分层架构将软件分成若干个层，每一层都有清晰的角色和分工。层与层之间通过软件 接口通信。在一些实施例中，将Android系统分为四层，从上至下分别为应用程序层，应用程序框架层，安卓运行时(Android runtime)和系统库，以及内核层。
应用程序层可以包括一系列应用程序包。
如图16所示，应用程序包可以包括相机，图库，日历，通话，地图，导航，WLAN，蓝牙，音乐，视频，短信息等应用程序。
应用程序框架层为应用程序层的应用程序提供应用编程接口(application programming interface，API)和编程框架。应用程序框架层包括一些预先定义的函数。
如图16所示，应用程序框架层可以包括窗口管理器，内容提供器，视图系统，电话管理器，资源管理器，通知管理器等。
窗口管理器用于管理窗口程序。窗口管理器可以获取显示屏大小，判断是否有状态栏，锁定屏幕，截取屏幕等。
内容提供器用来存放和获取数据，并使这些数据可以被应用程序访问。所述数据可以包括视频，图像，音频，拨打和接听的电话，浏览历史和书签，电话簿等。
视图系统包括可视控件，例如显示文字的控件，显示图片的控件等。视图系统可用于构建应用程序。显示界面可以由一个或多个视图组成的。例如，包括短信通知图标的显示界面，可以包括显示文字的视图以及显示图片的视图。
电话管理器用于提供电子设备100的通信功能。例如通话状态的管理(包括接通，挂断等)。
资源管理器为应用程序提供各种资源，比如本地化字符串，图标，图片，布局文件，视频文件等等。
通知管理器使应用程序可以在状态栏中显示通知信息，可以用于传达告知类型的消息，可以短暂停留后自动消失，无需用户交互。比如通知管理器被用于告知下载完成，消息提醒等。通知管理器还可以是以图表或者滚动条文本形式出现在系统顶部状态栏的通知，例如后台运行的应用程序的通知，还可以是以对话窗口形式出现在屏幕上的通知。例如在状态栏提示文本信息，发出提示音，电子设备振动，指示灯闪烁等。
Android Runtime包括核心库和虚拟机。Android runtime负责安卓系统的调度和管理。
核心库包含两部分：一部分是java语言需要调用的功能函数，另一部分是安卓的核心库。
应用程序层和应用程序框架层运行在虚拟机中。虚拟机将应用程序层和应用程序框架层的java文件执行为二进制文件。虚拟机用于执行对象生命周期的管理，堆栈管理，线程管理，安全和异常的管理，以及垃圾回收等功能。
系统库可以包括多个功能模块。例如：表面管理器(surface manager)，媒体库(Media Libraries)，三维图形处理库(例如：OpenGL ES)，2D图形引擎(例如：SGL)等。
表面管理器用于对显示子系统进行管理，并且为多个应用程序提供了2D和3D图层的融合。
媒体库支持多种常用的音频，视频格式回放和录制，以及静态图像文件等。媒体库可以支持多种音视频编码格式，例如:MPEG4，H.264，MP3，AAC，AMR，JPG，PNG等。
三维图形处理库用于实现三维图形绘图，图像渲染，合成，和图层处理等。
2D图形引擎是2D绘图的绘图引擎。
内核层是硬件和软件之间的层。内核层至少包含显示驱动，摄像头驱动，音频驱动，传感器驱动。
下面结合捕获拍照场景，示例性说明电子设备100软件以及硬件的工作流程。
当触摸传感器180K接收到触摸操作，相应的硬件中断被发给内核层。内核层将触摸操作加工成原始输入事件(包括触摸坐标，触摸操作的时间戳等信息)。原始输入事件被存储在内核层。应用程序框架层从内核层获取原始输入事件，识别该输入事件所对应的控件。以该触摸操作是触摸单击操作，该单击操作所对应的控件为相机应用图标的控件为例，相机应用调用应用框架层的接口，启动相机应用，进而通过调用内核层启动摄像头驱动，通过摄像头193捕获静态图像或视频。
上述实施例中所用，根据上下文，术语“当…时”可以被解释为意思是“如果…”或“在…后”或“响应于确定…”或“响应于检测到…”。类似地，根据上下文，短语“在确定…时”或“如果检测到(所陈述的条件或事件)”可以被解释为意思是“如果确定…”或“响应于确定…”或“在检测到(所陈述的条件或事件)时”或“响应于检测到(所陈述的条件或事件)”。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线)或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如DVD)、或者半导体介质(例如固态硬盘)等。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，该流程可以由计算机程序来指令相关的硬件完成，该程序可存储于计算机可读取存储介质中，该程序在执行时，可包括如上述各方法实施例的流程。而前述的存储介质包括：ROM或随机存储记忆体RAM、磁碟或者光盘等各种可存储程序代码的介质。

Claims (18)

  1. 一种图像选优方法，其特征在于，所述方法包括：
    电子设备检测第一反馈信息，所述第一反馈信息包含多张图像和作用在所述多张图像中的图像的用户操作；
    所述电子设备根据所述第一反馈信息，调整决策模型的参数以得到更新的决策模型；
    所述电子设备根据所述更新的决策模型，从第一图像组中选出第一图像作为所述第一图像组的优选图像。
  2. 根据权利要求1所述的方法，其特征在于，所述电子设备检测第一反馈信息之前，所述方法还包括：
    所述电子设备显示第一用户界面，所述第一用户界面包含第二图像组，所述第二图像组是连拍得到的图像，所述第二图像组包含第二图像和第三图像，所述第二图像是所述电子设备根据所述决策模型选出的所述第二图像组的优选图像；
    所述电子设备检测第一反馈信息，包括：
    所述电子设备在所述第一用户界面上检测第一用户操作，响应于所述第一用户操作，所述电子设备将所述第二图像组的优选图像修改为所述第三图像；
    所述第一反馈信息包括所述第一用户操作、所述第二图像和所述第三图像。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第一反馈信息包括对图库中的图像的操作记录和所述操作记录对应的图像，所述操作记录指示以下一项或多项操作：删除操作、浏览操作、收藏操作和分享操作。
  4. 根据权利要求1至3任一项所述的方法，其特征在于，所述第一反馈信息包括，第一人脸特征和包含所述第一人脸特征的图像在图库中的占比；
    其中：所述第一人脸特征是所述图库中包含图像数量最多的人脸特征，所述图库中包含所述电子设备中已存储的图像。
  5. 根据权利要求4所述的方法，其特征在于，所述电子设备根据所述第一反馈信息，调整决策模型的参数以得到更新的决策模型，包括：
    所述电子设备将所述第一人脸特征的人脸表情评分在所述决策模型中所占的权重调大；所述人脸表情评分用于对图像内人脸特征的表情进行评分；其中，所述第一图像组中每张图像包含一个或多个人脸特征，所述一个或多个人脸特征包含所述第一人脸特征。
  6. 根据权利要求4所述的方法，其特征在于，所述电子设备根据所述第一反馈信息，调整决策模型的参数以得到更新的决策模型，包括：
    所述电子设备将所述第一人脸特征的人像身材比例评分在所述决策模型中所占的权重调大；所述人像身材比例评分用于对图像内人脸特征的身材比例进行评分；其中，所述第 一图像组中每张图像包含一个或多个人脸特征，所述一个或多个人脸特征包含所述第一人脸特征。
  7. 根据权利要求1至6任一项所述的方法，其特征在于，所述电子设备根据所述更新的决策模型，从第一图像组中选出第一图像作为所述第一图像组的优选图像之前，所述方法还包括：
    所述电子设备显示相机应用界面，所述相机应用界面包含拍摄控件；
    响应于作用在所述拍摄控件的第二用户操作，所述电子设备连拍得到第一图像组；
    所述电子设备根据所述更新的决策模型，从第一图像组中选出第一图像作为所述第一图像组的优选图像之后，所述方法还包括：
    响应于用于显示所述第一图像组的第三用户操作，所述电子设备显示连拍图像界面，所述连拍图像界面包含所述第一图像和所述第一图像组中每张图像的缩略图。
  8. 根据权利要求1至6任一项所述的方法，其特征在于，所述电子设备根据所述更新的决策模型，从第一图像组中选出第一图像作为所述第一图像组的优选图像之前，所述方法还包括：
    所述电子设备从所述图库中检测第一图像组；其中，所述第一图像组的缩略图在图库应用界面上相邻显示，所述第一图像组中每张图像均包含第一图像特征，所述第一图像特征包含第二人脸特征或者第一拍摄场景；
    所述电子设备根据所述更新的决策模型，从第一图像组中选出第一图像作为所述第一图像组的优选图像之后，所述方法还包括：
    响应于作用在图库图标的第四用户操作，所述电子设备显示所述图库应用界面，所述图库应用界面上包含所述第一图像组中图像的缩略图；其中，所述第一图像的缩略图的尺寸大于所述第一图像组中其他图像的缩略图的尺寸。
  9. 根据权利要求1至8任一项所述的方法，其特征在于，所述电子设备根据所述更新的决策模型，从第一图像组中选出第一图像作为所述第一图像组的优选图像之前，所述方法还包括：
    所述电子设备显示第二用户界面，所述第二用户界面包含多个图像特征选项和确定控件；其中，所述多个图像特征选项中每个图像特征选项对应有图像特征；
    响应于作用在第一选项的第五用户操作，所述电子设备将所述第一选项由未选中状态显示为选中状态；所述多个图像特征选项包含所述第一选项；
    响应于作用在所述确定控件的第六用户操作，所述电子设备根据所述第一选项对应的图像特征调整所述决策模型的参数，以得到所述更新的决策模型。
  10. 一种电子设备，其特征在于，所述电子设备包括：一个或多个处理器、存储器和显示屏；
    所述存储器与所述一个或多个处理器耦合，所述存储器用于存储计算机程序代码，所 述计算机程序代码包括计算机指令，所述一个或多个处理器调用所述计算机指令以使得所述电子设备执行：
    检测第一反馈信息，所述第一反馈信息包含多张图像和作用在所述多张图像中的图像的用户操作；
    根据所述第一反馈信息，调整决策模型的参数以得到更新的决策模型；
    根据所述更新的决策模型，从第一图像组中选出第一图像作为所述第一图像组的优选图像。
  11. 根据权利要求10所述的电子设备，其特征在于，所述一个或多个处理器，还用于调用所述计算机指令以使得所述电子设备执行：
    显示第一用户界面，所述第一用户界面包含第二图像组，所述第二图像组是连拍得到的图像，所述第二图像组包含第二图像和第三图像，所述第二图像是所述电子设备根据所述决策模型选出的所述第二图像组的优选图像；
    所述一个或多个处理器，具体用于调用所述计算机指令以使得所述电子设备执行：
    在所述第一用户界面上检测第一用户操作，响应于所述第一用户操作，将所述第二图像组的优选图像修改为所述第三图像；
    所述第一反馈信息包括所述第一用户操作、所述第二图像和所述第三图像。
  12. 根据权利要求10或11所述的电子设备，其特征在于，所述第一反馈信息包括对图库中的图像的操作记录和所述操作记录对应的图像，所述操作记录指示以下一项或多项操作：删除操作、浏览操作、收藏操作和分享操作。
  13. 根据权利要求10至12任一项所述的电子设备，其特征在于，所述第一反馈信息包括，第一人脸特征和包含所述第一人脸特征的图像在图库中的占比；
    其中：所述第一人脸特征是所述图库中包含图像数量最多的人脸特征，所述图库中包含所述电子设备中已存储的图像。
  14. 根据权利要求13所述的电子设备，其特征在于，所述一个或多个处理器，具体用于调用所述计算机指令以使得所述电子设备执行：
    将所述第一人脸特征的人脸表情评分在所述决策模型中所占的权重调大；所述人脸表情评分用于对图像内人脸特征的表情进行评分；其中，所述第一图像组中每张图像包含一个或多个人脸特征，所述一个或多个人脸特征包含所述第一人脸特征。
  15. 根据权利要求13所述的电子设备，其特征在于，所述一个或多个处理器，具体用于调用所述计算机指令以使得所述电子设备执行：
    将所述第一人脸特征的人像身材比例评分在所述决策模型中所占的权重调大；所述人像身材比例评分用于对图像内人脸特征的身材比例进行评分；其中，所述第一图像组中每张图像包含一个或多个人脸特征，所述一个或多个人脸特征包含所述第一人脸特征。
  16. 根据权利要求10至15任一项所述的电子设备，其特征在于，所述一个或多个处理器，还用于调用所述计算机指令以使得所述电子设备执行：
    显示相机应用界面，所述相机应用界面包含拍摄控件；
    响应于作用在所述拍摄控件的第二用户操作，连拍得到第一图像组；
    响应于用于显示所述第一图像组的第三用户操作，显示连拍图像界面，所述连拍图像界面包含所述第一图像和所述第一图像组中每张图像的缩略图。
  17. 根据权利要求10至15任一项所述的电子设备，其特征在于，所述一个或多个处理器，还用于调用所述计算机指令以使得所述电子设备执行：
    从所述图库中检测第一图像组；其中，所述第一图像组的缩略图在图库应用界面上相邻显示，所述第一图像组中每张图像均包含第一图像特征，所述第一图像特征包含第二人脸特征或者第一拍摄场景；
    所述一个或多个处理器，还用于调用所述计算机指令以使得所述电子设备执行：
    响应于作用在图库图标的第四用户操作，显示所述图库应用界面，所述图库应用界面上包含所述第一图像组中图像的缩略图；其中，所述第一图像的缩略图的尺寸大于所述第一图像组中其他图像的缩略图的尺寸。
  18. 根据权利要求10至17任一项所述的电子设备，其特征在于，所述一个或多个处理器，还用于调用所述计算机指令以使得所述电子设备执行：
    显示第二用户界面，所述第二用户界面包含多个图像特征选项和确定控件；其中，所述多个图像特征选项中每个图像特征选项对应有图像特征；
    响应于作用在第一选项的第五用户操作，将所述第一选项由未选中状态显示为选中状态；所述多个图像特征选项包含所述第一选项；
    响应于作用在所述确定控件的第六用户操作，根据所述第一选项对应的图像特征调整所述决策模型的参数，以得到所述更新的决策模型。
PCT/CN2020/116963 2019-09-29 2020-09-23 图像选优方法及电子设备 WO2021057752A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/764,391 US20220343648A1 (en) 2019-09-29 2020-09-23 Image selection method and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910936462.7A CN112580400B (zh) 2019-09-29 2019-09-29 图像选优方法及电子设备
CN201910936462.7 2019-09-29

Publications (1)

Publication Number Publication Date
WO2021057752A1 true WO2021057752A1 (zh) 2021-04-01

Family

ID=75110788

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/116963 WO2021057752A1 (zh) 2019-09-29 2020-09-23 图像选优方法及电子设备

Country Status (3)

Country Link
US (1) US20220343648A1 (zh)
CN (1) CN112580400B (zh)
WO (1) WO2021057752A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113011387A (zh) * 2021-04-20 2021-06-22 上海商汤科技开发有限公司 网络训练及人脸活体检测方法、装置、设备及存储介质
US11640705B1 (en) * 2021-12-17 2023-05-02 Lodestar Software Inc. Active learning with human feedback loop to optimize future sampling priority

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20200100918A (ko) * 2019-02-19 2020-08-27 삼성전자주식회사 카메라를 이용하는 어플리케이션을 통해 다양한 기능을 제공하는 전자 장치 및 그의 동작 방법
CN113408632A (zh) * 2021-06-28 2021-09-17 北京百度网讯科技有限公司 提高图像分类准确性的方法、装置、电子设备及存储介质
CN114979738B (zh) * 2022-05-17 2023-03-14 深圳市旭联信息技术有限公司 无线投屏方法、接收器及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004135029A (ja) * 2002-10-10 2004-04-30 Fuji Photo Film Co Ltd デジタルカメラ
CN104185981A (zh) * 2013-10-23 2014-12-03 华为终端有限公司 从连拍图像中选择图像的方法和终端
CN105893578A (zh) * 2016-03-31 2016-08-24 青岛海信移动通信技术股份有限公司 一种照片选择的方法及装置
CN107659722A (zh) * 2017-09-25 2018-02-02 维沃移动通信有限公司 一种图像选择方法及移动终端
CN108876782A (zh) * 2018-06-27 2018-11-23 Oppo广东移动通信有限公司 回忆视频创建方法及相关装置

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1704710A4 (en) * 2003-12-24 2007-09-19 Walker Digital Llc METHOD AND DEVICE FOR AUTOMATIC COLLECTION AND MANAGEMENT OF IMAGES
JP5083090B2 (ja) * 2007-09-18 2012-11-28 ソニー株式会社 表示制御装置、撮像装置、表示制御方法およびプログラム
US8248482B2 (en) * 2008-05-15 2012-08-21 Samsung Electronics Co., Ltd. Digital camera personalization
US9124800B2 (en) * 2012-02-13 2015-09-01 Htc Corporation Auto burst image capture method applied to a mobile device, method for tracking an object applied to a mobile device, and related mobile device
KR102379171B1 (ko) * 2015-02-27 2022-03-25 삼성전자주식회사 전자 장치 및 그의 영상 표시 방법
US10038836B2 (en) * 2015-03-17 2018-07-31 Mediatek Inc. Automatic image capture during preview and image recommendation
CN106570028B (zh) * 2015-10-10 2020-12-25 比亚迪股份有限公司 移动终端及模糊图像的删除方法和装置
CN105635567A (zh) * 2015-12-24 2016-06-01 小米科技有限责任公司 拍照方法和装置
US10091414B2 (en) * 2016-06-24 2018-10-02 International Business Machines Corporation Methods and systems to obtain desired self-pictures with an image capture device
US9807301B1 (en) * 2016-07-26 2017-10-31 Microsoft Technology Licensing, Llc Variable pre- and post-shot continuous frame buffering with automated image selection and enhancement
WO2018093182A1 (en) * 2016-11-16 2018-05-24 Samsung Electronics Co., Ltd. Image management method and apparatus thereof
CN107025437A (zh) * 2017-03-16 2017-08-08 南京邮电大学 基于智能构图及微表情分析的智能拍照方法及装置
CN107871011B (zh) * 2017-11-21 2020-04-24 Oppo广东移动通信有限公司 图像处理方法、装置、移动终端及计算机可读存储介质
US10671887B2 (en) * 2017-12-05 2020-06-02 Axis Ab Best image crop selection
CN108184063A (zh) * 2018-01-02 2018-06-19 联想(北京)有限公司 一种图像处理方法及装置
CN109831618A (zh) * 2018-12-10 2019-05-31 平安科技（深圳）有限公司 基于表情的拍照方法、计算机可读存储介质及终端设备
CN110012225B (zh) * 2019-03-27 2021-09-24 维沃移动通信有限公司 一种图像处理的方法、装置以及移动终端
CN110543579A (zh) * 2019-07-26 2019-12-06 华为技术有限公司 一种图像显示方法与电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004135029A (ja) * 2002-10-10 2004-04-30 Fuji Photo Film Co Ltd デジタルカメラ
CN104185981A (zh) * 2013-10-23 2014-12-03 华为终端有限公司 从连拍图像中选择图像的方法和终端
CN105893578A (zh) * 2016-03-31 2016-08-24 青岛海信移动通信技术股份有限公司 一种照片选择的方法及装置
CN107659722A (zh) * 2017-09-25 2018-02-02 维沃移动通信有限公司 一种图像选择方法及移动终端
CN108876782A (zh) * 2018-06-27 2018-11-23 Oppo广东移动通信有限公司 回忆视频创建方法及相关装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113011387A (zh) * 2021-04-20 2021-06-22 上海商汤科技开发有限公司 网络训练及人脸活体检测方法、装置、设备及存储介质
US11640705B1 (en) * 2021-12-17 2023-05-02 Lodestar Software Inc. Active learning with human feedback loop to optimize future sampling priority
US11935278B1 (en) * 2021-12-17 2024-03-19 Lodestar Software Inc. Image labeling for artificial intelligence datasets

Also Published As

Publication number Publication date
CN112580400B (zh) 2022-08-05
US20220343648A1 (en) 2022-10-27
CN112580400A (zh) 2021-03-30

Similar Documents

Publication Publication Date Title
WO2020078299A1 (zh) 一种处理视频文件的方法及电子设备
WO2021057752A1 (zh) 图像选优方法及电子设备
CN110471606B (zh) 输入方法及电子设备
WO2020029306A1 (zh) 一种图像拍摄方法及电子设备
CN109981885B (zh) 一种电子设备在来电时呈现视频的方法和电子设备
US11470246B2 (en) Intelligent photographing method and system, and related apparatus
WO2020192761A1 (zh) 记录用户情感的方法及相关装置
WO2021082815A1 (zh) 一种显示要素的显示方法和电子设备
CN111625670A (zh) 一种图片分组方法及设备
CN112783379A (zh) 一种选择图片的方法和电子设备
WO2020259554A1 (zh) 可进行学习的关键词搜索方法和电子设备
CN112214636A (zh) 音频文件的推荐方法、装置、电子设备以及可读存储介质
US20230276125A1 (en) Photographing method and electronic device
CN112529645A (zh) 一种图片的布局方法及电子设备
CN113170037A (zh) 一种拍摄长曝光图像的方法和电子设备
CN112150499A (zh) 图像处理方法及相关装置
WO2022156473A1 (zh) 一种播放视频的方法及电子设备
CN115115679A (zh) 一种图像配准方法及相关设备
WO2020073317A1 (zh) 文件管理方法及电子设备
CN115525783B (zh) 图片显示方法及电子设备
WO2022143921A1 (zh) 一种图像重建方法、相关装置及系统
CN113923372A (zh) 曝光调整方法及相关设备
WO2022228010A1 (zh) 一种生成封面的方法及电子设备
WO2023036084A1 (zh) 一种图像处理方法及相关装置
WO2023207799A1 (zh) 消息处理方法和电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20867679

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20867679

Country of ref document: EP

Kind code of ref document: A1