WO2021109680A1 - 一种人脸图像处理方法、装置、计算机设备及介质 - Google Patents

一种人脸图像处理方法、装置、计算机设备及介质 Download PDF

Info

Publication number
WO2021109680A1
WO2021109680A1 PCT/CN2020/116526 CN2020116526W WO2021109680A1 WO 2021109680 A1 WO2021109680 A1 WO 2021109680A1 CN 2020116526 W CN2020116526 W CN 2020116526W WO 2021109680 A1 WO2021109680 A1 WO 2021109680A1
Authority
WO
WIPO (PCT)
Prior art keywords
face image
face
optimized
image
facial
Prior art date
Application number
PCT/CN2020/116526
Other languages
English (en)
French (fr)
Inventor
王金栋
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to US17/610,315 priority Critical patent/US20220245962A1/en
Priority to EP20896073.2A priority patent/EP3958169A4/en
Publication of WO2021109680A1 publication Critical patent/WO2021109680A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • 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
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/772—Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/50—Maintenance of biometric data or enrolment thereof

Definitions

  • This application relates to the field of image processing technology, in particular to a method, device, computer equipment and medium for processing a face image.
  • This application provides a face image processing method, device, computer equipment, and medium to realize automatic optimization processing of face images including defects.
  • an embodiment of the present application provides a face image processing method, including: acquiring a face image to be optimized of a target user; acquiring a reference face image matching the face image to be optimized from a preset face database Optimize the face image to be optimized according to the reference face image.
  • an embodiment of the present application provides a face image processing device, including: a face image acquisition module to be optimized for acquiring a face image to be optimized for a target user; It is assumed that a face database acquires a reference face image matching the face image to be optimized; an image optimization processing module is used to optimize the face image to be optimized according to the reference face image.
  • an embodiment of the present application provides a computer including: one or more processors; a storage device for storing one or more programs; when the one or more programs are used by the one or more The processor executes, so that the one or more processors implement the face image processing method described in any of the embodiments of the present application.
  • an embodiment of the present application provides a storage medium that stores a computer program that, when executed by a processor, implements the face image processing method described in any of the embodiments of the present application.
  • FIG. 1 is a schematic flowchart of a face image processing method provided by an embodiment of the application
  • FIG. 2 is a schematic flowchart of a face image processing method provided by an embodiment of the application.
  • FIG. 3 is a schematic structural diagram of a face image processing apparatus provided by an embodiment of the application.
  • FIG. 4 is a schematic structural diagram of a computer device provided by an embodiment of this application.
  • FIG. 1 is a schematic flowchart of a face image processing method provided by an embodiment of this application. This method can be applied to the situation that the intelligent terminal automatically optimizes the face image including the defect.
  • the method can be executed by the face image processing device provided by the present application, which can be implemented by software and/or hardware and integrated in a smart terminal (typically, various types of smart phones, tablet computers, or personal computers, etc.) on.
  • a smart terminal typically, various types of smart phones, tablet computers, or personal computers, etc.
  • a face image processing method provided by this application includes S110, S120, and S130.
  • S110 Acquire a face image to be optimized of the target user.
  • the target user is the user who uses the smart terminal to obtain the face image.
  • the target user may be a user who has unlocking authority for the smart terminal.
  • the unlocking authority includes, but is not limited to, fingerprint unlocking, face recognition unlocking, password unlocking, and so on.
  • the face image to be optimized may be a face image that has defects and needs to be optimized. Defects can be defects such as blurry, overexposure, over-darkness, closed eyes, or face distortion such as failure to focus. This type of defect cannot be repaired by itself through the smart terminal's camera function.
  • the smart terminal may obtain the face image of the target user through the photographing function, where the photographing function includes Selfie and non-Selfie functions.
  • the smart terminal can also acquire the face image of the target user according to the designation or selection operation of the target user.
  • the face image of the target user specified by the photo album, gallery or other application APP (Application) of the smart terminal is used as the face image of the target user, the embodiment of the application does not obtain the face image of the target user from the smart terminal The way is limited.
  • acquiring the face image of the target user to be optimized may include: acquiring the face image of the target user, performing defect detection on the face image, and determining that the face image has a face When there is a defect, the face image is determined as the face image to be optimized.
  • the facial defect in the face image can be detected, and when it is determined that the face image has a facial defect to be repaired according to the detection result, there will be a face
  • the defective face image is used as the face image to be optimized of the target user.
  • S120 Obtain a reference face image matching the face image to be optimized from a preset face database.
  • the reference face image is an unlocked face image used when the target user performs face unlocking, and/or a standard face image stored by the target user.
  • the preset face database may be a database pre-established for the target user and used to store the unlocked face image of the target user and/or the standard face image stored by the target user.
  • the unlocked face image may be an image used for face recognition and unlocking.
  • the unlocked face image may be the face image collected by the smart terminal when the target user performs face recognition and unlocking through the smart terminal, or it may be pre-stored by the smart terminal for face recognition and unlocking of the target user. The image is compared and matched with the standard face image.
  • the collected face image and the standard face image can also be used as the unlocked face image at the same time, that is, all the face images that can be used to realize the face unlock can be used as the unlocked face image.
  • the embodiments of the present application are not There is no limitation on the method of obtaining the unlocked face image.
  • the standard face image stored by the target user may be a face image obtained in advance by the target user through a photographing function, a download function, or a picture saving function, and can be used for image optimization.
  • a selfie of the target user stored in a local album that has undergone image optimization processing, etc. can be used as a reference face image.
  • smart terminals can be equipped with a face recognition unlocking function.
  • the unlocked face image used by the face recognition unlocking function is often a clear and standard face image. Therefore, the unlocked face image can be used as a reference face image.
  • the target user uses the smart terminal, he will save his standard face image through various image acquisition methods such as the camera function, the download function, or the picture saving function.
  • These standard portrait images are usually clear and standard facial images. Therefore, standard facial images stored by the target user can also be used as reference facial images.
  • S130 Perform optimization processing on the face image to be optimized according to the reference face image.
  • the optimized face image can be optimized according to the standard reference face image.
  • the unlocked face image and the standard face image stored by the target user will not have defects such as blurry, overexposed, dark, closed eyes or face distortion, etc.
  • the unlocked face image and/or target The standard face image stored by the user is used as the reference face image to optimize the optimized face image, and can repair the defects in the optimized face image such as blurry, overexposed, dark, closed eyes or face distortion in the optimized face image .
  • the embodiment of the application obtains the face image to be optimized of the target user, and obtains the face image matching the face image to be optimized from the preset face database as the reference face image, so as to treat the optimized face according to the reference face image
  • Image optimization processing solves the problem that existing smart terminals cannot optimize partial defect facial images, and realizes automatic optimization processing of facial images including defects.
  • the method may include: acquiring a face image collected when the target user performs face unlocking as the unlocking A face image; and/or, obtaining a standard face image used for comparison and matching with the collected face image when the target user performs face unlocking as the unlocked face image; and obtaining a standard stored by the target user Face image; establishing the preset face database according to the unlocked face image and/or the standard face image stored by the target user.
  • the standard face image used when unlocking the face is used for comparison and matching with the face image collected when the target user is unlocking the face
  • the standard face image used when unlocking the face will not include such
  • the failed focus image is blurry, overexposed, too dark, closed eyes or face distortion, etc.
  • the facial features and facial expressions in the standard facial image used when the face is unlocked will meet the pre-set standard requirements of the smart terminal.
  • the face image collected when the target user unlocks the face is used for unlocking.
  • the target user will pay attention to maintaining the rigor of facial features to ensure that the unlocking can be successful, so the face collected when the target user unlocks the face
  • the image generally does not include defects such as blurring, overexposure, over-darkness, closed eyes, or face distortion. Therefore, the face image collected when the target user performs face unlocking can be used as the unlocked face image; and/or the standard face image used for comparison and matching with the collected face image when the target user performs face unlocking As an unlocked face image.
  • it can also obtain the standard face image stored by the target user, such as obtaining the standard face image stored in the local album or the cloud album corresponding to the target user, and unlock the face image and/or the standard person stored by the target user.
  • the face image establishes a corresponding preset face database.
  • target users may be one or multiple. As long as users with face recognition and unlocking permissions on the smart terminal can be used as target users, this embodiment of the application does not limit this.
  • the establishing the preset face database according to the unlocked face image and/or the standard face image stored by the target user may include: selecting the unlocked person according to the face image filtering conditions The face image and/or the standard face image stored by the target user are screened to obtain a face image sample; the face image sample includes the unlocked face image and/or the standard face image stored by the target user And at least one feature value of the unlocked face image and/or the standard face image stored by the target user; adding the face image sample to the preset face database.
  • the face image filtering condition may be a condition for filtering the unlocked face image and/or the standard face image stored by the target user to obtain a high-quality face image.
  • the filtering conditions for the face image may be that the image is clear, the eyes are not closed, or the face is not blocked.
  • the embodiment of the present application does not limit the specific content of the face image screening condition.
  • the acquired unlocked face images and/or the standard face images stored by the target user may be filtered according to face image filtering conditions. This is because the standard face image in the unlocked face image and/or the feature values such as the angle or brightness corresponding to the standard face image stored by the target user may not be unique.
  • the smart terminal correspondingly stores different angles for a target user. Standard face images corresponding to multiple unlocked face images. And in view of the variability of the unlocking scene, the brightness, angle, and facial emotions of the target user's face are not consistent during each unlocking process. Or, the target user stores multiple standard facial images of different angles in the smart terminal.
  • the face image sample may include one or more unlocked face images and at least one feature value corresponding to each unlocked face image, and/or include one or more standard face images stored by the target user and each At least one feature value corresponding to the standard face image stored by the target user.
  • the feature value is used to prompt the features of the face image, which may include, but is not limited to, image sharpness, angle value, brightness value, facial expression, facial features, facial contour, etc.
  • the face image sample can be added to the preset face database to complete the establishment of the preset face database.
  • the face image samples may include multiple face image samples of different face angles of the target user.
  • the smart terminal can always obtain unlocked face images and/or standard face images stored by the target user during the use process. Therefore, the preset face database can also follow a set period (such as one week, etc.) Update the unlocked face image stored locally and/or the standard face image stored by the target user according to the latest unlocked face image acquired by the smart terminal and/or the standard face image stored by the target user to ensure the optimization effect of the face image .
  • a set period such as one week, etc.
  • the feature value may include an angle value
  • the obtaining a reference face image matching the face image to be optimized from a preset face database may include: according to the value of the face image to be optimized The angle value, obtaining a face image matching the angle value of the face image to be optimized from a preset face database as the reference face image.
  • the angle value can be any angle value based on the XYZ axis
  • the angle value in the face image may be used as the basis, and the face angles that are similar The face image is used as a reference face image.
  • the advantage of this setting is that the face angle of the face image to be optimized is not unique, and the face image can also involve multiple face angles of the target user. Therefore, according to the angle value of the face image to be optimized, a face image matching the angle value of the face image to be optimized is obtained from the preset face database as a reference face image, which can ensure the optimization effect of the face image.
  • the face image to be optimized is the front face image of the target user
  • the unlocked face image and/or the front standard face stored by the target user can be obtained when the target user faces the smart terminal.
  • the image is used as a reference face image.
  • the face image to be optimized is the left face image of the target user
  • the unlocked face image when the target user faces the smart terminal on the left side and/or the standard face image stored on the left side of the target user can be obtained as the reference person Face image.
  • the matching unlocked face image is selected as the reference face image, which can effectively ensure the matching degree between the reference face image and the face image to be optimized, thereby further ensuring the optimization effect of the face image.
  • the performing optimization processing on the face image to be optimized according to the reference face image may include: extracting feature values of the reference face image and the face image to be optimized; The feature value of the face image to be optimized is optimized with reference to the feature value of the face image.
  • the feature values of the reference face image and the face image to be optimized can be extracted respectively, so that the feature values of the face image to be optimized are extracted according to the feature values of the reference face image.
  • the characteristic value is optimized.
  • the feature value may further include at least one of image clarity, brightness value, facial expression, facial features, and facial contour.
  • the performing optimization processing on the feature value of the face image to be optimized according to the feature value of the reference face image may include: performing the optimization process on the person to be optimized according to the picture definition of the reference face image.
  • the picture definition of the face image is optimized; the brightness value of the face image to be optimized is optimized according to the brightness value of the reference face image; the person to be optimized is optimized according to the facial expression of the reference face image Optimizing the facial expressions of the face image; optimizing the facial features of the face image to be optimized according to the facial features of the reference face image; or, optimizing the facial features of the face image to be optimized according to the facial contours of the reference face image
  • the face contour of the face image to be optimized is optimized.
  • the optimizing the picture definition of the face image to be optimized according to the picture definition of the reference face image may include: when the picture definition of the face image to be optimized satisfies the first In the case of a face restoration condition, the image clarity of the face image to be optimized is restored according to the image clarity of the reference face image; the image clarity of the face image to be optimized is restored according to the brightness value of the reference face image; Optimizing the brightness of the face image to be optimized; may include: in the case that the brightness value of the face image to be optimized meets the second face restoration condition, performing optimization on the brightness value of the reference face image Repairing the brightness value of the face image; said optimizing the face expression of the face image to be optimized according to the face expression of the reference face image; may include: in the face image of the person to be optimized In the case that the facial expression satisfies the third face restoration condition, the facial expression of the face image to be optimized is repaired according to the facial expression of the reference face image; the person according to the reference face image
  • the first face restoration condition may be used to determine whether the picture definition of the face image to be optimized meets the restoration optimization condition.
  • the first face restoration condition may be: the picture definition of the face image to be optimized is lower than the first preset threshold.
  • the first preset threshold may be set according to actual requirements, which is not limited in the embodiment of the present application.
  • the first face restoration condition may also be: noise or blurring of the face image to be optimized.
  • the second face restoration condition may be used to determine whether the brightness value of the face image to be optimized meets the restoration optimization condition.
  • the second face restoration condition may be: the brightness value of the face image to be optimized is lower than the second preset threshold, or the brightness value of the face image to be optimized is higher than the third preset threshold.
  • the second preset threshold and the third preset threshold can also be set according to actual needs, which is not limited in the embodiment of the present application.
  • the third face restoration condition may be used to determine whether the facial expression of the face image to be optimized meets the restoration optimization condition.
  • the third face repair condition may be: the face expression of the face image to be optimized is distorted or there is no smiling expression, etc.
  • the fourth face restoration condition may be used to determine whether the facial features of the face image to be optimized meet the restoration optimization condition.
  • the fourth face repair condition may be: eyes closed or half closed in the face image to be optimized.
  • the fifth face restoration condition may be used to determine whether the face contour of the face image to be optimized meets the restoration optimization condition.
  • the fifth face repair condition may be: the face contour of the face image to be optimized is distorted, etc.
  • the image definition of the optimized face image can be repaired according to the image definition of the reference face image, such as setting the image definition of the face image to be optimized
  • the face image to be optimized is subjected to noise reduction processing, blur compensation or enhancement processing, etc., so as to realize the optimization of the picture definition of the face image to be optimized.
  • the brightness value of the face image to be optimized can be optimized according to the brightness value of the reference face image Repair, such as setting the brightness value of the face image to be optimized as the brightness value of the reference face image, so as to realize the brightness balance adjustment of the face image to be optimized.
  • the facial expression of the face image to be optimized meets the third face restoration condition, such as the distortion of the middle face of the face image to be optimized, or the facial expression without a smile, etc., it can be treated according to the facial expression of the reference face image
  • the facial expressions of the optimized face images are repaired, for example, the facial expressions of the reference face images are added to the optimized face images to realize the adjustment of the facial expressions of the optimized faces.
  • the face image can be optimized based on the eye features of the reference face image
  • the face image can be optimized based on the eye features of the reference face image
  • the eye features of the face image to be optimized such as adjusting the eye features of the face image to be optimized according to the eye features of the reference face image, to repair the closed and half-closed eyes in the face image to be optimized.
  • the face contour of the optimized face image can be treated according to the facial contour features of the reference face image Feature restoration, such as adjusting the face contour features of the optimized face image according to the face contour features of the reference face image, etc., to repair the facial distortion in the face image to be optimized.
  • FIG. 2 is a schematic flow chart of a face image processing method provided by an embodiment of the application.
  • the target user can repeatedly collect the target user’s face image during the process of using the smart terminal.
  • the smart terminal When the smart terminal obtains the captured or designated face image of the target user, it can perform defect detection on the obtained face image, and when it is determined that the face image has a facial defect, the face image is used as the face to be optimized image. Then, the smart terminal can obtain the face image matching the angle value of the face image to be optimized from the preset face database as the reference face image, and extract the position of the defect point in the face image to be optimized and the reference face image correspondence The feature value of the position is optimized according to the feature value of the corresponding position of the reference face image to optimize the feature value of the position of the defect point in the face image to be optimized, so as to realize the optimization of the defect point of the face image to be optimized, and finally to the target The user outputs the optimized picture.
  • the embodiment of the application obtains the face image to be optimized of the target user, obtains the face image matching the face image to be optimized from the preset face database as the reference face image, and extracts the reference face image and the person to be optimized
  • the feature value of the face image is optimized according to the feature value of the reference face image.
  • the feature value of the optimized face image is optimized to solve the problem that the existing smart terminal cannot optimize the partial defect face image. Automatic optimization of face images.
  • FIG. 3 is a schematic structural diagram of a face image processing device provided by an embodiment of the application. As shown in FIG. 3, the face image processing device in the embodiment of the application, Can be integrated on the smart terminal.
  • the device includes: a face image acquisition module 210 to be optimized, a reference face image acquisition module 220, and an image optimization processing module 230, wherein:
  • the to-be-optimized face image acquisition module 210 is configured to acquire the to-be-optimized face image of the target user
  • the reference face image acquisition module 220 is configured to acquire a reference face image matching the face image to be optimized from a preset face database
  • the image optimization processing module 230 is configured to perform optimization processing on the face image to be optimized according to the reference face image.
  • the embodiment of the application obtains the face image to be optimized of the target user, and obtains the face image matching the face image to be optimized from the preset face database as the reference face image, so as to treat the optimized face according to the reference face image
  • Image optimization processing solves the problem that existing smart terminals cannot optimize partial defect facial images, and realizes automatic optimization processing of facial images including defects.
  • the reference face image is an unlocked face image used when the target user performs face unlocking, and/or a standard face image stored by the target user;
  • the device further includes: a preset The face database establishment module is configured to obtain the face image collected when the target user performs face unlocking as the unlocked face image; and/or obtain the face image collected when the target user performs face unlocking.
  • the standard face image for comparison and matching of the face image is used as the unlocked face image; the standard face image stored by the target user is acquired; according to the unlocked face image and/or the standard face stored by the target user The image establishes the preset face database.
  • the preset face database establishment module is configured to filter the unlocked face image and/or the standard face image stored by the target user according to the face image filtering conditions to obtain a face image sample;
  • the face image sample includes the unlocked face image and/or the standard face image stored by the target user and at least one feature of the unlocked face image and/or the standard face image stored by the target user Value; adding the face image sample to the preset face database.
  • the feature value includes an angle value; referring to the face image acquisition module 220, it is configured to obtain the same value as the face image to be optimized from a preset face database according to the angle value of the face image to be optimized.
  • the face image matching the angle value of is used as the reference face image.
  • the image optimization processing module 230 is configured to extract feature values of the reference face image and the face image to be optimized; and compare the face image to be optimized according to the feature value of the reference face image The eigenvalues are optimized.
  • the feature value further includes at least one of picture clarity, brightness value, facial expression, facial features, and facial contour
  • the image optimization processing module 230 is configured to be configured according to the reference facial image Optimize the picture definition of the face image to be optimized; optimize the brightness value of the face image to be optimized according to the brightness value of the reference face image; and optimize the brightness value of the face image to be optimized according to the reference face image
  • Optimize the facial expressions of the facial image to be optimized optimize the facial features of the facial image to be optimized according to the facial features of the reference facial image; or, according to the The face contour of the face image to be optimized is optimized with reference to the face contour of the face image.
  • the image optimization processing module 230 is configured to perform the correction of the image definition of the reference face image according to the image definition of the reference face image when the picture definition of the face image to be optimized satisfies the first face restoration condition.
  • the image clarity of the face image to be optimized is restored; in the case that the brightness value of the face image to be optimized meets the second face restoration condition, the person to be optimized is corrected according to the brightness value of the reference face image
  • the brightness value of the face image is restored; in the case that the facial expression of the face image to be optimized meets the third face restoration condition, the face image to be optimized is processed according to the facial expression of the reference face image
  • the facial expressions of the face image to be optimized are repaired; in the case that the eye features of the face image to be optimized meet the fourth face repair condition, the face image of the face image to be optimized is corrected according to the eye features of the reference face image Eye features are repaired; in the case that the face contour of the face image to be optimized meets the fifth face restoration condition, the face image of the face image to be optimized is
  • the above-mentioned facial image processing device can execute the facial image processing method provided by any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.
  • the face image processing method provided in any embodiment of this application.
  • the face image processing device introduced above is a device that can execute the face image processing method in the embodiment of this application, based on the face image processing method introduced in the embodiment of this application, those skilled in the art can understand The specific implementation of the face image processing device of this embodiment and various variations thereof, so how the face image processing device implements the face image processing method in the embodiment of the application will not be described in detail here. As long as the person skilled in the art implements the face image processing method in the embodiment of the application, the device shall fall within the scope of the protection of the application.
  • FIG. 4 is a schematic structural diagram of a computer device provided by an embodiment of the application.
  • the computer device provided by the application includes: one or more processors 31 And the storage device 32; the processor 31 of the computer device may be one or more, in FIG. 4, one processor 31 is taken as an example; the storage device 32 is used to store one or more programs; the one or more programs are The one or more processors 31 execute, so that the one or more processors 31 implement the face image processing method as described in the embodiments of the present application: obtain the to-be-optimized face image of the target user; The face database acquires a reference face image that matches the face image to be optimized; and optimizes the face image to be optimized according to the reference face image.
  • Computer equipment can typically be any type of intelligent terminal equipment.
  • the processor 31 and the storage device 32 in the computer equipment may be connected through a bus or other methods.
  • the connection through a bus is taken as an example.
  • the storage device 32 can be configured to store software programs, computer-executable programs, and modules, such as the program instructions/modules corresponding to the face image processing method described in the embodiments of the present application (for example, face image The to-be-optimized face image acquisition module 210, the reference face image acquisition module 220, and the image optimization processing module 230 in the processing device).
  • the storage device 32 may include a storage program area and a storage data area, where the storage program area may store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the device, and the like.
  • the storage device 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the storage device 32 may further include a memory provided remotely with respect to the processor 31, and these remote memories may be connected to the computer device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the embodiment of the present application also provides a storage medium, the storage medium stores a computer program, and when the computer program is executed by a processor, the face image processing method described in any of the embodiments of the present application is obtained: The face image to be optimized; a reference face image matching the face image to be optimized is obtained from a preset face database; and the face image to be optimized is optimized according to the reference face image.
  • the embodiment of the application obtains the face image to be optimized of the target user, and obtains the face image matching the face image to be optimized from the preset face database as the reference face image, so as to treat the optimized face according to the reference face image
  • Image optimization processing solves the problem that existing smart terminals cannot optimize partial defect facial images, and realizes automatic optimization processing of facial images including defects.
  • the computer storage medium of the embodiment of the present application may adopt any combination of one or more computer-readable media.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above.
  • computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (Read Only Memory) , ROM), Erasable Programmable Read Only Memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or the above Any suitable combination of.
  • the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.
  • suitable medium including but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.
  • the computer program code used to perform the operations of this application can be written in one or more programming languages or a combination thereof.
  • the programming languages include object-oriented programming languages—such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider for example, using an Internet service provider to pass Internet connection.
  • terminal encompasses any suitable type of wireless user equipment, such as a mobile phone, a portable data processing device, a portable web browser, or a vehicle-mounted mobile station.
  • the various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic or any combination thereof.
  • some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, although the present application is not limited thereto.
  • Computer program instructions can be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or written in any combination of one or more programming languages Source code or object code.
  • ISA Instruction Set Architecture
  • the block diagram of any logic flow in the drawings of the present application may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions.
  • the computer program can be stored on the memory.
  • the memory can be of any type suitable for the local technical environment and can be implemented using any suitable data storage technology, such as but not limited to read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), optical Memory devices and systems (Digital Video Disc (DVD) or Compact Disk (CD)), etc.
  • Computer-readable media may include non-transitory storage media.
  • the data processor can be any type suitable for the local technical environment, such as but not limited to general-purpose computers, special-purpose computers, microprocessors, digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (ASICs) ), programmable logic devices (Field-Programmable Gate Array, FGPA), and processors based on multi-core processor architecture.
  • DSP Digital Signal Processing
  • ASICs application specific integrated circuits
  • FGPA programmable logic devices

Abstract

一种人脸图像处理方法、装置、计算机设备及介质。该人脸图像处理，包括：获取目标用户的待优化人脸图像(S110)；从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像(S120)；根据所述参考人脸图像对所述待优化人脸图像进行优化处理(S130)。

Description

一种人脸图像处理方法、装置、计算机设备及介质
相关申请的交叉引用
本申请基于申请号为201911244817.2、申请日为2019年12月6日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及图像处理技术领域，具体涉及一种人脸图像处理方法、装置、计算机设备及介质。
背景技术
在智能终端(如智能手机等)中，拍摄已经成为一种不可或缺的应用功能，用户可以通过拍摄功能进行自拍等。
用户在使用智能终端进行拍摄时，往往会受到终端设备、环境光线以及拍摄目标等因素的影响，导致拍摄获取的人脸图像并不完美。人脸图像中一些小的瑕疵用户可以利用智能终端自带的修图软件进行修正，但对于对焦失败图像模糊、过曝或过暗的等人脸图像，部分智能终端自带的图像处理软件是无法完成优化的，需要通过专业的图像处理软件才可以进行优化。
发明内容
本申请提供一种人脸图像处理方法、装置、计算机设备及介质，实现对包括缺陷的人脸图像的自动优化处理。
第一方面，本申请实施例提供一种人脸图像处理方法，包括：获取目标用户的待优化人脸图像；从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像；根据所述参考人脸图像对所述待优化人脸图像进行优化处理。
第二方面，本申请实施例提供一种人脸图像处理装置，包括：待优化人脸图像获取模块，用于获取目标用户的待优化人脸图像；参考人脸图像获取模块，用于从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像；图像优化处理模块，用于根据所述参考人脸图像对所述待优化人脸图像进行优化处理。
第三方面，本申请实施例提供了一种计算机，包括：一个或多个处理器；存储装置，用于存储一个或多个程序；当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如本申请实施例任意所述的人脸图像处理方法。
第四方面，本申请实施例提供了一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现本申请实施例任意所述的人脸图像处理方法。
关于本申请的以上实施例和其他方面以及其实现方式，在附图说明、具体实施方式和 权利要求中提供更多说明。
附图说明
图1为本申请实施例提供的一种人脸图像处理方法的流程示意图；
图2为本申请实施例提供的一种人脸图像处理方法的流程示意图；
图3为本申请实施例提供的一种人脸图像处理装置的结构示意图；
图4为本申请实施例提供的一种计算机设备的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚明白，下文中将结合附图对本申请的实施例进行详细说明。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互任意组合。
在一个示例性实施方式中，图1为本申请实施例提供的一种人脸图像处理方法的流程示意图。该方法可以适用于智能终端对包括缺陷的人脸图像进行自动优化处理的情况。该方法可以由本申请提供的人脸图像处理装置执行，该人脸图像处理装置可以由软件和/或硬件实现，并集成在智能终端(典型的，各类智能手机、平板电脑或个人计算机等)上。
如图1所示，本申请提供的一种人脸图像处理方法，包括S110、S120及S130。
S110、获取目标用户的待优化人脸图像。
其中，目标用户即为使用智能终端获取人脸图像的用户。在一些示例中，目标用户可以是拥有智能终端解锁权限的用户。其中，解锁权限包括但不限于指纹解锁、人脸识别解锁及密码解锁等等。待优化人脸图像可以是存在缺陷的需要进行优化的人脸图像。缺陷可以是诸如对焦失败图像模糊、过曝、过暗、出现闭眼或脸型畸变等缺陷。这类缺陷无法通过智能终端拍照功能自行修复。
在本申请实施例中，智能终端可以通过拍照功能获取目标用户的人脸图像，其中，拍照功能包括自拍和非自拍功能。或者，智能终端还可以根据目标用户的指定或选定操作等获取目标用户的人脸图像。如将目标用户通过智能终端的相册、图库或其他应用APP(Application，应用程序)等指定的人脸图像作为目标用户的人脸图像，本申请实施例并不对智能终端获取目标用户的人脸图像的方式进行限定。
在本申请的一个实施例中，获取目标用户的待优化人脸图像，可以包括：获取目标用户的人脸图像，对所述人脸图像进行缺陷检测，并在确定所述人脸图像存在面部缺陷时，将所述人脸图像确定为所述待优化人脸图像。
在本申请实施例中，在获取到目标用户的人脸图像后，可以对人脸图像中的面部缺陷进行检测，并在根据检测结果确定人脸图像存在待修复的面部缺陷时，将存在面部缺陷的人脸图像作为目标用户的待优化人脸图像。
S120、从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像。
其中，所述参考人脸图像为所述目标用户进行人脸解锁时使用的解锁人脸图像，和/ 或所述目标用户存储的标准人脸图像。
其中，预设人脸数据库可以是针对目标用户预先建立的用于存储目标用户的解锁人脸图像和/或目标用户存储的标准人脸图像的数据库。解锁人脸图像可以是用于进行人脸识别解锁所涉及到的图像。示例性的，解锁人脸图像可以是目标用户通过智能终端进行人脸识别解锁时，智能终端采集的人脸图像，也可以是智能终端预先存储的用于对目标用户进行人脸识别解锁采集的图像进行对比匹配的标准人脸图像。或者，也还可以同时将采集的人脸图像和标准人脸图像作为解锁人脸图像，也即，可以用于实现人脸解锁的人脸图像均可以作为解锁人脸图像，本申请实施例并不对解锁人脸图像的获取方式进行限定。目标用户存储的标准人脸图像可以是目标用户通过拍照功能、下载功能或图片保存功能等预先获取的，可用于进行图像优化的人脸图像。例如，目标用户在本地相册中存储的已经经过图像优化处理的自拍照等，可以作为参考人脸图像。
可以理解的是，随着人脸识别技术的成熟及广泛应用，智能终端可以配置人脸识别解锁功能。而人脸识别解锁功能所使用的解锁人脸图像往往是清晰标准的人脸图像，因此，可以采用解锁人脸图像作为参考人脸图像。同时，目标用户在使用智能终端的过程中，会通过拍照功能、下载功能或图片保存功能等多种图像获取手段，保存个人的标准人脸图像。这些标准人像图像通常也是清晰标准的人脸图像，因此，也还可以将目标用户存储的标准人脸图像作为参考人脸图像。
S130、根据所述参考人脸图像对所述待优化人脸图像进行优化处理。
相应的，可以根据标准的参考人脸图像对待优化人脸图像进行优化处理。
由于解锁人脸图像和目标用户存储的标准人脸图像中不会出现诸如对焦失败图像模糊、过曝、过暗、出现闭眼或脸型畸变等缺陷，因此，采用解锁人脸图像和/或目标用户存储的标准人脸图像作为参考人脸图像对待优化人脸图像进行优化处理，可以对待优化人脸图像中诸如对焦失败图像模糊、过曝、过暗、出现闭眼或脸型畸变等缺陷进行修复。
本申请实施例通过获取目标用户的待优化人脸图像，并从预设人脸数据库获取与待优化人脸图像匹配的人脸图像作为参考人脸图像，以根据参考人脸图像对待优化人脸图像进行优化处理，解决现有智能终端无法对部分缺陷人脸图像进行优化的问题，实现对包括缺陷的人脸图像的自动优化处理。
在上述实施例的基础上，提出了上述实施例的变型实施例，在此需要说明的是，为了使描述简要，在变型实施例中仅描述与上述实施例的不同之处。
在一个示例中，在从预设面部数据库获取与所述待优化人脸图像匹配的参考人脸图像之前，可以包括：获取所述目标用户进行人脸解锁时采集的人脸图像作为所述解锁人脸图像；和/或，获取所述目标用户进行人脸解锁时用于与采集的人脸图像进行对比匹配的标准人脸图像作为所述解锁人脸图像；获取所述目标用户存储的标准人脸图像；根据所述解锁人脸图像和/或所述目标用户存储的标准人脸图像建立所述预设人脸数据库。
可以理解的是，由于人脸解锁时使用的标准人脸图像用于与目标用户进行人脸解锁时采集的人脸图像进行对比匹配，所以人脸解锁时使用的标准人脸图像不会包括诸如对焦失败图像模糊、过曝、过暗、出现闭眼或脸型畸变等缺陷，且人脸解锁时使用的标准人脸图像中人脸五官和人脸表情等都会满足智能终端预先设定标准需求。目标用户进行人脸解锁时采集的人脸图像是用于解锁的，通常情况下目标用户会注意保持面部特征的严谨性，以确定能够解锁成功，所以目标用户进行人脸解锁时采集的人脸图像一般也不会包括诸如对焦失败图像模糊、过曝、过暗、出现闭眼或脸型畸变等缺陷。因此，可以将目标用户进行人脸解锁时采集的人脸图像作为解锁人脸图像；和/或，将目标用户进行人脸解锁时用于与采集的人脸图像进行对比匹配的标准人脸图像作为解锁人脸图像。同时，还可以获取目标用户存储的标准人脸图像，如在本地相册或目标用户对应的云相册中获取其存储的标准人脸图像，并根据解锁人脸图像和/或目标用户存储的标准人脸图像建立对应的预设人脸数据库。
需要说明的是，目标用户的数量可以是一个，也可以是多个，只要在智能终端具有人脸识别解锁权限的用户均可以作为目标用户，本申请实施例对此并不进行限制。
在一个示例中，所述根据所述解锁人脸图像和/或所述目标用户存储的标准人脸图像建立所述预设人脸数据库，可以包括：根据人脸图像筛选条件对所述解锁人脸图像和/或所述目标用户存储的标准人脸图像进行筛选，得到人脸图像样本；所述人脸图像样本包括所述解锁人脸图像和/或所述目标用户存储的标准人脸图像及所述解锁人脸图像和/或所述目标用户存储的标准人脸图像的至少一个特征值；将所述人脸图像样本添加至所述预设人脸数据库。
其中，人脸图像筛选条件可以是用于对解锁人脸图像和/或目标用户存储的标准人脸图像进行筛选以获取高质量的人脸图像的条件。例如，人脸图像筛选条件可以是图像清晰、未发生闭眼或面部未被遮挡等。本申请实施例并不对人脸图像筛选条件的具体内容进行限定。
为了进一步保障预设人脸数据库中人脸图像的质量，可以对获取的解锁人脸图像和/或目标用户存储的标准人脸图像根据人脸图像筛选条件进行筛选。这是因为解锁人脸图像中的标准人脸图像和/或目标用户存储的标准人脸图像对应的角度或亮度等特征值可能并不唯一，如智能终端针对一个目标用户对应存储了不同角度的多个解锁人脸图像对应的标准人脸图像。并且鉴于解锁场景的可变性，每次解锁过程中，目标用户面部亮度、角度及面部情绪都不一致。或者，目标用户在智能终端存储了不同角度的多个标准人脸图像。因此，在获取到解锁人脸图像和/或目标用户存储的标准人脸图像后，可以根据人脸图像筛选条件进行筛选，得到高质量的人脸图像作为人脸图像样本。在人脸图像样本中，可以包括一个或多个解锁人脸图像及每个解锁人脸图像对应的至少一个特征值，和/或包括一个或多个目标用户存储的标准人脸图像及每个目标用户存储的标准人脸图像对应的至少一个特 征值。其中，特征值用于提示人脸图像特征，可以包括但不限于图像清晰度、角度值、亮度值、人脸表情、人脸五官及人脸轮廓等，本申请实施例并不对特征值的类型进行限定。相应的，获取到人脸图像样本后，即可将人脸图像样本添加至预设人脸数据库，以完成预设人脸数据库的建立。在一些示例中，人脸图像样本可以包括目标用户不同面部角度的多个人脸图像样本。
需要说明的是，智能终端在使用的过程中，可以一直获取解锁人脸图像和/或目标用户存储的标准人脸图像，因此，预设人脸数据库还可以按照设定周期(如一周等)根据智能终端最新获取的解锁人脸图像和/或目标用户存储的标准人脸图像对本地存储的解锁人脸图像和/或目标用户存储的标准人脸图像进行更新，以保证人脸图像的优化效果。
在一个示例中，所述特征值可以包括角度值；所述从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像，可以包括：根据所述待优化人脸图像的角度值，从预设人脸数据库获取与所述待优化人脸图像的角度值匹配的人脸图像作为所述参考人脸图像。
其中，角度值可以是以XYZ轴为基准的任意角度值，
在本申请实施例中，在一些示例中，从预设人脸数据库获取与待优化人脸图像匹配的参考人脸图像时，可以以人脸图像中的角度值为依据，将面部角度相近的人脸图像作为参考人脸图像。这样设置的好处是：待优化人脸图像的面部角度不唯一，而人脸图像也可以涉及到目标用户的多个面部角度。因此，根据待优化人脸图像的角度值，从预设人脸数据库获取与待优化人脸图像的角度值匹配的人脸图像作为参考人脸图像，可以保证人脸图像优化效果。
在一个具体的例子中，假设待优化人脸图像为目标用户的正面人脸图像，则可以获取目标用户正面面对智能终端时的解锁人脸图像和/或目标用户存储的正面的标准人脸图像作为参考人脸图像。假设待优化人脸图像为目标用户的左侧人脸图像，则可以获取目标用户左侧面对智能终端时的解锁人脸图像和/或目标用户存储的左侧的标准人脸图像作为参考人脸图像。根据角度值选择匹配解锁人脸图像作为参考人脸图像，可以有效保证参考人脸图像与待优化人脸图像的匹配度，从而进一步保证人脸图像的优化效果。
在一个示例中，所述根据所述参考人脸图像对所述待优化人脸图像进行优化处理，可以包括：提取所述参考人脸图像及所述待优化人脸图像的特征值；根据所述参考人脸图像的特征值对所述待优化人脸图像的特征值进行优化处理。
在本申请实施例中，在对待优化人脸图像进行优化处理时，可以分别提取参考人脸图像及待优化人脸图像的特征值，从而根据参考人脸图像的特征值对待优化人脸图像的特征值进行优化处理。
在一个示例中，所述特征值还可以包括图片清晰度、亮度值、人脸表情、人脸五官及人脸轮廓中的至少一种。相应的，所述根据所述参考人脸图像的特征值对所述待优化人脸图像的特征值进行优化处理，可以包括：根据所述参考人脸图像的图片清晰度对所述待优 化人脸图像的图片清晰度进行优化；根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度值进行优化；根据所述参考人脸图像的人脸表情对所述待优化人脸图像的人脸表情进行优化；根据所述参考人脸图像的人脸五官对所述待优化人脸图像的人脸五官进行优化；或，根据所述参考人脸图像的人脸轮廓对所述待优化人脸图像的人脸轮廓进行优化。
在一个示例中，所述根据所述参考人脸图像的图片清晰度对所述待优化人脸图像的图片清晰度进行优化，可以包括：在所述待优化人脸图像的图片清晰度满足第一人脸修复条件的情况下，根据所述参考人脸图像的图像清晰度对所述待优化人脸图像的图像清晰度进行修复；所述根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度进行优化；可以包括：在所述待优化人脸图像的亮度值满足第二人脸修复条件的情况下，根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度值进行修复；所述根据所述参考人脸图像的人脸表情对所述待优化人脸图像的人脸表情进行优化；可以包括：在所述待优化人脸图像的人脸表情满足第三人脸修复条件的情况下，根据所述参考人脸图像的人脸表情对所述待优化人脸图像的人脸表情进行修复；所述根据所述参考人脸图像的人脸五官对所述待优化人脸图像的人脸五官进行优化，可以包括：在所述待优化人脸图像的眼部特征满足第四人脸修复条件的情况下，根据所述参考人脸图像的眼部特征对所述待优化人脸图像的眼部特征进行修复；所述根据所述参考人脸图像的人脸轮廓对所述待优化人脸图像的人脸轮廓进行优化，可以包括：在所述待优化人脸图像的人脸轮廓满足第五人脸修复条件的情况下，根据所述参考人脸图像的人脸轮廓特征对所述待优化人脸图像的人脸轮廓特征进行修复。
其中，第一人脸修复条件可以是用于判定待优化人脸图像的图片清晰度是否满足修复优化的条件。示例性的，第一人脸修复条件可以是：待优化人脸图像的图片清晰度低于第一预设阈值。第一预设阈值可以根据实际需求设定，本申请实施例对此并不进行限制。或者，第一人脸修复条件还可以是：待优化人脸图像出现噪点或虚化等情况。第二人脸修复条件可以是用于判定待优化人脸图像的亮度值是否满足修复优化的条件。示例性的，第二人脸修复条件可以是：待优化人脸图像的亮度值低于第二预设阈值，或待优化人脸图像的亮度值高于第三预设阈值。第二预设阈值和第三预设阈值同样可以根据实际需求设定，本申请实施例对此并不进行限制。第三人脸修复条件可以是用于判定待优化人脸图像的人脸表情是否满足修复优化的条件。示例性的，第三人脸修复条件可以是：待优化人脸图像的人脸表情出现扭曲或没有微笑表情等。第四人脸修复条件可以是用于判定待优化人脸图像的人脸五官是否满足修复优化的条件。示例性的，第四人脸修复条件可以是：待优化人脸图像出现闭眼或半闭眼等情况。第五人脸修复条件可以是用于判定待优化人脸图像的人脸轮廓是否满足修复优化的条件。示例性的，第五人脸修复条件可以是：待优化人脸图像的人脸轮廓出现畸变等情况。
具体的，根据参考人脸图像的特征值对待优化人脸图像的特征值进行优化处理时，如果确定待优化人脸图像的图片清晰度满足第一人脸修复条件，如待优化人脸图像出现噪点 或虚化，或图片清晰度取值不满足需求时，可以根据参考人脸图像的图片清晰度对待优化人脸图像的图像清晰度进行修复，如将待优化人脸图像的图片清晰度设置为参考人脸图像的图片清晰度，并对待优化人脸图像进行降噪处理、虚化弥补或增强处理等，以实现对待优化人脸图像图片清晰度的优化。如果确定待优化人脸图像的亮度值满足第二人脸修复条件，如待优化人脸图像的亮度过高或亮度过低，可以根据参考人脸图像的亮度值对待优化人脸图像的亮度值进行修复，如将待优化人脸图像的亮度值设置为参考人脸图像的亮度值，以实现对待优化人脸图像明暗平衡调整。如果确定待优化人脸图像的人脸表情满足第三人脸修复条件，如待优化人脸图像的中人脸出现扭曲，或面部无微笑表情等，可以根据参考人脸图像的人脸表情对待优化人脸图像的人脸表情进行修复，如对待优化人脸图像添加参考人脸图像的面部微笑表情等，以实现对待优化人脸面部表情的调整。如果确定待优化人脸图像的眼部特征满足第四人脸修复条件，如待优化人脸图像出现闭眼或半闭眼情况时，可以根据参考人脸图像的眼部特征对待优化人脸图像的眼部特征进行修复，如根据参考人脸图像的眼部特征对待优化人脸图像的眼部特征进行调整等，以修复待优化人脸图像中的闭眼和半闭眼情况。如果确定待优化人脸图像的人脸轮廓满足第五人脸修复条件，如待优化人脸图像出现脸型畸变时，可以根据参考人脸图像的人脸轮廓特征对待优化人脸图像的人脸轮廓特征进行修复，如根据参考人脸图像的人脸轮廓特征对待优化人脸图像的人脸轮廓特征进行调整等，以修复待优化人脸图像中的脸型畸变情况。
图2为本申请实施例提供的一种人脸图像处理方法的流程示意图，在一个具体的例子中，如图2所示，目标用户在使用智能终端的过程中，可以反复采集目标用户进行人脸解锁时向智能终端输入的解锁人脸图像，和/或目标用户存储的人脸图像，然后对采集的人脸图像进行筛选，并记录筛选的人脸图像的图片清晰度、亮度值、角度值(XYZ轴)、人脸表情、人脸五官和脸型轮廓等特征值，以根据采集的人脸图像以及对应的特征值建立预设人脸数据库。当智能终端获取到目标用户的拍摄获取或指定的人脸图像时，可以对获取的人脸图像进行缺陷检测，并在确定人脸图像存在面部缺陷时，将该人脸图像作为待优化人脸图像。然后，智能终端可以从预设人脸数据库获取与待优化人脸图像的角度值匹配的人脸图像作为参考人脸图像，并提取待优化人脸图像中缺陷点所在位置以及参考人脸图像对应位置的特征值，以根据参考人脸图像对应位置的特征值对待优化人脸图像中缺陷点所在位置的特征值进行优化处理，进而实现对待优化人脸图像的缺陷点的优化，最后可以向目标用户输出优化处理后的图片。
本申请实施例通过获取目标用户的待优化人脸图像，并从预设人脸数据库获取与待优化人脸图像匹配的人脸图像作为参考人脸图像，并提取参考人脸图像及待优化人脸图像的特征值，以根据参考人脸图像的特征值对待优化人脸图像的特征值进行优化处理，解决现有智能终端无法对部分缺陷人脸图像进行优化的问题，实现对包括缺陷的人脸图像的自动优化处理。
本申请提供了一种人脸图像处理装置，图3为本申请实施例提供的一种人脸图像处理装置的结构示意图，如图3所示，本申请实施例中的人脸图像处理装置，可以集成在智能终端上。该装置包括：待优化人脸图像获取模块210、参考人脸图像获取模块220以及图像优化处理模块230，其中，
待优化人脸图像获取模块210，设置为获取目标用户的待优化人脸图像；
参考人脸图像获取模块220，设置为从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像；
图像优化处理模块230，设置为根据所述参考人脸图像对所述待优化人脸图像进行优化处理。
本申请实施例通过获取目标用户的待优化人脸图像，并从预设人脸数据库获取与待优化人脸图像匹配的人脸图像作为参考人脸图像，以根据参考人脸图像对待优化人脸图像进行优化处理，解决现有智能终端无法对部分缺陷人脸图像进行优化的问题，实现对包括缺陷的人脸图像的自动优化处理。
在一个示例中，所述参考人脸图像为所述目标用户进行人脸解锁时使用的解锁人脸图像，和/或所述目标用户存储的标准人脸图像；所述装置还包括：预设人脸数据库建立模块，设置为获取所述目标用户进行人脸解锁时采集的人脸图像作为所述解锁人脸图像；和/或，获取所述目标用户进行人脸解锁时用于与采集的人脸图像进行对比匹配的标准人脸图像作为所述解锁人脸图像；获取所述目标用户存储的标准人脸图像；根据所述解锁人脸图像和/或所述目标用户存储的标准人脸图像建立所述预设人脸数据库。
在一个示例中，预设人脸数据库建立模块，设置为根据人脸图像筛选条件对所述解锁人脸图像和/或所述目标用户存储的标准人脸图像进行筛选，得到人脸图像样本；所述人脸图像样本包括所述解锁人脸图像和/或所述目标用户存储的标准人脸图像及所述解锁人脸图像和/或所述目标用户存储的标准人脸图像的至少一个特征值；将所述人脸图像样本添加至所述预设人脸数据库。
在一个示例中，所述特征值包括角度值；参考人脸图像获取模块220，设置为根据所述待优化人脸图像的角度值，从预设人脸数据库获取与所述待优化人脸图像的角度值匹配的人脸图像作为所述参考人脸图像。
在一个示例中，图像优化处理模块230，设置为提取所述参考人脸图像及所述待优化人脸图像的特征值；根据所述参考人脸图像的特征值对所述待优化人脸图像的特征值进行优化处理。
在一个示例中，所述特征值还包括图片清晰度、亮度值、人脸表情、人脸五官及人脸轮廓中的至少一种；图像优化处理模块230，设置为根据所述参考人脸图像的图片清晰度对所述待优化人脸图像的图片清晰度进行优化；根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度值进行优化；根据所述参考人脸图像的人脸表情对所述待优化人脸图 像的人脸表情进行优化；根据所述参考人脸图像的人脸五官对所述待优化人脸图像的人脸五官进行优化；或，根据所述参考人脸图像的人脸轮廓对所述待优化人脸图像的人脸轮廓进行优化。
在一个示例中，图像优化处理模块230，设置为在所述待优化人脸图像的图片清晰度满足第一人脸修复条件的情况下，根据所述参考人脸图像的图像清晰度对所述待优化人脸图像的图像清晰度进行修复；在所述待优化人脸图像的亮度值满足第二人脸修复条件的情况下，根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度值进行修复；在所述待优化人脸图像的人脸表情满足第三人脸修复条件的情况下，根据所述参考人脸图像的人脸表情对所述待优化人脸图像的人脸表情进行修复；在所述待优化人脸图像的眼部特征满足第四人脸修复条件的情况下，根据所述参考人脸图像的眼部特征对所述待优化人脸图像的眼部特征进行修复；在所述待优化人脸图像的人脸轮廓满足第五人脸修复条件的情况下，根据所述参考人脸图像的人脸轮廓特征对所述待优化人脸图像的人脸轮廓特征进行修复。
上述人脸图像处理装置可执行本申请任意实施例所提供的人脸图像处理方法，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，可参见本申请任意实施例提供的人脸图像处理方法。
由于上述所介绍的人脸图像处理装置为可以执行本申请实施例中的人脸图像处理方法的装置，故而基于本申请实施例中所介绍的人脸图像处理方法，本领域所属技术人员能够了解本实施例的人脸图像处理装置的具体实施方式以及其各种变化形式，所以在此对于该人脸图像处理装置如何实现本申请实施例中的人脸图像处理方法不再详细介绍。只要本领域所属技术人员实施本申请实施例中人脸图像处理方法所采用的装置，都属于本申请所欲保护的范围。
本申请实施例提供了一种计算机设备，图4为本申请实施例提供的一种计算机设备的结构示意图，如图4所示，本申请提供的计算机设备，包括：一个或多个处理器31和存储装置32；该计算机设备的处理器31可以是一个或多个，图4中以一个处理器31为例；存储装置32用于存储一个或多个程序；所述一个或多个程序被所述一个或多个处理器31执行，使得所述一个或多个处理器31实现如本申请实施例中所述的人脸图像处理方法：获取目标用户的待优化人脸图像；从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像；根据所述参考人脸图像对所述待优化人脸图像进行优化处理。计算机设备典型的可以是任意类型的智能终端设备。
计算机设备中的处理器31、存储装置32可以通过总线或其他方式连接，图4中以通过总线连接为例。
存储装置32作为一种计算机可读存储介质，可设置为存储软件程序、计算机可执行程序以及模块，如本申请实施例所述人脸图像处理方法对应的程序指令/模块(例如，人脸图像处理装置中的待优化人脸图像获取模块210、参考人脸图像获取模块220以及图像优 化处理模块230)。存储装置32可包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据设备的使用所创建的数据等。此外，存储装置32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。在一些实例中，存储装置32可进一步包括相对于处理器31远程设置的存储器，这些远程存储器可以通过网络连接至计算机设备。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。
本申请实施例还提供一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现本申请实施例中任一所述的人脸图像处理方法：获取目标用户的待优化人脸图像；从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像；根据所述参考人脸图像对所述待优化人脸图像进行优化处理。
本申请实施例通过获取目标用户的待优化人脸图像，并从预设人脸数据库获取与待优化人脸图像匹配的人脸图像作为参考人脸图像，以根据参考人脸图像对待优化人脸图像进行优化处理，解决现有智能终端无法对部分缺陷人脸图像进行优化的问题，实现对包括缺陷的人脸图像的自动优化处理。
本申请实施例的计算机存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(Read Only Memory，ROM)、可擦式可编程只读存储器((Erasable Programmable Read Only Memory，EPROM)或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括——但不限于无线、电线、光缆、射频(Radio Frequency，RF)等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还 包括常规的过程式程序设计语言——诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
以上所述，仅为本申请的示例性实施例而已，并非用于限定本申请的保护范围。
本领域内的技术人员应明白，术语终端涵盖任何适合类型的无线用户设备，例如移动电话、便携数据处理装置、便携网络浏览器或车载移动台。
一般来说，本申请的多种实施例可以在硬件或专用电路、软件、逻辑或其任何组合中实现。例如，一些方面可以被实现在硬件中，而其它方面可以被实现在可以被控制器、微处理器或其它计算装置执行的固件或软件中，尽管本申请不限于此。
本申请的实施例可以通过移动装置的数据处理器执行计算机程序指令来实现，例如在处理器实体中，或者通过硬件，或者通过软件和硬件的组合。计算机程序指令可以是汇编指令、指令集架构(Instruction Set Architecture，ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码。
本申请附图中的任何逻辑流程的框图可以表示程序步骤，或者可以表示相互连接的逻辑电路、模块和功能，或者可以表示程序步骤与逻辑电路、模块和功能的组合。计算机程序可以存储在存储器上。存储器可以具有任何适合于本地技术环境的类型并且可以使用任何适合的数据存储技术实现，例如但不限于只读存储器(Read-Only Memory，ROM)、随机访问存储器(Random Access Memory，RAM)、光存储器装置和系统(数码多功能光碟(Digital Video Disc，DVD)或光盘(Compact Disk，CD))等。计算机可读介质可以包括非瞬时性存储介质。数据处理器可以是任何适合于本地技术环境的类型，例如但不限于通用计算机、专用计算机、微处理器、数字信号处理器(Digital Signal Processing，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑器件(Field-Programmable Gate Array，FGPA)以及基于多核处理器架构的处理器。

Claims (10)

  1. 一种人脸图像处理方法，包括：
    获取目标用户的待优化人脸图像；
    从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像；
    根据所述参考人脸图像对所述待优化人脸图像进行优化处理。
  2. 根据权利要求1所述的方法，其中，所述参考人脸图像为所述目标用户进行人脸解锁时使用的解锁人脸图像，和/或所述目标用户存储的标准人脸图像；
    在从预设面部数据库获取与所述待优化人脸图像匹配的参考人脸图像之前，包括：
    获取所述目标用户进行人脸解锁时采集的人脸图像作为所述解锁人脸图像；和/或
    获取所述目标用户进行人脸解锁时用于与采集的人脸图像进行对比匹配的标准人脸图像作为所述解锁人脸图像；
    获取所述目标用户存储的标准人脸图像；
    根据所述解锁人脸图像和/或所述目标用户存储的标准人脸图像建立所述预设人脸数据库。
  3. 根据权利要求2所述的方法，其中，所述根据所述解锁人脸图像和/或所述目标用户存储的标准人脸图像建立所述预设人脸数据库，包括：
    根据人脸图像筛选条件对所述解锁人脸图像和/或所述目标用户存储的标准人脸图像进行筛选，得到人脸图像样本；所述人脸图像样本包括所述解锁人脸图像和/或所述目标用户存储的标准人脸图像及所述解锁人脸图像和/或所述目标用户存储的标准人脸图像的至少一个特征值；
    将所述人脸图像样本添加至所述预设人脸数据库。
  4. 根据权利要求3所述的方法，其中，所述特征值包括角度值；
    所述从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像，包括：
    根据所述待优化人脸图像的角度值，从预设人脸数据库获取与所述待优化人脸图像的角度值匹配的人脸图像作为所述参考人脸图像。
  5. 根据权利要求4所述的方法，其中，所述根据所述参考人脸图像对所述待优化人脸图像进行优化处理，包括：
    提取所述参考人脸图像及所述待优化人脸图像的特征值；
    根据所述参考人脸图像的特征值对所述待优化人脸图像的特征值进行优化处理。
  6. 根据权利要求5所述的方法，其中，所述特征值还包括图片清晰度、亮度值、人脸表情、人脸五官及人脸轮廓中的至少一种；
    所述根据所述参考人脸图像的特征值对所述待优化人脸图像的特征值进行优化处理，包括：
    根据所述参考人脸图像的图片清晰度对所述待优化人脸图像的图片清晰度进行优化；
    根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度值进行优化；
    根据所述参考人脸图像的人脸表情对所述待优化人脸图像的人脸表情进行优化；
    根据所述参考人脸图像的人脸五官对所述待优化人脸图像的人脸五官进行优化；或
    根据所述参考人脸图像的人脸轮廓对所述待优化人脸图像的人脸轮廓进行优化。
  7. 根据权利要求6所述的方法，其中，所述根据所述参考人脸图像的图片清晰度对所述待优化人脸图像的图片清晰度进行优化，包括：
    在所述待优化人脸图像的图片清晰度满足第一人脸修复条件的情况下，根据所述参考人脸图像的图像清晰度对所述待优化人脸图像的图像清晰度进行修复；
    所述根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度进行优化；包括：
    在所述待优化人脸图像的亮度值满足第二人脸修复条件的情况下，根据所述参考人脸图像的亮度值对所述待优化人脸图像的亮度值进行修复；
    所述根据所述参考人脸图像的人脸表情对所述待优化人脸图像的人脸表情进行优化；包括：
    在所述待优化人脸图像的人脸表情满足第三人脸修复条件的情况下，根据所述参考人脸图像的人脸表情对所述待优化人脸图像的人脸表情进行修复；
    所述根据所述参考人脸图像的人脸五官对所述待优化人脸图像的人脸五官进行优化，包括：
    在所述待优化人脸图像的眼部特征满足第四人脸修复条件的情况下，根据所述参考人脸图像的眼部特征对所述待优化人脸图像的眼部特征进行修复；
    所述根据所述参考人脸图像的人脸轮廓对所述待优化人脸图像的人脸轮廓进行优化，包括：
    在所述待优化人脸图像的人脸轮廓满足第五人脸修复条件的情况下，根据所述参考人脸图像的人脸轮廓特征对所述待优化人脸图像的人脸轮廓特征进行修复。
  8. 一种人脸图像处理装置，包括：
    待优化人脸图像获取模块，用于获取目标用户的待优化人脸图像；
    参考人脸图像获取模块，用于从预设人脸数据库获取与所述待优化人脸图像匹配的参考人脸图像；
    图像优化处理模块，用于根据所述参考人脸图像对所述待优化人脸图像进行优化处理。
  9. 一种计算机设备，包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序；
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-7中任一所述的人脸图像处理方法。
  10. 一种计算机存储介质，其上存储有计算机程序，其中，该程序被处理器执行时实 现如权利要求1-7中任一所述的人脸图像处理方法。
PCT/CN2020/116526 2019-12-06 2020-09-21 一种人脸图像处理方法、装置、计算机设备及介质 WO2021109680A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/610,315 US20220245962A1 (en) 2019-12-06 2020-09-21 Facial image processing method and apparatus, computer device, and medium
EP20896073.2A EP3958169A4 (en) 2019-12-06 2020-09-21 FACE IMAGE PROCESSING METHOD AND APPARATUS, COMPUTER DEVICE AND MEDIA

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911244817.2 2019-12-06
CN201911244817.2A CN112926369A (zh) 2019-12-06 2019-12-06 一种人脸图像处理方法、装置、计算机设备及介质

Publications (1)

Publication Number Publication Date
WO2021109680A1 true WO2021109680A1 (zh) 2021-06-10

Family

ID=76161948

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/116526 WO2021109680A1 (zh) 2019-12-06 2020-09-21 一种人脸图像处理方法、装置、计算机设备及介质

Country Status (4)

Country Link
US (1) US20220245962A1 (zh)
EP (1) EP3958169A4 (zh)
CN (1) CN112926369A (zh)
WO (1) WO2021109680A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113486749A (zh) * 2021-06-28 2021-10-08 中星电子股份有限公司 图像数据收集方法、装置、电子设备和计算机可读介质
CN115908119B (zh) * 2023-01-05 2023-06-06 广州佰锐网络科技有限公司 基于人工智能的人脸图像美颜处理方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8811683B2 (en) * 2011-06-02 2014-08-19 Apple Inc. Automatic red-eye repair using multiple recognition channels
CN109360170A (zh) * 2018-10-24 2019-02-19 北京工商大学 基于高级特征的人脸修复方法
CN109919830A (zh) * 2019-01-23 2019-06-21 复旦大学 一种基于美学评价的带参考人眼图像修复方法
CN111105369A (zh) * 2019-12-09 2020-05-05 Oppo广东移动通信有限公司 图像处理方法、图像处理装置、电子设备和可读存储介质
CN111553864A (zh) * 2020-04-30 2020-08-18 深圳市商汤科技有限公司 图像修复方法及装置、电子设备和存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109919866B (zh) * 2019-02-26 2023-12-01 Oppo广东移动通信有限公司 图像处理方法、装置、介质及电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8811683B2 (en) * 2011-06-02 2014-08-19 Apple Inc. Automatic red-eye repair using multiple recognition channels
CN109360170A (zh) * 2018-10-24 2019-02-19 北京工商大学 基于高级特征的人脸修复方法
CN109919830A (zh) * 2019-01-23 2019-06-21 复旦大学 一种基于美学评价的带参考人眼图像修复方法
CN111105369A (zh) * 2019-12-09 2020-05-05 Oppo广东移动通信有限公司 图像处理方法、图像处理装置、电子设备和可读存储介质
CN111553864A (zh) * 2020-04-30 2020-08-18 深圳市商汤科技有限公司 图像修复方法及装置、电子设备和存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3958169A4 *

Also Published As

Publication number Publication date
US20220245962A1 (en) 2022-08-04
EP3958169A1 (en) 2022-02-23
CN112926369A (zh) 2021-06-08
EP3958169A4 (en) 2022-07-27

Similar Documents

Publication Publication Date Title
US10949952B2 (en) Performing detail enhancement on a target in a denoised image
US8405736B2 (en) Face detection using orientation sensor data
US9626745B2 (en) Temporal multi-band noise reduction
US8503818B2 (en) Eye defect detection in international standards organization images
US10275584B2 (en) Method and system for unlocking mobile terminal on the basis of a high-quality eyeprint image
WO2022062346A1 (zh) 图像增强方法、装置及电子设备
WO2017096857A1 (zh) 相机拍摄参数调整方法及装置
US11425309B2 (en) Image capture method and apparatus
WO2021109680A1 (zh) 一种人脸图像处理方法、装置、计算机设备及介质
EP3644599B1 (en) Video processing method and apparatus, electronic device, and storage medium
CN113992850B (zh) 基于isp的图像处理方法及装置、存储介质和摄像设备
CN111491106B (zh) 拍摄图像的处理方法、装置、移动终端及存储介质
US10880742B2 (en) Iris recognition workflow
WO2021008205A1 (zh) 图像处理
WO2023137956A1 (zh) 图像处理方法、装置、电子设备及存储介质
CN112532891A (zh) 拍照方法及装置
WO2019129041A1 (zh) 一种亮度调节方法、装置、终端及计算机可读存储介质
CN113158773B (zh) 一种活体检测模型的训练方法及训练装置
US20220309627A1 (en) Face image straight line processing method, terminal device and storage medium
JP6132343B2 (ja) 画像処理装置、画像処理方法、及びプログラム
US8629925B2 (en) Image processing apparatus, image processing method, and computer program
WO2018214900A1 (zh) 存储装置、移动终端及其图像处理方法
CN111798389B (zh) 自适应图像增强方法及装置
CN112104812B (zh) 一种采集图片的方法和装置
CN103905707A (zh) 一种摄像装置的控制方法及装置

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: 20896073

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020896073

Country of ref document: EP

Effective date: 20211117

NENP Non-entry into the national phase

Ref country code: DE