WO2019100766A1 - 一种图像处理方法、装置、电子设备及存储介质 - Google Patents

一种图像处理方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2019100766A1
WO2019100766A1 PCT/CN2018/100213 CN2018100213W WO2019100766A1 WO 2019100766 A1 WO2019100766 A1 WO 2019100766A1 CN 2018100213 W CN2018100213 W CN 2018100213W WO 2019100766 A1 WO2019100766 A1 WO 2019100766A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
preview image
processed
image
determining
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2018/100213
Other languages
English (en)
French (fr)
Inventor
吴威操
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Gree Electric Appliances Inc of Zhuhai
Gree Wuhan Electric Appliances Co Ltd
Original Assignee
Gree Electric Appliances Inc of Zhuhai
Gree Wuhan Electric Appliances Co Ltd
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 Gree Electric Appliances Inc of Zhuhai, Gree Wuhan Electric Appliances Co Ltd filed Critical Gree Electric Appliances Inc of Zhuhai
Publication of WO2019100766A1 publication Critical patent/WO2019100766A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80—Camera processing pipelines; Components thereof
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • 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
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • 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
    • H04N23/62—Control of parameters via user interfaces
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/2621—Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability

Definitions

  • the solution in the embodiment of the present application relates to the field of computer technologies, and in particular, to an image processing method, device, electronic device, and storage medium.
  • APP Application, APP
  • various applications having beauty or other special effects functions can be used in a smart terminal (for example, a mobile terminal) device, and people are increasingly accustomed to taking pictures with such an APP.
  • An image processing method, device, electronic device and storage medium are provided in the embodiment of the present application to solve the problem that the existing image processing functionality is single.
  • An aspect of the present application provides an image processing method, including: determining whether a human face is included in a captured preview image of the camera when detecting that the camera of the terminal is turned on; if the image includes a human face, determining a face to be processed in the preview image; performing a preset operation on the determined face to be processed in the preview image.
  • the determining the face to be processed in the preview image includes: determining whether a face selection instruction is received within a preset time; if the face selection instruction is received within the preset time, acquiring The feature information carried by the face selection instruction, the feature information includes at least one of a location feature, a dressing feature, and a feature; and the face matching the feature information is determined to be processed in the preview image Face.
  • the method further includes: if the face selection instruction is not received within the preset time, determining whether at least two faces are included in the preview image; if yes, acquiring the person in the preview image The face ratio of the face, the skin delicateness, and the skin color gloss; the at least two faces in the preview image are scored according to the face proportion of the face, the skin delicateness, and the skin tone gloss; As a result of the scoring, the face with the highest score in the preview image is obtained; and the face with the highest score is determined to be the face to be processed in the preview image.
  • performing the preset operation on the determined human face in the preview image including: performing a beauty treatment on the determined face in the preview image; and/or determining The face to be processed in the preview image is given a preset label.
  • the method further includes: after the camera captures the preview image after performing the preset operation, receiving a save instruction; and executing the preview image after performing the preset operation according to the save instruction Save it.
  • Another aspect of the present application provides an image processing apparatus, including: a first determining module, configured to determine whether a human face is included in a captured preview image of the camera when detecting that the camera of the terminal is turned on; a determining module, configured to determine a face to be processed in the preview image if a face is included in the preview image; and the first processing module is configured to perform a preset on the determined face to be processed in the preview image Operation.
  • the first determining module includes: a first determining unit, configured to determine whether a face selection instruction is received within a preset time; the first obtaining unit is configured to receive the The face selection instruction acquires feature information carried by the face selection instruction, the feature information includes at least one of a location feature, a dressing feature, and a appearance feature; and the first determining unit is configured to be associated with the feature information
  • the matching face is determined as the face to be processed in the preview image.
  • the first determining module further includes: a second determining unit, configured to determine whether the preview image includes at least two faces if the face selection instruction is not received within the preset time; a second obtaining unit, configured to: if yes, obtain a face proportion, a skin delicateness, and a skin color glossiness of the face in the preview image; the scoring unit is set to be based on the face proportion of the face, the skin delicateness, and The skin color gloss, the at least two faces in the preview image are scored; the third obtaining unit is configured to acquire a face with the highest score in the preview image according to the result of the scoring; the second determining unit And determining to determine that the face with the highest score is the face to be processed in the preview image.
  • a second determining unit configured to determine whether the preview image includes at least two faces if the face selection instruction is not received within the preset time
  • a second obtaining unit configured to: if yes, obtain a face proportion, a skin delicateness, and a skin color glossiness of the face in the preview image
  • the first processing module is specifically configured to: perform beauty processing on the determined face in the preview image; and/or assign a pre-processed face to the determined preview image. Set the label.
  • the device further includes: a receiving module, configured to receive a save instruction after the camera captures the preview image after performing the preset operation; and the saving module is configured to set according to the save instruction The preview image after the preset operation is performed is saved.
  • a receiving module configured to receive a save instruction after the camera captures the preview image after performing the preset operation
  • the saving module is configured to set according to the save instruction The preview image after the preset operation is performed is saved.
  • a still further aspect of the embodiments of the present application provides an electronic device, including: at least one processor; and a memory communicably coupled to the at least one processor; wherein the memory is stored for processing by the at least one An instruction executed by the at least one processor to enable the at least one processor to perform the method as described above.
  • a storage medium in which a computer program is stored, the computer program being configured to execute the method as described above at runtime.
  • the terminal camera after the terminal camera is turned on, it is first determined whether a face is included in the preview image captured by the terminal, and if a face is in the image, the face to be processed is determined according to a preset condition, thereby determining the waiting
  • the processed face performs a preset operation.
  • This embodiment can subjectively select a face in an image for special processing, enriches the function of image processing, and improves user autonomy.
  • FIG. 1 is a schematic flowchart diagram of an image processing method according to an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a method for determining a face to be processed in the image according to a preset condition in an image processing method according to an embodiment of the present disclosure
  • FIG. 3 is a schematic flowchart of an image processing method according to another embodiment of the present application.
  • FIG. 4 is a schematic flowchart of an image processing method according to another embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • the embodiment of the present application provides an image processing method, which can be applied to a terminal device including a camera, and the terminal device includes a smart phone, a tablet computer, a portable computer, a smart camera, and the like.
  • the method may be implemented by an APP running on a smart phone or a tablet, or may be implemented by a software installed in a portable computer, or may be implemented by a system software function in the mobile terminal device.
  • the image processing method includes:
  • S101 Determine, when the camera of the terminal is turned on, whether a human face is included in the captured preview image of the camera.
  • the camera preview image of the camera is a preview image corresponding to the preview mode, and determines whether the preview image includes a human face.
  • the preview image is preprocessed and feature extracted, so that the extracted image is extracted.
  • the feature is matched with the preset facial feature. If the feature matching is the same, it indicates that the image to be captured corresponding to the camera includes a human face.
  • determining a face to be processed in the preview image includes:
  • S1021 Determine whether a face selection instruction is received within a preset time
  • S1022 If the face selection instruction is received in the preset time, acquiring feature information carried by the face selection instruction, where the feature information includes at least one of a location feature, a dressing feature, and a appearance feature. ;
  • the face selection instruction is used to select a face in the image, and the face selection instruction is issued by the user, and the user can issue the face selection instruction by touching the display screen or voice input.
  • the preset time can be set manually or set by the system, for example, set to 10 seconds or 30 seconds.
  • the face selection command may select one face in the image, or may select multiple faces in the image.
  • the mobile terminal device performing the method can acquire the user touch on the display screen.
  • the specific location is the location feature; optionally, the facial feature of the image corresponding to the specific location is obtained, for example, the specific location is a nose, and the facial feature of the image corresponding to the specific location is a nose;
  • the specific location is centered, and other facial features in the preset range are obtained.
  • the entire human face is determined according to the obtained facial features and other facial features, and the determined entire human face is the to-be-processed Face.
  • the user when the user sends the face selection command by voice, if there is only one face in the image, the user can directly output the "face” by voice, that is, the face is selected, and the face is processed later.
  • the face and the background area can be distinguished to deal with the face separately; if the image includes multiple faces, the user can voice output a voice command such as "left face” or "middle face” by using the voice command obtained.
  • Speech recognition and speech processing to determine the face selected by the user; in addition, when the image includes a plurality of faces, the user can also output a voice instruction including a person's dressing feature or appearance feature, such as "yellow hair”, Double eyelids, “red clothes”, etc., so that after the voice command is recognized by the machine, the face to be processed is determined.
  • a voice instruction including a person's dressing feature or appearance feature, such as "yellow hair”, Double eyelids, “red clothes”, etc.
  • the performing the preset operation on the face to be processed includes: performing a beauty process on the determined face in the determined image; and/or, assigning a preset to the determined face to be processed in the image. label.
  • a label that is preset to the face to be processed for example, "cute”, “beautiful” and other text labels.
  • the embodiment of the present application provides an image processing method. After the terminal camera is turned on, it is first determined whether a preview image captured by the terminal includes a human face. If a face is in the image, it is determined whether a person is received within a preset time. The face selection instruction, if a face selection instruction is received, determines a face to be processed according to the face selection instruction, thereby performing a preset operation on the determined face to be processed.
  • This embodiment can subjectively select a face in an image for special processing, enriches the function of image processing, and improves user autonomy.
  • the face of the image can be selected by the user autonomously, so that the face selected by the user is specially processed.
  • the system can determine the face to be processed.
  • another embodiment of the present application provides an image processing method, where the method further includes:
  • S201 When detecting that the camera of the terminal is turned on, determining whether a preview image captured by the terminal includes a human face;
  • S203 If the face selection instruction is not received in the preset time, determine whether at least two faces are included in the preview image; the process is a face recognition process, and may refer to determining the preview image in the foregoing embodiment. Whether there is a step in the face.
  • the face proportion of the face can be calculated based on the existing related algorithm of face recognition, the proportion of the face including the proportion of the length and the width of the entire face, and the proportion between some facial features in a face.
  • obtaining the skin delicateness and skin gloss of the face in the preview image relates to an image-based skin detection technology, and in this embodiment, a skin detection method based on the HSV color space, a content-based image skin detection method, and Image skin detection is performed by other methods such as multi-spectral imaging skin detection methods, and skin delicateness and skin gloss are obtained during the detection process.
  • a skin detection method based on the HSV color space, a content-based image skin detection method, and Image skin detection is performed by other methods such as multi-spectral imaging skin detection methods, and skin delicateness and skin gloss are obtained during the detection process.
  • a face database is pre-established, and data of a face in real life is collected, thereby storing a large amount of data of different face proportions in the preset face database, and data of different skin details. And the data of different skin glosses, and determining the weight of each data in the preset face database based on the existing public aesthetic standards, for example, the closer the face ratio is to the "three courts and five eyes" standard, then the person The weight of the face proportion is higher.
  • the preset person Searching in the face database to find the same data as the data, so as to determine the face proportion, skin fineness and skin color gloss of the face in the image according to the weight corresponding to the same data.
  • the weights of the three parameters are summed and the sum obtained is the score of the face.
  • the score value of each face in the image is calculated according to the above embodiment, thereby completing the process of scoring the face in the image.
  • the face in the image may be scored by other methods, without being bound to the method provided in this embodiment.
  • the face with the highest score is obtained, and the face can be regarded as the most beautiful face in the image.
  • the most beautiful face is Make a beauty treatment and add a preset label to the highest scored face, which can be "most beautiful”.
  • the image after the preset operation is performed is displayed on the screen of the terminal, and in addition, the scoring result of the face in the image may be simultaneously displayed.
  • the label or the score corresponding to the face moves along with the movement of the face, and the special treatment effect on the face also follows the face.
  • the movement moves, so that the label, the scoring result, and the special processing effect are not separated from the face, and the processed image can be made more natural.
  • this embodiment the face image after the beauty treatment, and/or the labeled face image, and/or the score corresponding to the face image are displayed, so that the user can see the final processing result. .
  • this embodiment also enhances the interactivity between users during self-photographing because the results corresponding to each face are displayed on the image.
  • the above method may be used to score the only one face in the image, and finally, the user may display The score of the face is scored, thereby increasing the entertainment of the user when taking a selfie.
  • the method may further include: acquiring, according to the result of the scoring, a face with the lowest score in the image; according to the proportion of the face corresponding to the face with the lowest score, the skin delicateness, and Skin color glossiness, obtaining evaluation information of the face with the lowest score; displaying the evaluation information in a preset area of the face with the lowest score in the image, such as serious dark circles, darker skin, a small amount of color Spot and so on. Therefore, it is possible to provide reference suggestions for people who are not beautiful in the image, to help the unbeautiful person to become beautiful, to make the self-timer scientifically meaningful, and to enhance the user experience.
  • the method further includes: performing beauty treatment on the other faces of the at least two faces according to the obtained skin delicateness and skin color gloss corresponding to the highest scored face .
  • the person with the highest score is the "most beautiful” person according to the aesthetics of the public.
  • the other people's skin parameters are used to beautify other people, so that other faces in the image can be close to the most beautiful user.
  • the human face enriches the image beauty method and enhances the user's entertainment.
  • An embodiment of the present application provides an image processing method.
  • the method When detecting a plurality of human faces in a preview image, the method performs scoring of multiple faces in the preview image by using related technologies such as face recognition and face skin detection.
  • This embodiment can separately process one or a few faces in the preview image, which not only enriches the function of image processing, but also enhances the entertainment of the user during self-timer.
  • FIG. 4 is a schematic flowchart diagram of an image processing method according to another embodiment of the present application. The main difference between FIG. 4 and FIG. 3 above is that the method further includes:
  • the save instruction may be triggered by the user actively, for example, the user triggers the save instruction by performing a preset operation, the pre- The operation may be that the finger draws a preset gesture on the screen, or may press a save button on the mobile terminal device, or may be a voice output save command, and the like.
  • the save command can also be triggered automatically by the system, for example, when the system captures a smile on the face of the image, that is, an automatic screenshot, and the like.
  • the user can share the saved image to a preset third-party application according to his or her own desire, and the third-party application includes WeChat, QQ, Weibo, and the like.
  • the embodiment of the present application provides an image processing method. After the camera is turned on, the method first determines whether a face is included in the captured preview image of the camera. If a face is in the image, it is determined whether the person is received within the preset time. a face selection instruction, if a face selection instruction is received, determining a face to be processed according to the face selection instruction, thereby performing a preset operation on the determined face to be processed; if the face selection instruction is not received, and determining When at least two faces are included in the image, the "most beautiful" face in the image is determined by the face recognition technology and the face skin detection technology, and the "most beautiful" face is processed correspondingly, optionally, in the After the camera has finished processing the processed image, the captured image is saved.
  • the face in the image can be subjectively selected for special processing, the function of the image processing is enriched, the user's autonomy is enhanced, and on the other hand, the user's self-photographing is enhanced and the user experience is improved.
  • FIG. 5 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application.
  • the device 30 includes: a first determining module 301, a first determining module 302, and a first processing module 303.
  • the first determining module 301 is configured to determine whether a human face is included in the captured preview image of the camera when the camera of the terminal is detected to be turned on.
  • the first determining module 302 is configured to: if the image includes a human face, Determining a face to be processed in the preview image; the first processing module 303 is configured to perform a preset operation on the determined face to be processed in the preview image.
  • the first processing module 303 is specifically configured to: perform beauty processing on the determined face in the preview image; and/or, give a pre-determined face to be processed in the determined preview image. Set the label.
  • the first determining module 302 includes: a first determining unit 3021, a first obtaining unit 3022, and a first determining unit 3023.
  • the first determining unit 3021 is configured to determine whether a face selection instruction is received within a preset time; the first obtaining unit 3022 is configured to acquire the face if the face selection instruction is received within the preset time Selecting feature information carried by the instruction, the feature information including at least one of a location feature, a dressing feature, and a appearance feature; the first determining unit 3023 is configured to determine a face that matches the feature information as the preview The face to be processed in the image.
  • the first determining module 302 further includes: a second determining unit 3024, a second obtaining unit 3025, The scoring unit 3026, the third obtaining unit 3027, and the second determining unit 3028.
  • the second determining unit 3024 is configured to determine whether the preview image includes at least two faces if the face selection instruction is not received within the preset time; and the second obtaining unit 3025 is configured to acquire if yes a face ratio, a skin delicateness, and a skin color gloss of the face in the preview image; the scoring unit 3026 is configured to be in the preview image according to the face proportion, the skin delicateness, and the skin color gloss of the face The at least two faces are scored; the third obtaining unit 3027 is configured to acquire a face with the highest score in the preview image according to the result of the scoring; and the second determining unit 3028 is configured to determine that the score is the highest The face is the face to be processed in the preview image.
  • the apparatus 30 further includes a receiving module 304, a saving module 305, and a sharing module 306.
  • the receiving module 304 is configured to receive a save instruction after the camera captures the preview image after performing the preset operation
  • the saving module 305 is configured to perform the preset operation according to the save instruction.
  • the preview image is saved;
  • the sharing module 306 is configured to share the saved preview image.
  • the various modules in the embodiments of the present application can be implemented as separate hardware or software, and a combination of functions of the respective units can be implemented using separate hardware or software as needed.
  • An embodiment of the present application provides an image processing apparatus. After the terminal camera is turned on, it is determined whether a preview image captured by the terminal includes a human face. If a face is in the image, it is determined whether a person is received within a preset time. a face selection instruction, if a face selection instruction is received, determining a face to be processed according to the face selection instruction, thereby performing a preset operation on the determined face to be processed; if the face selection instruction is not received, and determining When at least two faces are included in the image, the "most beautiful" face in the image is determined by the face recognition technology and the face skin detection technology, and the "most beautiful" face is processed correspondingly, optionally, in the After the camera has finished processing the processed image, the captured image is saved.
  • the face in the image can be subjectively selected for special processing, the function of the image processing is enriched, the user's autonomy is enhanced, and on the other hand, the user's self-photographing is enhanced and the user experience is improved.
  • FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 6, the electronic device 40 includes:
  • One or more processors 41 and a memory 42 are exemplified by a processor 41 in FIG.
  • the processor 41 and the memory 42 may be connected by a bus or other means, as exemplified by a bus connection in FIG.
  • the memory 42 is a non-volatile computer readable storage medium, and can be used for storing non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions corresponding to the image processing methods in the embodiments of the present application. / Module (for example, the modules and units shown in Figure 5).
  • the processor 41 executes various functional applications and data processing of the server by executing nonvolatile software programs, instructions, and modules stored in the memory 42, that is, the image processing method of the above method embodiment is implemented.
  • the memory 42 may include a storage program area in which an operating system, an application required for at least one function, and a storage data area may be stored, wherein the storage data area may store data created according to use of the image processing apparatus, and the like.
  • memory 42 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.
  • memory 42 may optionally include memory remotely located relative to processor 41, which may be coupled to the image processing device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the one or more modules are stored in the memory 42 and, when executed by the one or more processors 41, perform an image processing method in any of the above method embodiments, for example, performing the above described FIG. Method steps S101 to S103, method steps S1021 to S1023 in FIG. 2, method steps S201 to S208 in FIG. 3, and method steps S201 to S210 in FIG. 4, implementing modules 301-306 in FIG. , the function of the unit 3021-3028.
  • the electronic device of the embodiment of the present application exists in various forms, including but not limited to:
  • Mobile communication devices These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication.
  • Such terminals include: smart phones, multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access.
  • Such terminals include: PDAs, MIDs, and UMPC devices.
  • the embodiment of the present application provides a non-transitory computer readable storage medium storing computer-executable instructions that are executed by an electronic device to perform any of the above method embodiments.
  • the image processing method in the method for example, performs the method steps S101 to S103 in FIG. 1 described above, the method steps S1021 to S1023 in FIG. 2, the method steps S201 to S208 in FIG. 3, and the method in FIG. Steps S201 to S210 implement the functions of the modules 301-306 and 3021-3028 in FIG.
  • An embodiment of the present application provides a computer program product, including a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer,
  • the computer executes the image processing method in any of the above method embodiments, for example, performs the method steps S101 to S103 in FIG. 1 described above, the method steps S1021 to S1023 in FIG. 2, and the method steps S201 to S in FIG. S208, the method steps S201 to S210 in FIG. 4, the functions of the modules 301-306 and the units 3021-3028 in FIG. 5 are implemented.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
  • an image processing method, apparatus, electronic device, and storage medium provided by the embodiments of the present invention have the following beneficial effects: subjectively selecting a face in an image for special processing, enriching the function of image processing, and improving the user Autonomy.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)

Abstract

本申请实施例中的方案涉及计算机技术领域，尤其涉及一种图像处理方法、装置、电子设备及存储介质。该方法包括：在检测到终端的摄像头开启时，判断所述摄像头的拍摄预览图像中是否包括人脸；如果所述预览图像中包括人脸，确定所述预览图像中待处理的人脸；对确定的所述预览图像中待处理的人脸执行预设的操作。该实施方式能够主观选择图像中的人脸进行特殊处理，丰富了图像处理的功能，提升了用户的自主性。

Description

一种图像处理方法、装置、电子设备及存储介质 技术领域
本申请实施例中的方案涉及计算机技术领域，尤其涉及一种图像处理方法、装置、电子设备及存储介质。
背景技术
目前，智能终端(例如，移动终端)设备中能够使用各种具有美颜或者其他特效功能的应用程序(Application，APP)，人们越来越习惯于用这类APP进行拍照。
然而，通过这类APP进行拍照后所进行的美颜操作或者特效功能操作往往都是对整幅图像进行整体处理，比如，一键美颜等。以至于其功能太笼统，不能单独对图像中某一个或某几个人脸进行特别处理。
发明内容
本申请实施例中提供了一种图像处理方法、装置、电子设备及存储介质，以解决现有的图像处理功能性单一的问题。
本申请实施例的一个方面，提供一种图像处理方法，包括：在检测到终端的摄像头开启时，判断所述摄像头的拍摄预览图像中是否包括人脸；如果所述图像中包括人脸，确定所述预览图像中待处理的人脸；对确定的所述预览图像中待处理的人脸执行预设的操作。
可选地，所述确定所述预览图像中待处理的人脸，包括：判断预设时间内是否接收到人脸选择指令；如果所述预设时间内接收到所述人脸选择指令，获取所述人脸选择指令携带的特征信息，所述特征信息包括位置特征、着装特征、外貌特征中的至少一种；将与所述特征信息相匹配的人脸确定为所述预览图像中待处理的人脸。
可选地，所述方法还包括：如果所述预设时间内未接收到所述人脸选择指令，判断所述预览图像中是否包括至少两个人脸；如果是，获取所述 预览图像中人脸的脸部比例、皮肤细腻度以及肤色光泽度；根据所述人脸的脸部比例、皮肤细腻度以及肤色光泽度，对所述预览图像中的所述至少两个人脸进行打分；根据所述打分的结果，获取所述预览图像中评分最高的人脸；确定所述评分最高的人脸为所述预览图像中待处理的人脸。
可选地，所述对确定的所述预览图像中待处理的人脸执行预设的操作，包括：对确定的所述预览图像中待处理的人脸进行美颜处理；和/或对确定的所述预览图像中待处理的人脸赋予预设的标签。
可选地，所述方法还包括：在所述摄像头拍摄所述执行预设的操作后的预览图像后，接收保存指令；根据所述保存指令，将所述执行预设的操作后的预览图像进行保存。
本申请实施例的另一方面，提供一种图像处理装置，包括：第一判断模块，设置为在检测到终端的摄像头开启时，判断所述摄像头的拍摄预览图像中是否包括人脸；第一确定模块，设置为如果所述预览图像中包括人脸，确定所述预览图像中待处理的人脸；第一处理模块，设置为对确定的所述预览图像中待处理的人脸执行预设的操作。
可选地，所述第一确定模块包括：第一判断单元，设置为判断预设时间内是否接收到人脸选择指令；第一获取单元，设置为如果所述预设时间内接收到所述人脸选择指令，获取所述人脸选择指令携带的特征信息，所述特征信息包括位置特征、着装特征、外貌特征中的至少一种；第一确定单元，设置为将与所述特征信息相匹配的人脸确定为所述预览图像中待处理的人脸。
可选地，所述第一确定模块还包括：第二判断单元，设置为如果所述预设时间内未接收到所述人脸选择指令，判断所述预览图像中是否包括至少两个人脸；第二获取单元，设置为如果是，获取所述预览图像中人脸的脸部比例、皮肤细腻度以及肤色光泽度；打分单元，设置为根据所述人脸的脸部比例、皮肤细腻度以及肤色光泽度，对所述预览图像中的所述至少两个人脸进行打分；第三获取单元，设置为根据所述打分的结果，获取所述预览图像中评分最高的人脸；第二确定单元，设置为确定所述评分最高的人脸为所述预览图像中待处理的人脸。
可选地，所述第一处理模块具体设置为：对确定的所述预览图像中待 处理的人脸进行美颜处理；和/或对确定的所述预览图像中待处理的人脸赋予预设的标签。
可选地，所述装置还包括：接收模块，设置为在所述摄像头拍摄所述执行预设的操作后的预览图像后，接收保存指令；保存模块，设置为根据所述保存指令，将所述执行预设的操作后的预览图像进行保存。
本申请实施例的又一方面，提供一种电子设备，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如上所述的方法。
本申请实施例的再一方面，提供一种存储介质，所述存储介质中存储有计算机程序，所述计算机程序被设置为运行时执行如上所述的方法。
在本申请实施例中，在终端摄像头开启后，先判断终端拍摄的预览图像中是否包括人脸，如果图像中有人脸，则根据预设的条件确定待处理的人脸，从而对确定的待处理的人脸进行预设操作。该实施方式能够主观选择图像中的人脸进行特殊处理，丰富了图像处理的功能，提升了用户的自主性。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是本申请实施例提供的一种图像处理方法的流程示意图；
图2是本申请实施例提供的一种图像处理方法中根据预设的条件确定所述图像中待处理的人脸的方法的流程示意图；
图3是本申请另一实施例提供的一种图像处理方法的流程示意图；
图4是本申请又一实施例提供的一种图像处理方法的流程示意图；
图5是本申请实施例提供的一种图像处理装置的结构示意图；
图6是本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。
需要说明的是，如果不冲突，本申请实施例中的各个特征可以相互组合，均在本申请的保护范围之内。另外，虽然在装置示意图中进行了功能模块的划分，在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于装置示意图中的模块划分，或流程图中的顺序执行所示出或描述的步骤。此外，本文所采用的“第一”“第二”等字样并不对数据和执行次序进行限定，仅是对功能和作用基本相同的相同项或相似项进行区分。
本申请实施例提供了一种图像处理方法，该方法可以适用于包含摄像头的终端设备中，该终端设备包括智能手机、平板电脑、便携式计算机、智能相机等。其中，所述方法可以是以智能手机或者平板电脑上运行的APP方式实现，也可以是便携式计算机中安装的软件实现，还可以是移动终端设备中系统软件功能方式实现。如图1所示，该图像处理方法包括：
S101、在检测到终端的摄像头开启时，判断所述摄像头的拍摄预览图像中是否包括人脸；
其中，所述摄像头的拍摄预览图像即摄像头为预览模式所对应的预览图像，判断该预览图像中是否包括人脸，可选的，对所述预览图像进行预处理和特征提取，从而将提取的特征与预设的人脸特征进行匹配，如果特征匹配相同，则说明所述摄像头对应的待拍摄图像中包括人脸。此外，还可以通过现有技术中对图像中的人脸进行识别的方法，来判断所述摄像头对应的待拍摄的图像中是否包括人脸。
S102、如果所述预览图像中包括人脸，确定所述预览图像中待处理的人脸；
在本实施例中，可选的，如图2所示，确定所述预览图像中待处理的人脸，包括：
S1021、判断预设时间内是否接收到人脸选择指令；
S1022、如果所述预设时间内接收到所述人脸选择指令，获取所述人脸选择指令携带的特征信息，其中，所述特征信息包括位置特征、着装特征、外貌特征中的至少一种；
S1023、将与所述特征信息相匹配的人脸确定为所述预览图像中待处理的人脸。
其中，该人脸选择指令用于选择出图像中的人脸，由用户发出该人脸选择指令，用户可以通过触摸显示屏，或者语音输入等方式发出该人脸选择指令。该预设时间可以人为设置或者系统设置，比如设置为10秒或者30秒等。
在本实施例中，该人脸选择指令可以选择图像中的一个人脸，也可以选择图像中的多个人脸。
例如，当用户通过触摸显示屏的方式发出该人脸选择指令时，在用户触摸显示屏时，即触发人脸选择指令，此时，执行本方法的移动终端设备能够获取显示屏上用户触摸的具体位置，该具体位置即上述位置特征；可选的，获取该具体位置对应的图像的人脸特征，比如该具体位置是鼻子，则该具体位置对应的图像的人脸特征是鼻子；然后以该具体位置为中心，获取预设范围内的其他人脸特征；最后根据获取到的所述人脸特征和其他人脸特征，从而确定整个人脸，该确定的整个人脸即所述待处理的人脸。
例如，当用户通过语音的方式发出该人脸选择指令时，如果图像中只有一个人脸，此时用户可以直接语音输出“人脸”，即人脸被选中，在后续对人脸进行处理时，可以区分人脸和背景区域从而单独处理人脸；如果图像中包括多个人脸，此时用户可以语音输出“左边人脸”或者“中间人脸”等语音指令，通过对获取到的语音指令进行语音识别和语音处理，从而确定用户所选择的人脸；此外，当图像中包括多个人脸时，用户还可以输出包含人的着装特征或者外貌特征的语音指令，比如，“黄头发”、“双眼皮”、“红衣服”等，从而由机器识别出该语音指令后，确定待处理的人脸。
S103、对确定的所述预览图像中待处理的人脸执行预设的操作。
其中，对待处理人脸执行预设的操作包括：对确定的所述图像中待处理的人脸进行美颜处理；和/或，对确定的所述图像中待处理的人脸赋予预设的标签。
其中，添加美颜的效果具体可以参考现有的美颜方式。赋予待处理人脸预设的标签，比如，“可爱”、“美丽”等文字标签。
本申请实施例提供了一种图像处理方法，该方法通过在终端摄像头开 启后，先判断终端拍摄的预览图像中是否包括人脸，如果图像中有人脸，再判断预设时间内是否接收到人脸选择指令，如果接收到人脸选择指令，则根据人脸选择指令确定待处理的人脸，从而对确定的待处理的人脸进行预设操作。该实施方式能够主观选择图像中的人脸进行特殊处理，丰富了图像处理的功能，提升了用户的自主性。
上述实施例可以由用户自主选择图像中人脸，从而对用户选择的人脸进行特殊处理。当用户未在预设时间内发出人脸选择指令时，可以由系统来确定待处理的人脸。可选的，如图3所示，本申请另一实施例提供了一种图像处理方法，所述方法还包括：
S201、在检测到终端的摄像头开启时，判断所述终端拍摄的预览图像中是否包括人脸；
S202、如果所述预览图像中包括人脸，判断预设时间内是否接收到人脸选择指令；
S203、如果所述预设时间内未接收到所述人脸选择指令，判断所述预览图像中是否包括至少两个人脸；该过程即人脸识别过程，可以参考上述实施例中判断预览图像中是否有人脸的步骤。
S204、如果是，获取所述预览图像中人脸的脸部比例、皮肤细腻度以及肤色光泽度；
其中，可以基于现有的人脸识别的相关算法计算人脸的脸部比例，该脸部比例包括整个人脸的长度和宽度的比例，也包括一个人脸中部分五官之间的比例。
其中，获取预览图像中人脸的皮肤细腻度及皮肤光泽度，涉及到基于图像的皮肤检测技术，在本实施例中可以采用基于HSV颜色空间的皮肤检测方法、基于内容的图像皮肤检测方法以及基于多光谱成像的皮肤检测方法等其他方法进行图像皮肤检测，在检测过程中获取皮肤细腻度和皮肤光泽度。需要说明的是，基于HSV颜色空间的皮肤检测方法、基于内容的图像皮肤检测方法以及基于多光谱成像的皮肤检测方法的具体过程，在相关技术中均有详细的记载，在此不再赘述。
S205、根据所述人脸的脸部比例、皮肤细腻度以及肤色光泽度，对所 述预览图像中的所述至少两个人脸进行打分；
在本实施例在，预先建立人脸数据库，通过对实际生活中的人脸进行数据采集，从而在该预设的人脸数据库中存储大量的不同脸部比例的数据，不同皮肤细腻度的数据，以及不同皮肤光泽度的数据，并且，基于现有的大众审美标准分别确定预设人脸数据库中各项数据的权重，比如人脸比例接近越接近“三庭五眼”标准，则该人脸比例的权重越高。
在获取所述图像中的人脸的脸部比例、皮肤细腻度以及肤色光泽度后，根据人脸的脸部比例、皮肤细腻度以及肤色光泽度分别对应的数据，在所述预设的人脸数据库中查找，查找与所述数据相同的数据，从而根据该相同的数据所对应的权重确定所述图像中所述人脸的脸部比例、皮肤细腻度以及肤色光泽度的权重，最后，将获取到这三个参数的权重进行求和计算，所得的和，即所述人脸的分数值。
根据上述实施方式计算所述图像中每个人脸的分数值，从而完成对所述图像中的人脸进行打分的过程。
需要说明的是，还可以通过其他方法对所述图像中的人脸进行打分，不需拘泥于本实施例提供的方法。
S206、根据所述打分的结果，获取所述预览图像中评分最高的人脸；
S207、确定所述评分最高的人脸为所述待处理的人脸；
S208、对确定的所述预览图像中待处理的人脸执行预设的操作。
在对包含多个人脸的图像中的每一人脸进行打分后，获取分数值最高的人脸，该人脸即可以认为是图像中最美的人脸，在本实施例中，对最美的人脸进行美颜处理，并且可以为该评分最高的人脸增加预设的标签，该预设的标签可以是“最美”。最后在所述终端的屏幕上显示执行所述预设操作后的图像，另外，也可以同时显示图像中人脸的打分结果。
需要说明的是，当图像中的人脸在摄像头画面中移动时，该人脸对应的标签或者打分结果随着人脸的移动一起移动，并且对人脸进行的特殊处理效果也会随着人脸的移动而移动，从而使得标签、打分结果以及特殊处理效果不会与人脸脱离，能够让进行处理后的图像看起来更自然。
在本实施例中，对进行美颜处理后的人脸图像，和/或，贴标签的人脸图像，和/或，人脸图像对应的分数进行显示，从而使用户能够看到最终的 处理结果。该实施方式除了具备上述实施例的有益效果之外，还由于在图像上显示了每一人脸对应的结果，从而该实施方式增强了自拍时用户之间的互动性。
需要说明的是，当用户未在预设时间内发出人脸选择指令，并且所述图像中只包含一个人脸时，可以采用上述方法对图像中仅有的一个人脸进行打分，最后可以显示该人脸的打分结果，从而增加用户自拍时的娱乐性。
在其他一些实施例中，上述方法还可以包括：根据所述打分的结果，获取所述图像中评分最低的人脸；根据所述评分最低的人脸所对应的脸部比例、皮肤细腻度以及肤色光泽度，获取所述评分最低的人脸的评估信息；在所述图像中所述评分最低的人脸的预设区域内显示所述评估信息，比如黑眼圈严重、皮肤较黑、少量色斑等等。从而能够为图像中不美的人提供参考建议，以帮助不美的人变美，使自拍具有科学意义，提升了用户体验。
在其他一些实施例中，所述方法还包括：根据获取到的所述评分最高的人脸对应的皮肤细腻度和肤色光泽度，对所述至少两个人脸中的其他人脸进行美颜处理。可以理解的是，评分最高的人脸按照大众审美是“最美”的人，在这里，基于最美的人的皮肤参数来美化其他人，从而能够使图像中其他人脸都接近最美的那个用户的人脸，丰富了图像美颜方法，增强了用户的娱乐性。
本申请实施例提供了一种图像处理方法，该方法在检测到预览图像中包含多个人脸时，通过人脸识别、人脸皮肤检测等相关技术对预览图像中多个人脸进行打分，从而获取“最美”的人脸，并且对“最美”的人脸进行特殊处理。该实施方式能够对预览图像中的某一个或某几个人脸进行单独处理，不仅丰富了图像处理的功能，而且增强了用户自拍时的娱乐性。
请参阅图4，图4是本申请又一实施例提供的一种图像处理方法的流程示意图。图4与上述图3的主要区别在于，所述方法还包括：
S209、在所述摄像头拍摄所述执行预设的操作后的预览图像后，接收保存指令；该保存指令可以由用户主动触发，比如，用户通过执行预设的操作来触发该保存指令，该预设的操作可以是手指在屏幕上划出预设的手势，还可以是按动移动终端设备上的保存按钮，还可以是语音输出保存指 令，等等。该保存指令也可以由系统自动触发，比如，当系统捕捉到图像中的人脸出现微笑的表情时，即自动截图，等。
S210、根据所述保存指令，将所述执行预设的操作后的预览图像进行保存。
其中，用户可以根据自己的意愿将保存的图像分享至预设的第三方应用程序中，该第三方应用程序包括微信、QQ、微博等等。
本申请实施例提供了一种图像处理方法，该方法通过在终端摄像头开启后，先判断摄像头的拍摄预览图像中是否包括人脸，如果图像中有人脸，再判断预设时间内是否接收到人脸选择指令，如果接收到人脸选择指令，则根据人脸选择指令确定待处理的人脸，从而对确定的待处理的人脸进行预设操作；如果未接收到人脸选择指令，并且判断到图像中包括至少两个人脸时，通过人脸识别技术和人脸皮肤检测技术确定图像中“最美”的人脸，并对“最美”的人脸进行相应的处理，可选的，在所述摄像头拍摄完成处理后的图像之后，对该拍摄完成的图像进行保存。该实施方式，一方面能够主观选择图像中的人脸进行特殊处理，丰富了图像处理的功能，提升了用户的自主性，另一方面，增强了用户自拍时的趣味性，提升了用户体验。
请参阅图5，图5是本申请实施例提供的一种图像处理装置的结构示意图。如图5所示，该装置30包括：第一判断模块301、第一确定模块302以及第一处理模块303。
其中，第一判断模块301，设置为在检测到终端的摄像头开启时，判断所述摄像头的拍摄预览图像中是否包括人脸；第一确定模块302，设置为如果所述图像中包括人脸，确定所述预览图像中待处理的人脸；第一处理模块303，设置为对确定的所述预览图像中待处理的人脸执行预设的操作。
其中，所述第一处理模块303具体设置为：对确定的所述预览图像中待处理的人脸进行美颜处理；和/或，对确定的所述预览图像中待处理的人脸赋予预设的标签。
在本实施例中，第一确定模块302包括：第一判断单元3021、第一获取单元3022和第一确定单元3023。第一判断单元3021，设置为判断预设时间内是否接收到人脸选择指令；第一获取单元3022，设置为如果所述预 设时间内接收到所述人脸选择指令，获取所述人脸选择指令携带的特征信息，所述特征信息包括位置特征、着装特征、外貌特征中的至少一种；第一确定单元3023，设置为将与所述特征信息相匹配的人脸确定为所述预览图像中待处理的人脸。
在其他一些实施例中，同样请参阅图5，如果所述预设时间内未接收到人脸选择指令，所述第一确定模块302还包括：第二判断单元3024、第二获取单元3025、打分单元3026、第三获取单元3027以及第二确定单元3028。第二判断单元3024，设置为如果所述预设时间内未接收到所述人脸选择指令，判断所述预览图像中是否包括至少两个人脸；第二获取单元3025，设置为如果是，获取所述预览图像中人脸的脸部比例、皮肤细腻度以及肤色光泽度；打分单元3026，设置为根据所述人脸的脸部比例、皮肤细腻度以及肤色光泽度，对所述预览图像中的所述至少两个人脸进行打分；第三获取单元3027，设置为根据所述打分的结果，获取所述预览图像中评分最高的人脸；第二确定单元3028，设置为确定所述评分最高的人脸为所述预览图像中待处理的人脸。
在其他一些实施例中，同样请参阅图5，所述装置30还包括接收模块304、保存模块305以及分享模块306。接收模块304，设置为在所述摄像头拍摄所述执行预设的操作后的预览图像后，接收保存指令；保存模块305，设置为根据所述保存指令，将所述执行预设的操作后的预览图像进行保存；分享模块306，设置为分享保存的所述预览图像。
需要说明的是，本申请实施例中的图像处理装置中的各个模块、单元之间的信息交互、执行过程等内容，由于与本申请方法实施例基于同一构思，具体内容同样适用于图像处理装置。本申请实施例中的各个模块能作为单独的硬件或软件来实现，并且可以根据需要使用单独的硬件或软件来实现各个单元的功能的组合。
本申请实施例提供了一种图像处理装置，该装置通过在终端摄像头开启后，先判断终端拍摄的预览图像中是否包括人脸，如果图像中有人脸，再判断预设时间内是否接收到人脸选择指令，如果接收到人脸选择指令，则根据人脸选择指令确定待处理的人脸，从而对确定的待处理的人脸进行预设操作；如果未接收到人脸选择指令，并且判断到图像中包括至少两个 人脸时，通过人脸识别技术和人脸皮肤检测技术确定图像中“最美”的人脸，并对“最美”的人脸进行相应的处理，可选的，在所述摄像头拍摄完成处理后的图像之后，对该拍摄完成的图像进行保存。该实施方式，一方面能够主观选择图像中的人脸进行特殊处理，丰富了图像处理的功能，提升了用户的自主性，另一方面，增强了用户自拍时的趣味性，提升了用户体验。
请参阅图6，图6是本申请实施例提供的一种电子设备的结构示意图，如图6所示，该电子设备40包括：
一个或多个处理器41以及存储器42，图6中以一个处理器41为例。
处理器41和存储器42可以通过总线或者其他方式连接，图6中以通过总线连接为例。
存储器42作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的图像处理方法对应的程序指令/模块(例如，附图5所示的模块和单元)。处理器41通过运行存储在存储器42中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例图像处理方法。
存储器42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、至少一个功能所需要的应用程序；存储数据区可存储根据图像处理装置的使用所创建的数据等。此外，存储器42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、或其他非易失性固态存储器件。在一些实施例中，存储器42可选包括相对于处理器41远程设置的存储器，这些远程存储器可以通过网络连接至图像处理装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器42中，当被所述一个或者多个处理器41执行时，执行上述任意方法实施例中的图像处理方法，例如，执行以上描述的图1中的方法步骤S101至步骤S103，图2中的方法步骤S1021至步骤S1023，图3中的方法步骤S201至步骤S208，图4中的方法 步骤S201至步骤S210，实现图5中的模块301-306、单元3021-3028的功能。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
本申请实施例的电子设备以多种形式存在，包括但不限于：
(1)移动通信设备：这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括：智能手机、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备：这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括：PDA、MID和UMPC设备等。
(3)其他具有数据交互功能的电子装置。
本申请实施例提供了一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被电子设备执行上述任意方法实施例中的图像处理方法，例如，执行以上描述的图1中的方法步骤S101至步骤S103，图2中的方法步骤S1021至步骤S1023，图3中的方法步骤S201至步骤S208，图4中的方法步骤S201至步骤S210，实现图5中的模块301-306、单元3021-3028的功能。
本申请实施例提供了一种计算机程序产品，包括存储在非易失性计算机可读存储介质上的计算程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时时，使所述计算机执行上述任意方法实施例中的图像处理方法，例如，执行以上描述的图1中的方法步骤S101至步骤S103，图2中的方法步骤S1021至步骤S1023，图3中的方法步骤S201至步骤S208，图4中的方法步骤S201至步骤S210，实现图5中的模块301-306、单元3021-3028的功能。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现 本实施例方案的目的。
通过以上的实施方式的描述，本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件。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是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一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的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；在本申请的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本申请的不同方面的许多其它变化，为了简明，它们没有在细节中提供；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。
工业实用性
如上所述，本发明实施例提供的一种图像处理方法、装置、电子设备及存储介质具有以下有益效果：能够主观选择图像中的人脸进行特殊处理，丰富了图像处理的功能，提升了用户的自主性。

Claims (12)

  1. 一种图像处理方法，包括：
    在检测到终端的摄像头开启时，判断所述摄像头的拍摄预览图像中是否包括人脸；
    如果所述预览图像中包括人脸，确定所述预览图像中待处理的人脸；
    对确定的所述预览图像中待处理的人脸执行预设的操作。
  2. 根据权利要求1所述的方法，其中，所述确定所述预览图像中待处理的人脸，包括：
    判断预设时间内是否接收到人脸选择指令；
    如果所述预设时间内接收到所述人脸选择指令，获取所述人脸选择指令携带的特征信息，所述特征信息包括位置特征、着装特征、外貌特征中的至少一种；
    将与所述特征信息相匹配的人脸确定为所述预览图像中待处理的人脸。
  3. 根据权利要求2所述的方法，其中，所述方法还包括：
    如果所述预设时间内未接收到所述人脸选择指令，判断所述预览图像中是否包括至少两个人脸；
    如果是，获取所述预览图像中人脸的脸部比例、皮肤细腻度以及肤色光泽度；
    根据所述人脸的脸部比例、皮肤细腻度以及肤色光泽度，对所述预览图像中的所述至少两个人脸进行打分；
    根据所述打分的结果，获取所述预览图像中评分最高的人脸；
    确定所述评分最高的人脸为所述预览图像中待处理的人脸。
  4. 根据权利要求1至3任一项所述的方法，其中，所述对确定的所述预览图像中待处理的人脸执行预设的操作，包括：
    对确定的所述预览图像中待处理的人脸进行美颜处理；和/或
    对确定的所述预览图像中待处理的人脸赋予预设的标签。
  5. 根据权利要求4所述的方法，其中，所述方法还包括：
    在所述摄像头拍摄所述执行预设的操作后的预览图像后，接收保存指令；
    根据所述保存指令，将所述执行预设的操作后的预览图像进行保存。
  6. 一种图像处理装置，包括：
    第一判断模块，设置为在检测到终端的摄像头开启时，判断所述摄像头的拍摄预览图像中是否包括人脸；
    第一确定模块，设置为如果所述预览图像中包括人脸，确定所述预览图像中待处理的人脸；
    第一处理模块，设置为对确定的所述预览图像中待处理的人脸执行预设的操作。
  7. 根据权利要求6所述的装置，其中，所述第一确定模块包括：
    第一判断单元，设置为判断预设时间内是否接收到人脸选择指令；
    第一获取单元，设置为如果所述预设时间内接收到所述人脸选择指令，获取所述人脸选择指令携带的特征信息，所述特征信息包括位置特征、着装特征、外貌特征中的至少一种；
    第一确定单元，设置为将与所述特征信息相匹配的人脸确定为所述预览图像中待处理的人脸。
  8. 根据权利要求7所述的装置，其中，所述第一确定模块还包括：
    第二判断单元，设置为如果所述预设时间内未接收到所述人脸选择指令，判断所述预览图像中是否包括至少两个人脸；
    第二获取单元，设置为如果是，获取所述预览图像中人脸的脸部比例、皮肤细腻度以及肤色光泽度；
    打分单元，设置为根据所述人脸的脸部比例、皮肤细腻度以及肤色光泽度，对所述预览图像中的所述至少两个人脸进行打分；
    第三获取单元，设置为根据所述打分的结果，获取所述预览图像中评分最高的人脸；
    第二确定单元，设置为确定所述评分最高的人脸为所述预览图像中待处理的人脸。
  9. 根据权利要求6-8任一项所述的装置，其中，所述第一处理模块具体设置为：
    对确定的所述预览图像中待处理的人脸进行美颜处理；和/或
    对确定的所述预览图像中待处理的人脸赋予预设的标签。
  10. 根据权利要求9所述的装置，其中，所述装置还包括：
    接收模块，设置为在所述摄像头拍摄所述执行预设的操作后的预览图像后，接收保存指令；
    保存模块，设置为根据所述保存指令，将所述执行预设的操作后的预览图像进行保存。
  11. 一种电子设备，包括：至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-5任一项所述的方法。
  12. 一种存储介质，其中，所述存储介质中存储有计算机程序，所述计算机程序被设置为运行时执行所述权利要求1-5任一项所述的方法。
PCT/CN2018/100213 2017-11-22 2018-08-13 一种图像处理方法、装置、电子设备及存储介质 Ceased WO2019100766A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711173989.6 2017-11-22
CN201711173989.6A CN107948506A (zh) 2017-11-22 2017-11-22 一种图像处理方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2019100766A1 true WO2019100766A1 (zh) 2019-05-31

Family

ID=61930687

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/100213 Ceased WO2019100766A1 (zh) 2017-11-22 2018-08-13 一种图像处理方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN107948506A (zh)
WO (1) WO2019100766A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111091512A (zh) * 2019-12-18 2020-05-01 广州酷狗计算机科技有限公司 图像处理方法及装置、计算机可读存储介质
CN112734661A (zh) * 2020-12-30 2021-04-30 维沃移动通信有限公司 图像处理方法及装置
CN112785488A (zh) * 2019-11-11 2021-05-11 宇龙计算机通信科技(深圳)有限公司 一种图像处理方法、装置、存储介质及终端
CN114092357A (zh) * 2021-11-26 2022-02-25 维沃移动通信有限公司 图像处理方法、图像处理装置和电子设备
WO2023273111A1 (zh) * 2021-06-29 2023-01-05 北京市商汤科技开发有限公司 一种图像处理方法、装置、计算机设备和存储介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107948506A (zh) * 2017-11-22 2018-04-20 珠海格力电器股份有限公司 一种图像处理方法、装置及电子设备
CN110580808B (zh) * 2018-06-08 2021-03-23 杭州海康威视数字技术股份有限公司 一种信息处理方法、装置、电子设备及智能交通系统
CN108965692B (zh) * 2018-06-15 2021-03-09 Oppo广东移动通信有限公司 贴纸设置方法及装置
CN109034063A (zh) * 2018-07-27 2018-12-18 北京微播视界科技有限公司 人脸特效的多人脸跟踪方法、装置和电子设备
CN109145878B (zh) * 2018-09-30 2022-02-15 北京小米移动软件有限公司 图像提取方法及装置
JP7467139B2 (ja) * 2020-01-30 2024-04-15 キヤノン株式会社 表示制御装置及びその制御方法
CN113749614B (zh) * 2020-06-05 2023-03-10 华为技术有限公司 皮肤检测方法和设备
CN111860342A (zh) * 2020-07-22 2020-10-30 北京字节跳动网络技术有限公司 图像处理方法、装置、存储介质及电子设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090273667A1 (en) * 2006-04-11 2009-11-05 Nikon Corporation Electronic Camera
CN103413270A (zh) * 2013-08-15 2013-11-27 北京小米科技有限责任公司 一种图像的处理方法、装置和终端设备
CN106210521A (zh) * 2016-07-15 2016-12-07 深圳市金立通信设备有限公司 一种拍照方法及终端
CN106412458A (zh) * 2015-07-31 2017-02-15 中兴通讯股份有限公司 一种图像处理方法和装置
CN106815557A (zh) * 2016-12-20 2017-06-09 北京奇虎科技有限公司 一种人脸面部特征的评价方法、装置以及移动终端
CN107274354A (zh) * 2017-05-22 2017-10-20 奇酷互联网络科技（深圳）有限公司 图像处理方法、装置和移动终端
CN107948506A (zh) * 2017-11-22 2018-04-20 珠海格力电器股份有限公司 一种图像处理方法、装置及电子设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090273667A1 (en) * 2006-04-11 2009-11-05 Nikon Corporation Electronic Camera
CN103413270A (zh) * 2013-08-15 2013-11-27 北京小米科技有限责任公司 一种图像的处理方法、装置和终端设备
CN106412458A (zh) * 2015-07-31 2017-02-15 中兴通讯股份有限公司 一种图像处理方法和装置
CN106210521A (zh) * 2016-07-15 2016-12-07 深圳市金立通信设备有限公司 一种拍照方法及终端
CN106815557A (zh) * 2016-12-20 2017-06-09 北京奇虎科技有限公司 一种人脸面部特征的评价方法、装置以及移动终端
CN107274354A (zh) * 2017-05-22 2017-10-20 奇酷互联网络科技（深圳）有限公司 图像处理方法、装置和移动终端
CN107948506A (zh) * 2017-11-22 2018-04-20 珠海格力电器股份有限公司 一种图像处理方法、装置及电子设备

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112785488A (zh) * 2019-11-11 2021-05-11 宇龙计算机通信科技(深圳)有限公司 一种图像处理方法、装置、存储介质及终端
CN111091512A (zh) * 2019-12-18 2020-05-01 广州酷狗计算机科技有限公司 图像处理方法及装置、计算机可读存储介质
CN111091512B (zh) * 2019-12-18 2024-03-01 广州酷狗计算机科技有限公司 图像处理方法及装置、计算机可读存储介质
CN112734661A (zh) * 2020-12-30 2021-04-30 维沃移动通信有限公司 图像处理方法及装置
WO2023273111A1 (zh) * 2021-06-29 2023-01-05 北京市商汤科技开发有限公司 一种图像处理方法、装置、计算机设备和存储介质
CN114092357A (zh) * 2021-11-26 2022-02-25 维沃移动通信有限公司 图像处理方法、图像处理装置和电子设备

Also Published As

Publication number Publication date
CN107948506A (zh) 2018-04-20

Similar Documents

Publication Publication Date Title
WO2019100766A1 (zh) 一种图像处理方法、装置、电子设备及存储介质
US9207771B2 (en) Gesture based user interface
CN106022079B (zh) 一种指纹解锁方法及终端
WO2017185630A1 (zh) 基于情绪识别的信息推荐方法、装置和电子设备
CN103995998A (zh) 一种非接触手势命令的认证方法以及用户设备
CN108491147A (zh) 一种基于虚拟人物的人机交互方法及移动终端
US9423908B2 (en) Distinguishing between touch gestures and handwriting
US20150363591A1 (en) Method of activate upon authentication of electronic device
CN110866236A (zh) 隐私图片显示方法、装置、终端及存储介质
CN105404878A (zh) 一种照片分类方法和装置
JP2020507159A (ja) ピクチャプッシュの方法、移動端末および記憶媒体
CN110431838A (zh) 提供人脸识别摄像机的动态内容的方法及系统
CN111191503A (zh) 一种行人属性识别方法、装置、存储介质及终端
CN107222675A (zh) 一种移动终端的拍照方法及移动终端
CN107179831A (zh) 启动应用的方法、装置、存储介质及终端
WO2022089272A1 (zh) 图像处理方法及装置
US9733826B2 (en) Interacting with application beneath transparent layer
CN107580182A (zh) 一种抓拍方法、移动终端及计算机可读存储介质
CN116975820A (zh) 应用程序的登录验证方法、装置、电子设备及存储介质
CN111722892A (zh) 系统语言切换的方法、电子设备及存储装置
CN105704396A (zh) 一种图片处理方法及装置
CN112114806A (zh) 显示界面的生成方法、装置以及系统
CN116360298A (zh) 设备运行方法、装置、电子设备及存储介质
CN103984415B (zh) 一种信息处理方法及电子设备
CN108628454B (zh) 基于虚拟人的视觉交互方法及系统

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: 18881060

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: 18881060

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 13/10/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18881060

Country of ref document: EP

Kind code of ref document: A1