Facial image processing method and apparatus, electronic device and computer readable storage medium
地域：
Beijing
摘要
A facial image processing method and apparatus, an electronic device and a computer readable storage medium. The facial image processing method comprises: acquiring an image to be processed; detecting whether a facial image exists in the image to be processed; in response to the detected facial image, carrying out a first processing on the facial image to obtain a first image; and obtaining depth information, and adding the depth information to the first image to obtain a processed image. According to the method, the image depth information can be added after the image is processed, such that the image has a stereoscopic impression and the user operation is simplified.
說明書
This application is a continuation of International Patent Application No. PCT/CN2019/073071, filed on Jan. 25, 2019, which claims priority to Chinese Patent Application No. 201810609994.5, titled “FACIAL IMAGE PROCESSING METHOD AND APPARATUS, ELECTRONIC DEVICE AND COMPUTER READABLE STORAGE MEDIUM”, filed on Jun. 13, 2018 with the Chinese Patent Office, both of which are incorporated herein by reference in their entireties.
The present disclosure relates to the field of image processing, and in particular to a face image processing method, a face image processing apparatus, an electronic device, and a computer readable storage medium.
With the development of computer technologies, smart terminals are widely used in more and more areas. For example, the smart terminal can be used to listen to music, play games, chat online, and take pictures. Especially, the cameras of the smart terminals have more than 10 million pixels, with high definition and the camera effect comparable to professional cameras.
At present, a smart terminal, when used to take pictures, not only can perform the function of a traditional camera by using the camera software built-in at the factory, but also can achieve additional photographic effects by using applications (abbreviated as APP) that is downloaded from the network, such as the APPs that can realize dark light detection, beauty camera, and super pixel functions. The smart terminals can achieve beauty camera functions such as skin tone adjustment, skin grinding, big eyes effect and face-lifting and other beauty effects, and can apply the same degree of beauty effect on faces that are identified in an image.
權(quán)利要求
The invention claimed is:1. A face image processing method, comprising:obtaining a to-be-processed image; determining if a face image is detected in the to-be-processed image; in response to a detected face image, performing first processing on the face image to obtain a first image; obtaining feature points of the first image; determining a first standard template among at least two preset standard templates based at least in part on the feature points of the first image, wherein the at least two preset standard templates comprise a plurality of standard templates corresponding to a plurality of face images captured at different angles, each of the plurality of standard templates comprises feature points and their respective depth information, the first standard template is divided in a same manner as the first image is divided, each feature point in the first standard template has a corresponding feature point in the first image, and differences between coordinates of each feature point in the first standard template and coordinates of the corresponding feature point in the first image satisfy a preset relationship; determining depth information of the feature points of the first image based on depth information comprised in the first standard template; and adding the determined depth information to the first image to obtain a processed image. 2. The face image processing method according to claim 1 , wherein before the performing first processing on the face image, the method further comprises:determining a face image region on which the first processing is to be performed. 3. The face image processing method according to claim 2 , wherein the determining a face image region on which the first processing is to be performed comprises:selecting a face region that is to be deleted; deleting the selected face region; and determining a remaining face region after the deleting is performed as the face image region on which the first processing is to be performed. 4. The face image processing method according to claim 1 , wherein the performing first processing on the face image to obtain a first image comprises:performing low-pass filtering on the face image, to obtain a low frequency component of the face image; subtracting the low frequency component from the face image, to obtain a high frequency component of the face image; and amplifying the high frequency component to obtain the first image. 5. The face image processing method according to claim 4 , wherein the low-pass filtering comprises:calculating an average value of a value of a current pixel and values of adjacent pixels surrounding the current pixel in the face image, and using the average value as the value of the current pixel. 6. The face image processing method according to claim 5 , wherein the calculating the average value comprises:obtaining a smoothing matrix, and convolving the value of the current pixel and the values of the adjacent pixels surrounding the current pixel in the face image with the smoothing matrix, to obtain the average value. 7. The face image processing method according to claim 6 , whereinthe smoothing matrix is a two-dimensional matrix, and elements in the two-dimensional matrix are arranged in a manner that values of the elements decreases from a center to a periphery of the two-dimensional matrix. 8. A face image processing apparatus, comprising:at least one processor; and at least one memory communicatively coupled to the at least one processor and storing instructions that upon execution by the at least one processor cause the face image processing apparatus to perform operations comprising: obtaining a to-be-processed image; determining if a face image is detected in the to-be-processed image; in response to a detected face image, performing first processing on the face image, to obtain a first image; obtaining feature points of the first image; determining a first standard template among at least two preset standard templates based at least in part on the feature points of the first image, wherein the at least two preset standard templates comprise a plurality of standard templates corresponding to a plurality of face images captured at different angles, each of the plurality of standard templates comprises feature points and their respective depth information, the first standard template is divided in a same manner as the first image is divided, each feature point in the first standard template has a corresponding feature point in the first image, and differences between coordinates of each feature point in the first standard template and coordinates of the corresponding feature point in the first image satisfy a preset relationship; determining depth information of the feature points of the first image based on depth information comprised in the first standard template; and adding the determined depth information to the first image to obtain a processed image. 9. The face image processing apparatus according to claim 8 , wherein before performing first processing on the face image, the at least one memory further stores instructions that upon execution by the at least one processor cause the face image processing apparatus to further perform operations comprising:determining a face image region on which the first processing is to be performed. 10. The face image processing apparatus according to claim 9 , wherein the determining a face image region on which the first processing is to be performed comprises:selecting a face region that is to be deleted; deleting the selected face region; and determining a remaining face region after the deleting is performed as the face image region on which the first processing is to be performed. 11. The face image processing apparatus according to claim 8 , wherein the performing first processing on the face image, to obtain a first image comprises:performing low-pass filtering on the face image, to obtain a low frequency component of the face image; subtracting the low frequency component from the face image, to obtain a high frequency component of the face image; and amplifying the high frequency component to obtain the first image. 12. The face image processing apparatus according to claim 11 , wherein the low-pass filtering comprises:calculating an average value of a value of a current pixel and values of adjacent pixels surrounding the current pixel in the face image, and using the average value as the value of the current pixel. 13. The face image processing apparatus according to claim 12 , wherein the calculating the average value comprises:obtaining a smoothing matrix, and convolving the value of the current pixel and the values of the adjacent pixels surrounding the current pixel in the face image with the smoothing matrix, to obtain the average value. 14. The face image processing apparatus according to claim 13 , whereinthe smoothing matrix is a two-dimensional matrix, and elements in the two-dimensional matrix are arranged in a manner that values of the elements decreases from a center to a periphery of the two-dimensional matrix. 15. A non-transient computer-readable storage medium, storing computer instructions, the computer instructions are configured to cause a computer to perform operations comprising:obtaining a to-be-processed image; determining whether a face image is detected in the to-be-processed image; in response to a detected face image, performing first processing on the face image to obtain a first image; obtaining feature points of the first image; determining a first standard template among at least two preset standard templates based at least in part on the feature points of the first image, wherein the at least two preset standard templates comprise a plurality of standard templates corresponding to a plurality of face images captured at different angles, each of the plurality of standard templates comprises feature points and their respective depth information, the first standard template is divided in a same manner as the first image is divided, each feature point in the first standard template has a corresponding feature point in the first image, and differences between coordinates of each feature point in the first standard template and coordinates of the corresponding feature point in the first image satisfy a preset relationship; determining depth information of the feature points of the first image based on depth information comprised in the first standard template; and adding the determined depth information to the first image to obtain a processed image. 16. The non-transient computer-readable storage medium of claim 15 , wherein before the performing first processing on the face image, the operations further comprise:determining a face image region on which the first processing is to be performed. 17. The non-transient computer-readable storage medium of claim 16 , wherein the determining a face image region on which the first processing is to be performed further comprises:selecting a face region that is to be deleted; deleting the selected face region; and determining a remaining face region after the deleting is performed as the face image region on which the first processing is to be performed. 18. The non-transient computer-readable storage medium of claim 15 , wherein the performing first processing on the face image to obtain a first image further comprises:performing low-pass filtering on the face image, to obtain a low frequency component of the face image; subtracting the low frequency component from the face image, to obtain a high frequency component of the face image; and amplifying the high frequency component to obtain the first image. 19. The non-transient computer-readable storage medium of claim 15 , wherein the operations further comprise:calculating an average value of a value of a current pixel and values of adjacent pixels surrounding the current pixel in the face image, and using the average value as the value of the current pixel; and obtaining a smoothing matrix, and convolving the value of the current pixel and the values of the adjacent pixels surrounding the current pixel in the face image with the smoothing matrix to obtain the average value. 20. The non-transient computer-readable storage medium of claim 19 , wherein the smoothing matrix is a two-dimensional matrix, and elements in the two-dimensional matrix are arranged in a manner that values of the elements decreases from a center to a periphery of the two-dimensional matrix.
意見反饋
使用該功能遇到問題