WO2017107855A1 - Procédé et dispositif de recherche d'images - Google Patents

Procédé et dispositif de recherche d'images Download PDF

Info

Publication number
WO2017107855A1
WO2017107855A1 PCT/CN2016/110193 CN2016110193W WO2017107855A1 WO 2017107855 A1 WO2017107855 A1 WO 2017107855A1 CN 2016110193 W CN2016110193 W CN 2016110193W WO 2017107855 A1 WO2017107855 A1 WO 2017107855A1
Authority
WO
WIPO (PCT)
Prior art keywords
picture
search
dimension
image
search dimension
Prior art date
Application number
PCT/CN2016/110193
Other languages
English (en)
Chinese (zh)
Inventor
康琳
马士龙
Original Assignee
阿里巴巴集团控股有限公司
康琳
马士龙
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 阿里巴巴集团控股有限公司, 康琳, 马士龙 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2017107855A1 publication Critical patent/WO2017107855A1/fr

Links

Images

Classifications

    • 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]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying
    • 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
    • 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]
    • G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
    • G06F3/0485—Scrolling or panning
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a picture search method and apparatus.
  • a large number of pictures can be stored in a mobile phone, such as a picture that can be stored by a mobile phone, or an image that is stored by other means.
  • an embodiment of the present application provides a picture search method and apparatus.
  • the picture search instruction being generated according to the detected first operation for the first picture
  • Searching according to the search dimension corresponding to the first picture, a second picture that matches the first picture in the search dimension;
  • the first operation for the first picture comprises:
  • the operation of the user interface UI component for triggering the image search is selected in the screen display area of the first picture or in the preview view window.
  • the first screen touch operation performed in the screen display area of the first picture includes: a multi-finger zoom sliding operation performed in a screen display area of the first picture; or, in the A sliding operation of a single finger in a set direction in a screen display area of a picture.
  • the determining the search dimension corresponding to the first picture comprises:
  • a third screen touch operation performed in a screen display area of a picture is detected and popped up, and one search dimension option in the popup menu corresponds to one or more search dimensions; or
  • the search dimension comprises one or more of the following dimensions:
  • the search dimension of a photo-based device or source is a photo-based device or source.
  • the searching for a second image that matches the first image on the search dimension according to the search dimension corresponding to the first image including:
  • the first operation for the first picture is a first screen touch operation performed in a screen display area of the first picture, and the first picture is extracted according to a pixel of the first picture Characteristic information, including:
  • Extracting feature information of the first picture in the active area Extracting feature information of the first picture in the active area.
  • searching for the second picture that matches the first picture in the search dimension comprises: searching from the locally stored picture library and/or the network side stored picture library on the search dimension and the The second picture matches the first picture.
  • the outputting the search result comprises: displaying the searched second picture in a picture preview manner according to the order of matching degree, the number of the second pictures being one or more.
  • the outputting the search result comprises: displaying the found second image by using N sub-windows, each sub-window is for displaying a preview view of the second image or the second image, which is found based on one search dimension, each sub-window It is allowed to switch to display a preview view of the second picture or the second picture found based on the corresponding search dimension according to the sliding touch operation, where N is an integer greater than or equal to 1.
  • An acquiring module configured to acquire a picture search instruction, where the picture search instruction is generated according to the detected first operation for the first picture
  • a determining module configured to determine a search dimension corresponding to the first picture
  • a searching module configured to search, according to the search dimension corresponding to the first picture, a second picture that matches the first picture in the search dimension;
  • Output module for outputting the search results.
  • the first operation for the first picture comprises:
  • the operation of the user interface UI component for triggering the image search is selected in the screen display area of the first picture or in the preview view window.
  • the first screen touch operation performed in the screen display area of the first picture includes: a multi-finger zoom sliding operation performed in a screen display area of the first picture; or, in the A sliding operation of a single finger in a set direction in a screen display area of a picture.
  • the determining module is specifically configured to:
  • a third screen touch operation performed in a screen display area of a picture is detected and popped up, and one search dimension option in the popup menu corresponds to one or more search dimensions; or
  • the search dimension corresponding to the detected first operation, where the first The operation corresponds to one or more search dimensions.
  • the search dimension comprises one or more of the following dimensions:
  • the search dimension of a photo-based device or source is a photo-based device or source.
  • the searching module is specifically configured to: when the search dimension includes a search dimension based on an object in the image, extract feature information of the first image, and search for a second image according to the extracted feature information, where the second The feature information of the picture matches the feature information of the first picture.
  • the searching module is specifically configured to: when the first operation for the first picture is a first screen touch operation performed in a screen display area of the first picture, according to a screen in the first picture And performing a first screen touch operation performed in the display area, acquiring an action area of the first screen touch operation, and extracting feature information of the first picture in the active area.
  • the searching module is specifically configured to: search for a second picture that matches the first picture in the search dimension from a locally stored picture library and/or a picture library stored in the network side.
  • the output module is specifically configured to display the second picture that is found in a picture preview manner according to the order of matching degree, the number of the second pictures being one or more.
  • the output module is specifically configured to display the searched second image by using N sub-windows, each sub-window is configured to display a preview view of the second image or the second image that is found based on one search dimension, each sub-window It is allowed to switch to display a preview view of the second picture or the second picture found based on the corresponding search dimension according to the sliding touch operation, where N is an integer greater than or equal to 1.
  • a memory for storing computer program instructions
  • a processor coupled to the memory for reading computer program instructions stored by the memory and, in response, performing the following operations:
  • the picture search instruction being generated according to the detected first operation for the first picture
  • Searching according to the search dimension corresponding to the first picture, a second picture that matches the first picture in the search dimension;
  • the first operation for the first picture comprises:
  • the operation of the user interface UI component for triggering the image search is selected in the screen display area of the first picture or in the preview view window.
  • the first screen touch operation performed in the screen display area of the first picture includes:
  • the processor is specifically configured to:
  • the option for selecting the search dimension in the pop-up menu of the first picture is selected
  • the search dimension corresponding to the first picture is determined as a search dimension corresponding to the first picture, wherein the pop-up menu is popped after the third screen touch operation performed in the screen display area of the first picture is detected.
  • One search dimension option in the popup menu corresponds to one or more search dimensions; or
  • the search dimension comprises one or more of the following dimensions:
  • the search dimension of a photo-based device or source is a photo-based device or source.
  • the processor is specifically configured to: when the search dimension includes, based on a search dimension of an object in the image, extract feature information of the first image, and search for a second image according to the extracted feature information, where the second The feature information of the picture matches the feature information of the first picture.
  • the processor is specifically configured to: when the first operation for the first picture is a first screen touch operation performed in a screen display area of the first picture, according to a screen in the first picture And performing a first screen touch operation performed in the display area, acquiring an action area of the first screen touch operation, and extracting feature information of the first picture in the active area.
  • the processor is specifically configured to: search for a second picture that matches the first picture in the search dimension from a locally stored picture library and/or a picture library stored in the network side.
  • the processor is specifically configured to: in a picture preview manner, instruct the display to display the found second picture in an order of matching degree from high to low, the number of the second pictures being one or more.
  • the processor is specifically configured to: instruct the display to display the found second image by using N sub-windows, each sub-window is used to display the second image found based on a search dimension.
  • N is an integer greater than or equal to 1.
  • FIG. 1 is a schematic diagram of a network architecture applicable to an embodiment of the present application
  • FIG. 2 is a schematic diagram of a picture search process according to an embodiment of the present application.
  • FIG. 4 and FIG. 5 are schematic diagrams of screen touch operations for triggering a similar picture search process in an embodiment of the present application
  • FIG. 6 is a schematic diagram showing display of search results in an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a picture search apparatus according to an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a terminal according to an embodiment of the present application.
  • An embodiment of the present application provides an automatic picture search solution implemented on a terminal.
  • the solution provided by the embodiment of the present application can be applied to a mobile terminal, a PC (personal computer), or a smart device, and the mobile terminal can be a mobile phone, a PDA (Personal Digital Assistant), a smart wearable device, or the like. Especially suitable for mobile smart devices with touch screens.
  • FIG. 1 exemplarily shows a network architecture to which the embodiment of the present application is applied.
  • the network architecture may include a terminal and a server on the network side, and the terminal and the server enter through the network. Line communication.
  • the servers in the above architecture can be used to provide storage or access services to the user's photo library.
  • the user picture library is used to store the picture of the user. For example, the user can take a picture through the mobile phone and upload it to the user picture library for storage.
  • the server can also provide a data synchronization service. Through data synchronization, pictures stored on the terminal can be synchronously stored or updated into the user picture library.
  • the terminal in the above architecture can implement the image search method provided by the embodiment of the present application. Further, in the picture search process, the picture in the picture library of the terminal may be searched, or the picture of the user of the terminal in the user picture library may be searched by the server, or both the local picture library of the terminal and the network side may be searched. Photo gallery.
  • the terminal and the server can exchange information through the network, and the network can be a wide area network, a local area network or the Internet, or an Internet using mobile communication technology.
  • the terminal can access the Internet wirelessly, and the server is usually connected to the Internet by wire.
  • the terminal and the server can adopt cloud computing technology to implement information processing based on powerful functions of the cloud computing technology.
  • Servers and terminals can use cloud-based technology-based operating systems, such as YunOS, to consolidate cloud and terminal resources and services.
  • FIG. 2 it is a schematic diagram of a picture search process provided by an embodiment of the present application, where the process can be implemented on a terminal side. As shown, the process can include the following steps:
  • Step 201 Acquire a picture search instruction for the first picture, the picture search instruction is generated according to the detected first operation for the first picture. That is, after the first operation for the first picture is detected, the execution of the following steps 202 to 204 may be triggered.
  • the "first picture” does not specifically refer to a certain type of picture, but is a way of describing a convenient use.
  • the first operation for the first picture may include one of the following operations:
  • Operation 1 A first screen touch operation performed in a screen display area of the first picture.
  • the first picture is displayed in the picture display interface, such as being displayed in a normal size (or highlighted) in the picture browsing window, instead of only displaying its preview view, in this case, if the user Performing a screen touch operation in the display area of the first picture triggers a similar picture search process with the first picture as a reference.
  • the first screen touch operation performed in the screen display area of the first picture may be a single-finger touch operation (also referred to as a single touch operation) performed in the screen display area of the first picture, or may be a multi-finger operation.
  • the touch operation also referred to as a multi-touch operation
  • the embodiment of the present application does not limit the type of the touch operation, as long as the touch operation capable of triggering the similar picture search process is defined in advance.
  • the embodiment of the present application selects a specific screen touch operation to trigger a similar picture search process. For example, one of the following screen touch operations may be selected to trigger a similar image search process:
  • the multi-finger zooming operation may be a two-finger pinch sliding operation, which is not limited in this embodiment of the present application.
  • the multi-finger zooming operation may be a two-finger pinch sliding operation, which is not limited in this embodiment of the present application.
  • FIG. 3 when only the first picture is displayed in the picture browsing window 301, if the user performs the two-finger pinch-sliding operation 303 in the display area 302 of the first picture, this case Next, after the operation is detected, a similar picture search process based on the first picture is triggered.
  • the setting direction may be a downward direction.
  • the setting direction may be a downward direction.
  • Operation 2 The operation of obtaining the first picture by scanning is applicable to the terminal provided with the picture scanning device. As an example, after the terminal scans the first picture by using the scanning device disposed thereon, the similar picture search process using the first picture as a reference may be automatically triggered according to the obtained first picture scan information.
  • Operation 3 The operation of obtaining the first picture by shooting is applied to a terminal provided with an imaging device such as a camera.
  • an imaging device such as a camera.
  • the similar image search process based on the captured first image may be automatically triggered.
  • Operation 4 The operation of pasting the first picture in the search box.
  • the user opens an application for implementing image search, and pastes the selected first image into the application After the search box in the search interface, a similar image search process based on the first image will be triggered.
  • Operation 5 an operation for selecting an option for triggering a picture search in a popup menu of the first picture.
  • a picture operation option menu is popped up, and the menu may include one or more picture operation options, at least including An option for triggering an image search, for example, the menu may include the following options: "search for similar pictures", "copy pictures", "share pictures”; when the option for triggering image search (such as "search for similar pictures") is After selection, a similar image search process based on the first picture will be triggered.
  • the second screen touch operation may be a long press or a click operation in the first picture display area, which is not limited in this embodiment of the present application.
  • Operation 6 The operation of the UI (User Interface) component for triggering the image search is selected in the screen display area of the first picture or in the preview view window.
  • the UI component may be a function button or a text box or other type of UI component, which is not limited in this embodiment of the present application.
  • a UI component can be set in the preview view window of each image, such as a button named "similar image search", when the user triggers a picture in the preview view window by operation " After the similar image search button, a similar image search process based on the image can be triggered. For another example, as shown in FIG.
  • a UI component is generated (eg, The button named "Find Similar Image” in the figure is displayed in the interface, and if the UI component is triggered (such as being clicked), a similar image search process based on the first image is triggered.
  • Operation 7 Set the function key operation when the first picture is displayed on the screen.
  • the first picture is displayed (or highlighted) in a normal size in the picture browsing window, instead of only displaying its preview view, if it is detected that the user has pressed a particular button of the terminal, A similar picture search process based on the first picture is triggered.
  • Operation 8 A set gesture operation performed when the first picture is displayed on the screen.
  • the first picture is displayed in a normal size in the picture browsing window, instead of only displaying its preview view, if the user is detected to perform a specific gesture operation, for example, The action of the moving arm triggers a similar picture search process based on the first picture.
  • Step 202 Determine a search dimension corresponding to the first picture.
  • the embodiment of the present application can support image search of multiple dimensions to meet different needs of users. In a similar image search process, you can search based on one dimension or multiple dimensions.
  • the image search dimension provided by the embodiment of the present application may include one or more combinations of the following dimensions:
  • the search dimensions of the objects in the image For example, for a person or building or other object in the first picture, search for other pictures that contain the object. If the image is searched by using the dimension, the feature information of the first image and the feature information of other images in the image library may be extracted; then the feature information of the first image is compared with the feature information of other images, and the similarity measure function is used. Calculating the similarity between the pictures, wherein the similarity can be generally characterized by an Euclidean distance, a Cosine distance, or a Mahalanobis distance; if the similarity between the second picture and the first picture is higher than a set threshold, the second picture is As a searched image similar to the first picture.
  • feature extraction is a process of converting an image into a vector.
  • the vector is called an image feature.
  • Feature extraction can be done by a feature extraction model.
  • the input of the model is a picture (the value of each pixel in the picture), and the output is an image. feature.
  • feature extraction methods such as color histograms, LBP, Gabor, deep convolutional networks, etc., and embodiments of the present application can use these methods for feature extraction.
  • the hue of the picture can be calculated by using an image analysis algorithm.
  • the shooting time of the first picture can usually be saved in the picture library as metadata or attribute information of the picture.
  • Shooting of two pictures The similar shooting time means that the difference between the shooting times of the two pictures is within the set duration.
  • the location information of the image can be saved in the image library as metadata or attribute information of the image.
  • the location information of the image can be saved in the image library as metadata or attribute information of the image.
  • the current location of the mobile phone can be obtained, and related information (such as latitude and longitude) of the current location is saved as the metadata or attribute information of the image in the image library.
  • the similarity between the two pictures is that the distance between the two pictures is within the set distance.
  • Information about the shooting device used by the image can be saved in the image library as metadata or attribute information of the image.
  • the phone's related information phone type, etc.
  • the information (such as type, model, etc.) of the camera that took the photo may be saved as a metadata or attribute information of the image to the photo library; if the image is from WeChat (a social application), etc.
  • the application can save the related information of the application as the metadata or attribute information of the image to the image library when saving the image to the image library.
  • the above is only exemplarily shown in the image search dimension provided by the embodiment of the present application.
  • the embodiment of the present application is not limited to the above search dimension.
  • the search of the same or similar size may be performed based on the size of the image. List them one by one.
  • one or more search dimensions can be used when performing an image search.
  • the embodiment of the present application preferably provides the following search modes (the one of the method 1 to the mode 3) to determine the search dimension to be used in the image search, and specifically includes:
  • Method 1 Obtain a default search dimension, and determine a default search dimension as a search dimension corresponding to the first picture, and the default search dimension may include one or more search dimensions.
  • Manner 2 The operation for selecting a search dimension in the pop-up menu of the first picture is selected, and the selected search dimension is determined as the search dimension corresponding to the first picture.
  • the pop-up menu pops up after the third screen touch operation performed in the screen display area of the first picture, and one search dimension option in the pop-up menu corresponds to one or more search dimensions.
  • the third screen touch operation may be a one-finger long touch operation in a screen display area of the first picture.
  • a menu pops up, which includes "search for the same person", “search for the same color”, “search for the same source” "Option; if the user selects the "Search for the same person” option in the menu, the trigger uses a similar image search process based on feature extraction; if the user selects the "Search for the same color” option in the menu, the trigger based on the first image is triggered. Tone finds the search process for pictures with the same hue.
  • Manner 3 determining a search dimension corresponding to the detected first operation according to the detected type of the first operation, and the corresponding relationship between the type of the first operation and the search dimension, where a first operation corresponds to one Or multiple search dimensions.
  • the correspondence between the type of the touch operation of the screen and the search dimension is set in advance.
  • the one-point swipe operation corresponds to the “search dimension based on the object in the image”
  • the single-point swipe operation corresponds to the “image-based hue search”.
  • Step 203 Search for a second picture that matches the first picture on the search dimension according to the search dimension corresponding to the first picture.
  • the second picture refers to a picture that matches or is similar to the first picture in one or some search dimensions, and the second picture may be one or more.
  • the second picture that matches the first picture in the corresponding search dimension may be searched from the picture library stored locally by the terminal and/or the picture library stored on the network side.
  • the embodiment of the present application allows the user to select a local area in the first picture, and extract a feature based on the local area, thereby searching for a second picture similar to the feature of the local area.
  • the action area of the first screen touch operation may be acquired according to the first screen touch operation performed in the screen display area of the first picture; and then the feature information of the first picture in the active area is extracted, and further Other pictures The operation of feature extraction is performed; and the similarity between the images is calculated by the extracted feature information, thereby determining a second picture similar to the first picture.
  • feature information of the same size area in other pictures may be extracted according to the size of the action area, and the area may be in different positions for one picture (one picture in another picture)
  • the size of the feature extracts feature information of multiple regions, and when the feature information or the similarity comparison is performed, the feature information closest to the feature information extracted in the first image in one image may be retained as the feature information of the image, thereby measuring The similarity of the picture to the first picture.
  • the user can select a person's head by a single-finger click operation, thereby triggering feature extraction on the character's head area; for other pictures in the picture library to be compared, for example a second picture, where the different positions in the second picture (preferably including the same position as the selected person's head in the first picture) are feature-extracted by the size of the area, and the feature information of each feature information and the first picture is calculated.
  • the similarity retains the similarity in which the maximum value is the similarity of the second picture, and if the similarity is greater than the threshold, the second picture is output as the found similar picture. In this way, you can find additional images that contain the object for each object.
  • Step 204 Output the search result.
  • the search result can be output to the display device for display.
  • the found picture may be displayed, otherwise the prompt information of the picture that does not find the matching may be given.
  • the found second picture when the found second picture is displayed, the found second picture may be displayed in a picture preview manner according to the order of matching degree from high to low.
  • the matching degree refers to the similarity between the pictures determined based on the feature extraction method; for the aforementioned “search dimension based on the tone of the picture”, the matching degree refers to The closeness of the tone value of the picture; for the aforementioned “search dimension based on the picture-taking time”, the matching degree refers to the proximity of time; for the aforementioned “search dimension of the picture-based shooting location”, the matching degree refers to the location The proximity.
  • the matching degree of multiple dimensions may be combined to determine the total matching degree, and the search result is displayed according to the total matching degree.
  • N sub-windows can be set and used.
  • N sub-windows display the found second picture
  • each sub-window is used to display a preview view of the second picture or the second picture found based on one search dimension
  • each sub-window is allowed to switch display according to the corresponding search dimension according to the sliding touch operation
  • a preview view of the second or second picture found, N being an integer greater than or equal to one.
  • 6 exemplarily shows a search result page by taking three sub-windows as an example. As shown in FIG. 6, the area 601 is used to display the first picture, and the sub-window 602 is used to display the "search dimension based on the object in the picture".
  • the preview view in the child window 602 can be browsed by a one-way right swipe operation 605, and the preview view in the child window 603 can be browsed by a one-point left swipe operation 606.
  • the matching degree of the picture may also be displayed, for example, the matching degree is displayed below the found picture, so that the user can browse and select.
  • the embodiment of the present application after acquiring the image search instruction generated according to the detected first operation for the first picture, determining a search dimension corresponding to the first picture, and And searching, according to the search dimension corresponding to the first picture, a second picture that matches the first picture in the search dimension, thereby implementing an automatic search process of a similar picture triggered by the first operation, and adopting a manual manner
  • the user operation is low in complexity and time-consuming, and accordingly, the power consumption is also small.
  • the embodiment of the present application further provides a picture search device, which can implement the foregoing picture search process.
  • the device can be a terminal or a component integrated inside the terminal.
  • the device can be implemented by software or by a combination of software and hardware.
  • FIG. 7 is a schematic structural diagram of a picture search apparatus according to an embodiment of the present disclosure.
  • the picture search apparatus may include: an obtaining module 701, a determining module 702, a searching module 703, and an output module 704, where:
  • the obtaining module 701 is configured to acquire a picture search instruction, where the picture search instruction is generated according to the detected first operation for the first picture;
  • a determining module 702 configured to determine a search dimension corresponding to the first picture
  • the searching module 703 is configured to search according to the search dimension corresponding to the first picture. Searching for a second picture on the dimension that matches the first picture;
  • the output module 704 is configured to output a search result.
  • the first operation for the first picture comprises:
  • the operation of the user interface UI component for triggering the image search is selected in the screen display area of the first picture or in the preview view window.
  • the first screen touch operation performed in the screen display area of the first picture includes: a multi-finger zoom sliding operation performed in a screen display area of the first picture; or, in the A sliding operation of a single finger in a set direction in a screen display area of a picture.
  • the determining module 702 is specifically configured to:
  • a third screen touch operation performed in a screen display area of a picture is detected and popped up, and one search dimension option in the popup menu corresponds to one or more search dimensions; or
  • the search dimension comprises one or more of the following dimensions:
  • the search dimension of a photo-based device or source is a photo-based device or source.
  • the searching module 703 may be specifically configured to: when the search dimension includes the search dimension of the object in the image, extract feature information of the first image, and search for the second image according to the extracted feature information, where the second The feature information of the picture matches the feature information of the first picture.
  • the searching module 703 may be specifically configured to: when the first operation for the first picture is a first screen touch operation performed in a screen display area of the first picture, according to a screen in the first picture And performing a first screen touch operation performed in the display area, acquiring an action area of the first screen touch operation, and extracting feature information of the first picture in the active area.
  • the searching module 703 is specifically configured to: search for a second picture that matches the first picture in the search dimension from a locally stored picture library and/or a picture library stored in the network side.
  • the output module 704 is specifically configured to: display the second picture that is found in a picture preview manner according to the order of matching degree from high to low, the number of the second pictures being one or more.
  • the output module 704 is specifically configured to: display the searched second image by using N sub-windows, each sub-window is configured to display a preview view of the second image or the second image that is found based on one search dimension, each sub-window It is allowed to switch to display a preview view of the second picture or the second picture found based on the corresponding search dimension according to the sliding touch operation, where N is an integer greater than or equal to 1.
  • the embodiment of the present application further provides a terminal, where the terminal can implement the foregoing image search process.
  • FIG. 8 is a schematic structural diagram of a terminal according to an embodiment of the present application.
  • the terminal may generally include a processor 801, a memory 802, and a display 803.
  • the processor 801 can be a general purpose processor (such as a microprocessor or any conventional processor, etc.), a digital signal processor, an application specific integrated circuit, a field programmable gate array, or He has programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.
  • Memory 802 may specifically include internal memory and/or external memory, such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like, which are well established in the art.
  • Display 803 can include touch screen control circuitry.
  • the bus architecture may include any number of interconnected buses and bridges, specifically linked by one or more processors represented by processor 801 and various circuits of memory represented by memory 802.
  • the bus architecture can also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and, therefore, will not be further described herein.
  • the bus interface provides an interface.
  • the processor 801 is responsible for managing the bus architecture and general processing, and the memory 802 can store data used by the processor 801 in performing operations.
  • the picture search process disclosed in the embodiment of the present application may be applied to the processor 801 or implemented by the processor 801.
  • each step of the picture search process may be completed by an integrated logic circuit of hardware in the processor 801 or an instruction in the form of software.
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed.
  • the steps of the method disclosed in the embodiments of the present application may be directly implemented as a hardware processor, or may be performed by a combination of hardware and software modules in the processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the processor 801 is coupled to the memory 802 for reading computer program instructions stored by the memory 802 and, in response, performing the following operations:
  • the picture search instruction being generated according to the detected first operation for the first picture
  • Searching according to the search dimension corresponding to the first picture, a second picture that matches the first picture in the search dimension;
  • the first operation for the first picture comprises:
  • the UI component for triggering the picture search is selected.
  • the first screen touch operation performed in the screen display area of the first picture includes:
  • the processor 801 is specifically configured to:
  • a third screen touch operation performed in a screen display area of a picture is detected and popped up, and one search dimension option in the popup menu corresponds to one or more search dimensions; or
  • the search dimension comprises one or more of the following dimensions:
  • the search dimension of a photo-based device or source is a photo-based device or source.
  • the processor 801 may be specifically configured to: when the search dimension includes, based on a search dimension of an object in the image, extract feature information of the first image, and search for a second image according to the extracted feature information, where the second The feature information of the picture matches the feature information of the first picture.
  • the processor 801 is specifically configured to: when the first operation for the first picture is a first screen touch operation performed in a screen display area of the first picture, according to a screen in the first picture And performing a first screen touch operation performed in the display area, acquiring an action area of the first screen touch operation, and extracting feature information of the first picture in the active area.
  • the processor 801 is specifically configured to: search for a second picture that matches the first picture in the search dimension from a locally stored picture library and/or a picture library stored in the network side.
  • the processor 801 is specifically configured to: in the order of the matching degree from high to low, instruct the display to display the second picture that is found in a picture preview manner, the number of the second pictures being one or more.
  • the processor 801 is specifically configured to: instruct the display to display the searched second image by using the N sub-windows, each sub-window is configured to display a preview view of the second image or the second image that is found based on one search dimension, each The sub-window is allowed to switch to display a preview view of the second picture or the second picture found based on the corresponding search dimension according to the sliding touch operation, where N is an integer greater than or equal to 1.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Abstract

L'invention concerne un procédé et un dispositif de recherche d'images. Le procédé comprend : lors de la détection d'une première opération pour une première image, la détermination d'une dimension de recherche correspondant à la première image (202) ; et la recherche, en fonction de la dimension de recherche correspondant à la première image, d'une seconde image coïncidant avec la première image dans la dimension de recherche (203). Ainsi, un processus de recherche automatique d'images similaires déclenché par la première opération est accompli. Par rapport à un procédé de recherche d'images manuel, la présente invention aboutit à une opération utilisateur moins complexe, elle prend moins de temps, et elle consomme moins d'énergie.
PCT/CN2016/110193 2015-12-25 2016-12-15 Procédé et dispositif de recherche d'images WO2017107855A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510997392.8A CN106919326A (zh) 2015-12-25 2015-12-25 一种图片搜索方法及装置
CN201510997392.8 2015-12-25

Publications (1)

Publication Number Publication Date
WO2017107855A1 true WO2017107855A1 (fr) 2017-06-29

Family

ID=59089154

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/110193 WO2017107855A1 (fr) 2015-12-25 2016-12-15 Procédé et dispositif de recherche d'images

Country Status (2)

Country Link
CN (1) CN106919326A (fr)
WO (1) WO2017107855A1 (fr)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107632759A (zh) * 2017-08-21 2018-01-26 珠海市魅族科技有限公司 图片展示方法、装置、计算机装置及计算机可读存储介质
CN108874262A (zh) * 2018-06-07 2018-11-23 北京小度信息科技有限公司 信息交互方法、装置、电子设备及计算机可读存储介质
CN109840128A (zh) * 2019-01-23 2019-06-04 努比亚技术有限公司 一种双屏壁纸处理方法、服务器及移动终端
CN110245247A (zh) * 2019-05-24 2019-09-17 浙江大华技术股份有限公司 图片搜索的方法、电子设备和计算机存储介质
CN110598037B (zh) * 2019-09-23 2022-01-04 腾讯科技（深圳）有限公司 一种图像搜索方法、装置和存储介质
CN114422636B (zh) * 2021-12-16 2023-03-07 巴可(苏州)医疗科技有限公司 一种基于Android的生成测试图像检测显示器的方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103020184A (zh) * 2012-11-29 2013-04-03 北京百度网讯科技有限公司 使用拍摄图像获取搜索结果的方法和系统
CN103559248A (zh) * 2013-10-30 2014-02-05 广东明创软件科技有限公司 基于移动终端相册图片的搜索方法及其移动终端
CN104881457A (zh) * 2015-05-21 2015-09-02 百度在线网络技术（北京）有限公司 图片搜索方法及装置
US20150253962A1 (en) * 2014-03-10 2015-09-10 Samsung Electronics Co., Ltd. Apparatus and method for matching images
CN105138681A (zh) * 2015-09-15 2015-12-09 成都品果科技有限公司 基于空间坐标定位的图片搜索方法及系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101216830B (zh) * 2007-12-28 2011-09-21 腾讯科技（深圳）有限公司 根据颜色搜索商品的方法和系统
CN101825989A (zh) * 2010-04-23 2010-09-08 杭州图酷科技有限公司 拖拽式图像搜索输入方法
CN104111989B (zh) * 2014-07-02 2017-12-22 百度在线网络技术（北京）有限公司 搜索结果的提供方法和装置
CN104462325B (zh) * 2014-12-02 2019-05-03 百度在线网络技术（北京）有限公司 搜索推荐方法及装置
CN104951537A (zh) * 2015-06-18 2015-09-30 百度在线网络技术（北京）有限公司 一种图像搜索的方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103020184A (zh) * 2012-11-29 2013-04-03 北京百度网讯科技有限公司 使用拍摄图像获取搜索结果的方法和系统
CN103559248A (zh) * 2013-10-30 2014-02-05 广东明创软件科技有限公司 基于移动终端相册图片的搜索方法及其移动终端
US20150253962A1 (en) * 2014-03-10 2015-09-10 Samsung Electronics Co., Ltd. Apparatus and method for matching images
CN104881457A (zh) * 2015-05-21 2015-09-02 百度在线网络技术（北京）有限公司 图片搜索方法及装置
CN105138681A (zh) * 2015-09-15 2015-12-09 成都品果科技有限公司 基于空间坐标定位的图片搜索方法及系统

Also Published As

Publication number Publication date
CN106919326A (zh) 2017-07-04

Similar Documents

Publication Publication Date Title
WO2017107855A1 (fr) Procédé et dispositif de recherche d'images
EP3661187B1 (fr) Procédé de photographie et terminal mobile
JP5947131B2 (ja) 領域選択方式による検索の入力方法及びそのシステム
US9479693B2 (en) Method and mobile terminal apparatus for displaying specialized visual guides for photography
EP3547218B1 (fr) Dispositif et procédé de traitement de fichiers, et interface utilisateur graphique
US20170032219A1 (en) Methods and devices for picture processing
WO2016101757A1 (fr) Procédé et dispositif de traitement d'image basés sur un dispositif mobile
US20140211065A1 (en) Method and system for creating a context based camera collage
CN112954210B (zh) 拍照方法、装置、电子设备及介质
US20220417417A1 (en) Content Operation Method and Device, Terminal, and Storage Medium
US11190653B2 (en) Techniques for capturing an image within the context of a document
CN112269522A (zh) 图像处理方法、装置、电子设备和可读存储介质
US11232616B2 (en) Methods and systems for performing editing operations on media
EP3186953B1 (fr) Procédé et appareil de détermination de mode de capture après une capture du contenu
WO2017210908A1 (fr) Procédé et terminal de traitement
TW201828118A (zh) 圖片搜索方法及裝置
CN113271378B (zh) 图像处理方法、装置及电子设备
CN112383708B (zh) 拍摄方法、装置、电子设备及可读存储介质
WO2019075644A1 (fr) Procédé de recherche de photographie de portrait et terminal
WO2016101768A1 (fr) Terminal et procédé de recherche à base d'opération tactile et dispositif
CN108647097B (zh) 文本图像处理方法、装置、存储介质及终端
KR102662873B1 (ko) 픽처 처리 방법 및 장치, 디바이스 및 저장 매체
Patankar et al. A method for resizing images by content perception
WO2022057419A1 (fr) Procédé et appareil d'acquisition d'informations relatives à un sujet, ainsi que support de stockage et dispositif électronique
CN115048342A (zh) 文件分类方法及装置

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: 16877666

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: 16877666

Country of ref document: EP

Kind code of ref document: A1