WO2020151456A1 - 动物脸部的图像处理方法和装置 - Google Patents

动物脸部的图像处理方法和装置 Download PDF

Info

Publication number
WO2020151456A1
WO2020151456A1 PCT/CN2019/129119 CN2019129119W WO2020151456A1 WO 2020151456 A1 WO2020151456 A1 WO 2020151456A1 CN 2019129119 W CN2019129119 W CN 2019129119W WO 2020151456 A1 WO2020151456 A1 WO 2020151456A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
animal
face
processing
image processing
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/CN2019/129119
Other languages
English (en)
French (fr)
Inventor
王沈韬
杨辉
高乐
李小奇
沈言浩
倪光耀
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.)
Beijing ByteDance Network Technology Co Ltd
Original Assignee
Beijing ByteDance Network Technology 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 Beijing ByteDance Network Technology Co Ltd filed Critical Beijing ByteDance Network Technology Co Ltd
Priority to US17/425,579 priority Critical patent/US20220101645A1/en
Priority to JP2021542562A priority patent/JP7383714B2/ja
Priority to GB2110696.8A priority patent/GB2595094B/en
Publication of WO2020151456A1 publication Critical patent/WO2020151456A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—Two-dimensional [2D] image generation
    • G06T11/10—Texturing; Colouring; Generation of textures or colours
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • 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
    • 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
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning

Definitions

  • the present disclosure relates to the field of image processing, and in particular to an image processing method, device, electronic device, and computer-readable storage medium of an animal face.
  • smart terminals can be used to listen to music, play games, chat online, and take photos.
  • the camera technology of the smart terminal the camera pixel has reached more than 10 million pixels, with higher definition and the camera effect comparable to professional cameras.
  • APP Application, referred to as: APP
  • apps that can realize dark light detection, beauty camera, and super pixel functions.
  • the beauty functions of smart terminals usually include skin color adjustment, skin grinding, big eyes and face-lifting and other beauty processing effects, which can perform a certain degree of beauty processing on the recognized face in the image.
  • an embodiment of the present disclosure provides an image processing method of an animal face, including: acquiring an input image, the image including at least one animal; identifying the face image of the animal in the image; reading image processing
  • the configuration file of the configuration file includes the image processing parameters; the facial image of the animal is processed according to the image processing parameters to obtain the processed animal facial image.
  • the obtaining an input image, the image including at least one animal includes: obtaining a video image, the video image includes a plurality of video frames, and at least one of the plurality of video frames includes at least one animal.
  • the recognizing the facial image of the animal in the image includes recognizing the facial image of the animal in the current video frame.
  • the recognizing the facial image of the animal in the image includes: recognizing the facial area of the animal in the image, and detecting key points of the facial image of the animal in the facial area .
  • the read image processing configuration file includes: reading the image processing configuration file, the configuration file includes the image processing type Parameters and location parameters, wherein the location parameters are associated with the key points.
  • processing the facial image of the animal according to the image processing parameters to obtain the processed animal facial image includes: processing the type parameters according to the image and the face of the animal For the key points of the image, the face image of the animal is processed to obtain the processed animal face image.
  • said processing the facial image of the animal according to the type parameters of the image processing and the key points of the facial image of the animal to obtain the processed animal facial image includes:
  • the type parameter of image processing is texture processing to obtain the material required for the image processing; according to the key points of the animal’s face image, the material is rendered to a predetermined position of the animal’s face image to obtain the Material animal face images.
  • said processing the facial image of the animal according to the type parameters of the image processing and the key points of the facial image of the animal to obtain the processed animal facial image includes:
  • the type parameter of the image processing is the deformation type, and the key points related to the deformation type are acquired; the key points related to the deformation type are moved to a predetermined position to obtain the deformed animal face image.
  • the recognizing the facial image of the animal in the image includes: recognizing the facial images of a plurality of animals in the image, and assigning an animal face ID to the facial image of each animal according to the recognition order .
  • the reading the configuration file of image processing includes: reading the configuration file of image processing, and obtaining the information related to the animal face according to the animal face ID.
  • the image processing parameter corresponding to the part ID includes: reading the configuration file of image processing, and obtaining the information related to the animal face according to the animal face ID.
  • an image processing device for an animal face including:
  • An image acquisition module for acquiring an input image, the image including at least one animal
  • An animal face recognition module for recognizing the face image of the animal in the image
  • a configuration file reading module for reading a configuration file of image processing, the configuration file including the image processing parameters
  • the image processing module is configured to process the facial image of the animal according to the image processing parameters to obtain a processed facial image of the animal.
  • the image acquisition module further includes:
  • the video image acquisition module is configured to acquire a video image, the video image includes a plurality of video frames, and at least one video frame of the plurality of video frames includes at least one animal.
  • animal face recognition module further includes:
  • the video animal face recognition module is used to recognize the face image of the animal in the current video frame.
  • animal face recognition module further includes:
  • the key point detection module is used to identify the face area of the animal in the image, and detect the key point of the face image of the animal in the face area.
  • configuration file reading module includes:
  • the first configuration file reading module is configured to read an image processing configuration file, the configuration file includes the image processing type parameter and position parameter, wherein the position parameter is associated with the key point.
  • the image processing module further includes:
  • the first image processing module is configured to process the facial image of the animal according to the type parameters of the image processing and the key points of the facial image of the animal to obtain a processed facial image of the animal.
  • the first image processing module further includes:
  • the material acquisition module is used to acquire the material required for the image processing when the type parameter of the image processing is texture processing;
  • the texture processing module is used to render the material to a predetermined position of the animal face image according to the key points of the animal's face image to obtain the animal face image with the material.
  • the first image processing module further includes:
  • a key point acquisition module configured to acquire key points related to the deformation type when the type parameter of the image processing is a deformation type
  • the deformation processing module is used to move the key points related to the deformation type to a predetermined position to obtain a deformed animal face image.
  • animal face recognition module further includes:
  • the ID assignment module is used to identify the facial images of multiple animals in the image, and assign an animal facial ID to the facial images of each animal according to the recognition order.
  • the configuration file reading module further includes: a processing parameter acquisition module for reading a configuration file for image processing, and acquiring image processing parameters corresponding to the animal face ID according to the animal face ID.
  • embodiments of the present disclosure provide an electronic device, including: at least one processor; and,
  • the device can execute any one of the animal face image processing methods described in the first aspect.
  • embodiments of the present disclosure provide a non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute the aforementioned first aspect Any one of said animal face image processing methods.
  • the embodiments of the present disclosure provide an image processing method, device, electronic device, and computer-readable storage medium of an animal face.
  • the image processing method of the animal face includes: acquiring an input image, the image includes at least one animal; identifying the face image of the animal in the image; reading a configuration file for image processing, in the configuration file Including the image processing parameters; according to the image processing parameters, processing the animal's facial image to obtain the processed animal's facial image.
  • the embodiment of the present disclosure recognizes the animal face image in the image and processes the animal face image according to the configuration of the image processing in the configuration file to obtain different special effects, which solves the need for post-production in the prior art. The problem of inflexible production of special effects when processing animal face images.
  • FIG. 1 is a flowchart of Embodiment 1 of an image processing method for an animal face provided by an embodiment of the disclosure
  • FIG. 2a is a schematic diagram of key points of a cat face used in an image processing method of an animal face provided by an embodiment of the disclosure
  • 2b is a schematic diagram of the key points of the dog face used in the image processing method of the animal face provided by the embodiment of the disclosure;
  • Embodiment 3 is a flowchart of Embodiment 2 of the method for processing an image of an animal face provided by the disclosed embodiment
  • Embodiment 4 is a schematic structural diagram of Embodiment 1 of an image processing apparatus for an animal face provided by an embodiment of the disclosure
  • FIG. 5 is a schematic diagram of the structure of the animal face recognition module and the configuration file reading module in the second embodiment of the image processing device for the animal face provided by the embodiments of the disclosure.
  • Fig. 6 is a schematic structural diagram of an electronic device provided according to an embodiment of the present disclosure.
  • Embodiment 1 is a flowchart of Embodiment 1 of an image processing method for an animal face provided by an embodiment of the disclosure.
  • the image processing method for an animal face provided in this embodiment can be executed by an image processing device for an animal face.
  • the image processing device for the animal face can be implemented as software, or as a combination of software and hardware.
  • the image processing device for the animal face can be integrated in a certain device in the image processing system, such as an image processing server or an image processing terminal In the device. As shown in Figure 1, the method includes the following steps:
  • Step S101 acquiring an input image, the image including at least one animal
  • the obtaining of the input image includes obtaining the input image from a local storage space or obtaining an input image from a network storage space. No matter where the input image is obtained from, it is first necessary to obtain the storage address of the input image, and then The input image is obtained from the storage address, and the input image may be a video image or a picture, or a picture with dynamic effects, which will not be repeated here.
  • the obtaining of the input image includes obtaining a video image, the video image includes a plurality of video frames, and at least one video frame of the plurality of video frames includes at least one animal.
  • the input video image can be obtained by an image sensor, which refers to various devices that can collect images, and typical image sensors are video cameras, cameras, cameras, etc.
  • the image sensor may be a camera on a mobile terminal, such as a front or rear camera on a smart phone, and the video image collected by the camera may be directly displayed on the display screen of the phone.
  • the input image includes at least one animal, and the animal image is the basis for recognizing animal facial images.
  • the input image is a picture
  • the picture includes at least one animal image
  • the input image is a video
  • at least one of the video frames in the input image includes at least one animal image.
  • Step S102 Recognizing the facial image of the animal in the image
  • the recognizing the facial image of the animal in the image includes: recognizing the facial region of the animal in the image, and detecting the facial image of the animal in the facial region key point. Recognizing the face area of the animal in the image can be a rough identification of the image area with the face of the animal in the image, and selecting the area in a frame so as to be further in the face area. Check key points.
  • recognizing the face area of an animal you can use a classifier to classify the face of the animal in the image to get the face area of the animal. Specifically, you can use multiple classification methods, first perform a rough classification and then a rough classification of the image Perform fine classification to get the final classification result.
  • the animal face image can be grayed first, the image is converted into a gray image, and then the first feature of the gray image is extracted, and the first feature is a plurality of shapes and sizes on the image
  • the first feature is a plurality of shapes and sizes on the image
  • the difference between the sum of the gray values of all pixels in the same rectangle, the first feature reflects the local gray change of the image.
  • Use the first feature of the image in the training set to train a basic classifier, and combine the first N basic classifiers with the best classification ability to obtain a first classifier.
  • the weight value of the sample indicates how difficult it is to be correctly classified. At the beginning, each sample corresponds to the same weight value.
  • a basic classifier h1 For samples that are classified by h1, increase the corresponding weight value. For samples that are paired by h1, decrease the weight value. This makes the new sample distribution more prominent for the wrong samples, making the next step In the round of training, the basic classifier can focus more on these wrong samples.
  • the weight value of the basic classifier indicates the strength of its classification ability. The smaller the number of misclassified samples, the greater the weight of the basic classifier, to indicate the better its classification ability.
  • the weak classifier h1 is trained here to obtain the basic classifier h2 and its weights, and so on, after N rounds of iteration, N basic classifiers h1, h2, h3,..., hN, and N corresponding weight values, and finally h1, h2, h3,..., hN are accumulated according to the weight values to form the first classifier.
  • the training set includes positive samples and negative samples, where the positive samples include animal facial images, and the negative samples do not include animal facial images, wherein the animal facial images are an animal, such as All are dog facial images or all cat facial images, and a separate first classifier can be trained separately for each animal. Use the first classifier to classify the image to obtain the first classification result.
  • the classification result of the first classifier is continued to be classified by the second classifier, and the second classifier can use the second feature to classify the animal face image.
  • the second feature can be a directional gradient histogram feature
  • the second classifier can be a support vector machine classifier. Obtain the directional gradient histogram feature of the image in the classification result of the first classifier, and perform secondary classification on the image in the classification result through the support vector machine classifier to obtain the final classification result, that is, the image containing the specific animal face
  • the samples that are classified by the second classifier can also be put into the negative samples of the first classifier, and their weight values are adjusted to provide feedback for the adjustment of the first classifier.
  • the face area of the animal in the image is obtained, and the key points of the animal face are further detected in this area.
  • This detection can be realized by a deep learning method.
  • the location of the key points on the animal face can be predicted in the area first, and then refined positioning is performed according to different areas on the animal face.
  • the different areas of can be determined according to the organs of the animal’s face, such as eye area, nose area, mouth area, etc.
  • the key points of the contour of the face are detected, and these key points are combined to form a complete key point.
  • Typical animal face key points are shown in Figures 2a and 2b, where 2a is a cat face with 82 key points, 2b is a dog face with 90 key points, and the key points with digital marks are semantic points, such as cat face
  • the point marked with 0 in the middle is the root of the left lower ear, and the point marked with 8 is the chin point, and the numbers 1-7 have no specific meaning. In fact, the equal points between 0-8 are close to the edge of the contour. Other key points are similar and will not be repeated here. After identifying these keys, the subsequent image processing has a basis.
  • the input image is a video image
  • the recognizing the facial image of the animal in the image includes recognizing the facial image of the animal in the current video frame.
  • each frame of image is used as an input image to identify the key points of the animal's face image through the above recognition method, so that even if the animal's face moves in the video, it can be dynamically identified and tracked Face images of animals.
  • animal face recognition methods are only examples. In fact, any method that can recognize animal face images and detect key points of animal faces can be applied to the technical solutions of the present disclosure. There is no restriction on this.
  • Step S103 reading an image processing configuration file, the configuration file including the image processing parameters
  • the configuration file includes type parameters and location parameters of the image processing.
  • the type parameter determines the type of image processing.
  • the type can be a texture processing type or a deformation processing type; wherein the position parameter identifies the position where image processing is required.
  • the position parameter It can be the absolute position of the image, such as the UV coordinates of the image or various other coordinates.
  • the position parameter can be associated with the key points identified in step S102, because each key point is associated with the animal's face , So you can achieve the image processing effect moving with the movement of the animal's face.
  • the position parameter when the position parameter is associated with the key point, the position parameter describes which animal face key points are associated with the display position of the image processing material. By default, all key points can be associated, or you can set to follow Several key points.
  • the configuration file also includes the positional relationship between the material and the key point parameter "point", "point” can include two sets of associated points, "point0” means the first set of associated points, and "point1" means the second set .
  • point describes the position of the anchor point in the camera, which is obtained by calculating the weighted average of several groups of key points and their weights;
  • point can include any group of related points, and is not limited to two groups.
  • two anchor points can be obtained, and the material moves following the positions of the two anchor points.
  • the coordinates of each key point can be obtained from the key points detected in step S102.
  • the configuration file may also include the relationship between the scaling degree of the material and the key points, and the parameters "scaleX” and “scaleY” are used to describe the scaling requirements in the x and y directions, respectively.
  • the parameters "scaleX” and “scaleY” are used to describe the scaling requirements in the x and y directions, respectively.
  • two parameters “start_idx” and “end_idx” are included, which correspond to two key points. The distance between these two key points is multiplied by the value of "factor” to get the intensity of scaling.
  • the factor is a preset value and can be any value.
  • the configuration file can also include the rotation parameter "rotationtype" of the material, which will only take effect when there is only "point0" in the "position”. It can include two values of 0 and 1, where: 0 : No need to rotate; 1: Need to rotate according to the relative angle value of the key point.
  • the configuration file may also include a rendering blending mode.
  • the rendering blending refers to mixing two colors together. Specifically, in this disclosure, it refers to combining the color of a certain pixel position with the color to be drawn. Mixed together to achieve special effects, and the rendering blending mode refers to the method used for blending. Generally speaking, the blending method refers to calculating the source color and the target color to obtain the mixed color. In practical applications, it is often used The result obtained by multiplying the source color by the source factor and the result obtained by multiplying the target color by the target factor are calculated to obtain the mixed color.
  • BLENDcolor SRC_color*SCR_factor+DST_color*DST_factor, where 0 ⁇ SCR_factor ⁇ 1, 0 ⁇ DST_factor ⁇ 1.
  • the new color produced by mixing can be expressed as: (Rs*Sr+Rd*Dr,Gs*Sg+Gd*Dg,Bs*Sb+Bd*Db,As*Sa+Ad*Da), where the alpha value represents transparency, 0 ⁇ alpha ⁇ 1.
  • the above hybrid method is just an example. In practical applications, you can define or select the hybrid method by yourself.
  • the calculation can be addition, subtraction, multiplication, division, taking the larger of the two, taking the smaller of the two, logical operations (And, OR, XOR, etc.).
  • the above hybrid method is just an example. In practical applications, you can define or select the hybrid method by yourself.
  • the calculation can be addition, subtraction, multiplication, division, taking the larger of the two, taking the smaller of the two, logical operations (And, OR, XOR, etc.).
  • the configuration file may also include the rendering order.
  • the rendering order includes two levels. One is the rendering order between the sequence frames of the material.
  • the order can be defined by the parameter "zorder", "zorder” The smaller the value, the higher the rendering order; the second level is the rendering order between the material and the animal face image.
  • the order can be determined in many ways. Typically, it can also be used similar to "zorder" You can directly set the animal face to be rendered first or the material to be rendered first.
  • the position parameter when the position parameter is associated with key points, the position parameter describes which animal face key points are associated with the position of the deformation.
  • the type of deformation may specifically be magnification, and the magnified area may be determined by key points. For example, if the eyes on an animal face are magnified, the position parameter is the key point representing the eyes; optionally, the type of deformation may be For dragging, the position parameter may be a key point to be dragged and so on.
  • the deformation type may be at least one or a combination of zoom in, zoom out, translation, rotation, and drag.
  • the configuration file may also include a parameter of the degree of deformation.
  • the degree of deformation may be, for example, the magnification and reduction magnification, the translation distance, the rotation angle, the dragging distance, and so on.
  • the deformation degree parameter includes the position of the target point and the amplitude of the translation from the center point to the target point.
  • the amplitude may be a negative number, indicating translation in the opposite direction; in the deformation degree parameter
  • It may also include a translational attenuation coefficient. The larger the translational attenuation coefficient, the smaller the attenuation of the translation amplitude in the direction away from the center point.
  • the deformation type also includes a special type of deformation: flexible zoom in/out, which can freely adjust the degree of image deformation at an image position that is not far from the center point in the deformed area.
  • Step S104 processing the facial image of the animal according to the image processing parameters to obtain a processed animal facial image
  • this step it may include processing the facial image of the animal according to the type parameter of the image processing and the key points of the facial image of the animal to obtain a processed animal facial image.
  • the material required for the image processing is acquired; according to the key points of the animal's facial image, the material is rendered to a predetermined position of the animal's facial image To get an animal face image with the material.
  • the texture image includes multiple materials.
  • the storage address of the materials may be stored in the configuration file in step S103.
  • the materials may be a pair of glasses.
  • the key points in the key points of the animal’s face image are the position parameters in step S103. In this specific example, it may be the position of the eyes of the animal.
  • the glasses are rendered to the position of the eyes of the animal to obtain the glasses with glasses. Animal face images.
  • the key points related to the deformation type are acquired; the key points related to the deformation type are moved to a predetermined position to obtain the deformed animal face Department image.
  • the deformation type is magnification
  • the key points related to the deformation type are eye key points
  • the degree of magnification can be obtained according to the deformation degree parameter in the configuration file, and the key points of the eye after magnification are calculated Move all the key points of the eyes to the enlarged position to get an animal face image with enlarged eyes.
  • the step S102 the recognizing the facial image of the animal in the image, includes:
  • Step S301 Recognizing facial images of multiple animals in the image, and assigning an animal face ID to the facial image of each animal according to the recognition order.
  • step S103 a configuration file of image processing is read, the configuration file includes the parameters of the image processing, including:
  • Step S302 Read a configuration file for image processing, and obtain image processing parameters corresponding to the animal face ID according to the animal face ID.
  • the method of simultaneously performing image processing on the facial images of multiple animals in the image is realized.
  • each recognized animal facial image is in accordance with the recognition order Or assign animal face IDs in any other order, and configure the processing parameters corresponding to each ID in the configuration file in advance, including processing type, processing location, and various other necessary processing parameters.
  • processing parameters corresponding to each ID in the configuration file including processing type, processing location, and various other necessary processing parameters.
  • the embodiments of the present disclosure provide an image processing method, device, electronic device, and computer-readable storage medium of an animal face.
  • the image processing method of the animal face includes: acquiring an input image, the image includes at least one animal; identifying the face image of the animal in the image; reading a configuration file for image processing, in the configuration file Including the image processing parameters; according to the image processing parameters, processing the animal's facial image to obtain the processed animal's facial image.
  • the embodiment of the present disclosure recognizes the animal face image in the image and processes the animal face image according to the configuration of the image processing in the configuration file to obtain different special effects, which solves the need for post-production in the prior art. The problem of inflexible production of special effects when processing animal face images.
  • Embodiment 1 of an animal face image processing apparatus 400 provided by an embodiment of the disclosure.
  • the apparatus includes: an image acquisition module 401, an animal face recognition module 402, and configuration file reading Module 403 and image processing module 404. among them,
  • the image acquisition module 401 is configured to acquire an input image, the image includes at least one animal;
  • the animal face recognition module 402 is used to recognize the face image of the animal in the image
  • the configuration file reading module 403 is configured to read an image processing configuration file, the configuration file including the image processing parameters;
  • the image processing module 404 is configured to process the facial image of the animal according to the image processing parameters to obtain a processed facial image of the animal.
  • the image acquisition module 401 further includes:
  • the video image acquisition module is configured to acquire a video image, the video image includes a plurality of video frames, and at least one video frame of the plurality of video frames includes at least one animal.
  • animal face recognition module 402 further includes:
  • the video animal face recognition module is used to recognize the face image of the animal in the current video frame.
  • animal face recognition module 402 further includes:
  • the key point detection module is used to identify the face area of the animal in the image, and detect the key point of the face image of the animal in the face area.
  • configuration file reading module 403 includes:
  • the first configuration file reading module is configured to read an image processing configuration file, the configuration file includes the image processing type parameter and position parameter, wherein the position parameter is associated with the key point.
  • the image processing module 404 further includes:
  • the first image processing module is configured to process the facial image of the animal according to the type parameters of the image processing and the key points of the facial image of the animal to obtain a processed facial image of the animal.
  • the first image processing module further includes:
  • the material acquisition module is used to acquire the material required for the image processing when the type parameter of the image processing is texture processing;
  • the texture processing module is used to render the material to a predetermined position of the animal face image according to the key points of the animal's face image to obtain the animal face image with the material.
  • the first image processing module further includes:
  • a key point acquisition module configured to acquire key points related to the deformation type when the type parameter of the image processing is a deformation type
  • the deformation processing module is used to move the key points related to the deformation type to a predetermined position to obtain a deformed animal face image.
  • the device shown in FIG. 4 can execute the method of the embodiment shown in FIG. 1.
  • the parts not described in detail in this embodiment please refer to the related description of the embodiment shown in FIG. 1. Refer to the description in the embodiment shown in FIG. 1 for the execution process and technical effects of this technical solution, and will not be repeated here.
  • the animal face recognition module 402 further includes an ID allocation module 501, which is used to identify the image in the image Face images of multiple animals, and assign an animal face ID to the face image of each animal in the order of recognition.
  • the configuration file reading module 403 further includes: a processing parameter acquisition module 502, configured to read an image processing configuration file, and obtain image processing parameters corresponding to the animal face ID according to the animal face ID.
  • the device in the second embodiment above can execute the method of the embodiment shown in FIG. 3, and for parts not described in detail in this embodiment, please refer to the related description of the embodiment shown in FIG. 3.
  • FIG. 6 shows a schematic structural diagram of an electronic device 600 suitable for implementing embodiments of the present disclosure.
  • the electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (such as Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device 600 may include a processing device (such as a central processing unit, a graphics processor, etc.) 601, which can be loaded into a random access device according to a program stored in a read-only memory (ROM) 602 or from a storage device 608.
  • the program in the memory (RAM) 603 executes various appropriate actions and processing.
  • the RAM 603 also stores various programs and data required for the operation of the electronic device 600.
  • the processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604.
  • the following devices can be connected to the I/O interface 605: including input devices 606 such as touch screen, touch panel, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, An output device 607 such as a vibrator; a storage device 608 such as a magnetic tape, a hard disk, etc.; and a communication device 609.
  • the communication device 609 may allow the electronic device 600 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 6 shows an electronic device 600 having various devices, it should be understood that it is not required to implement or have all the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.
  • the process described above with reference to the flowchart can be implemented as a computer software program.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM602.
  • the processing device 601 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
  • the aforementioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • 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 any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), 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 any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a 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.
  • the computer-readable signal 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: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains an input image, the image includes at least one animal; The face image of the animal; read the image processing configuration file, the configuration file includes the image processing parameters; according to the image processing parameters, the face image of the animal is processed to obtain processing Of the face of the animal afterwards.
  • the computer program code used to perform the operations of the present disclosure may be written in one or more programming languages or a combination thereof.
  • the above-mentioned 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
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function Executable instructions.
  • the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware. Among them, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Image Processing (AREA)
  • Processing Or Creating Images (AREA)
  • Studio Devices (AREA)
  • Image Analysis (AREA)

Abstract

一种动物脸部的图像处理方法、装置、电子设备和计算机可读存储介质。其中所述动物脸部的图像处理方法包括：获取输入图像，所述图像中包括至少一个动物（S101）；识别所述图像中的动物的脸部图像（S102）；读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数（S103）；根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像（S104）。该方法通过识别图像中的动物脸部图像，并根据配置文件中的图像处理的配置，对动物的脸部图像进行处理，得到不同的特效，解决了现有技术中需要通过后期制作对动物脸部图像进行处理，特效制作不灵活的问题。

Description

动物脸部的图像处理方法和装置
相关申请的交叉引用
本申请要求于2019年01月25日提交的，申请号为201910073609.4、发明名称为“动物脸部的图像处理方法和装置”的中国专利申请的优先权，该申请的全文通过引用结合在本申请中。
技术领域
本公开涉及图像处理领域，尤其涉及一种动物脸部的图像处理方法、装置、电子设备及计算机可读存储介质。
背景技术
随着计算机技术的发展，智能终端的应用范围得到了广泛的提高，例如可以通过智能终端听音乐、玩游戏、上网聊天和拍照等。对于智能终端的拍照技术来说，其拍照像素已经达到千万像素以上，具有较高的清晰度和媲美专业相机的拍照效果。
目前在采用智能终端进行拍照时，不仅可以使用出厂时内置的拍照软件实现传统功能的拍照效果，还可以通过从网络端下载应用程序(Application，简称为：APP)来实现具有附加功能的拍照效果，例如可以实现暗光检测、美颜相机和超级像素等功能的APP。智能终端的美颜功能通常包括肤色调整、磨皮、大眼和瘦脸等美颜处理效果，能对图像中已识别出的人脸进行一定程度的美颜处理。
然而目前的各种相机和APP，一般只会对人脸进行一定的优化或者处理，并不会针对其他动物进行处理，而各种宠物如猫和狗也经常会出现在各种图像中，如果要对猫狗的图像进行处理，一般也是整体处理，如对猫的整个身体进行处理，而更加细致的局部处理，需要通过后期制作来处理，比较繁琐且对普通用户来说不够简便，因此需要一种简单的、可以对动物的图像进行特效处理的技术方案。
发明内容
第一方面，本公开实施例提供一种动物脸部的图像处理方法，包括：获取输入图像，所述图像中包括至少一个动物；识别所述图像中的动物的脸部图像；读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
进一步的，所述获取输入图像，所述图像中包括至少一个动物，包括：获取视频图像，所述视频图像包括多个视频帧，所述多个视频帧中的至少一个视频帧中包括至少一个动物。
进一步的，所述识别所述图像中的动物的脸部图像，包括：识别当前视频帧中的动物的脸部图像。
进一步的，所述识别所述图像中的动物的脸部图像，包括：识别所述图像中的动物的脸部区域，在所述脸部区域中检测出所述动物的脸部图像的关键点。
进一步的，所述读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数，包括：读取图像处理的配置文件，所述配置文件中包括有所述图像处理的类型参数以及位置参数，其中所述位置参数与所述关键点相关联。
进一步的，所述根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像，包括：根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
进一步的，所述根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像，包括：当所述图像处理的类型参数为贴图处理，获取所述图像处理所需的素材；根据所述动物的脸部图像的关键点，将所述素材渲染到动物脸部图像的预定位置，得到带有所述素材的动物脸部图像。
进一步的，所述根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像，包括：当所述图像处理的类型参数为形变类型，获取与所述形变类型相关的 关键点；将所述与所述形变类型相关的关键点移动到预定的位置，得到形变后的动物脸部图像。
进一步的，所述识别所述图像中的动物的脸部图像，包括：识别所述图像中的多个动物的脸部图像，并对每个动物的脸部图像按照识别顺序分配动物脸部ID。
进一步的，所述读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数，包括：读取图像处理的配置文件，根据所述动物脸部ID获取与所述动物脸部ID对应的图像处理的参数。
第二方面，本公开实施例提供一种动物脸部的图像处理装置，包括：
图像获取模块，用于获取输入图像，所述图像中包括至少一个动物；
动物脸部识别模块，用于识别所述图像中的动物的脸部图像；
配置文件读取模块，用于读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；
图像处理模块，用于根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
进一步的，所述图像获取模块，还包括:
视频图像获取模块，用于获取视频图像，所述视频图像包括多个视频帧，所述多个视频帧中的至少一个视频帧中包括至少一个动物。
进一步的，所述动物脸部识别模块，还包括：
视频动物脸部识别模块，用于识别当前视频帧中的动物的脸部图像。
进一步的，所述动物脸部识别模块，还包括：
关键点检测模块，用于识别所述图像中的动物的脸部区域，在所述脸部区域中检测出所述动物的脸部图像的关键点。
进一步的，所述配置文件读取模块，包括：
第一配置文件读取模块，用于读取图像处理的配置文件，所述配置文件中包括有所述图像处理的类型参数以及位置参数，其中所述位置参数与所述关键点相关联。
进一步的，所述图像处理模块，还包括：
第一图像处理模块，用于根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸 部图像。
进一步的，所述第一图像处理模块，还包括：
素材获取模块，用于当所述图像处理的类型参数为贴图处理，获取所述图像处理所需的素材；
贴图处理模块，用于根据所述动物的脸部图像的关键点，将所述素材渲染到动物脸部图像的预定位置，得到带有所述素材的动物脸部图像。
进一步的，所述第一图像处理模块，还包括：
关键点获取模块，用于当所述图像处理的类型参数为形变类型，获取与所述形变类型相关的关键点；
形变处理模块，用于将所述与所述形变类型相关的关键点移动到预定的位置，得到形变后的动物脸部图像。
进一步的，所述动物脸部识别模块，还包括：
ID分配模块，用于识别所述图像中的多个动物的脸部图像，并对每个动物的脸部图像按照识别顺序分配动物脸部ID。所述配置文件读取模块，还包括：处理参数获取模块，用于读取图像处理的配置文件，根据所述动物脸部ID获取与所述动物脸部ID对应的图像处理的参数。
第三方面，本公开实施例提供一种电子设备，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，所述存储器存储有能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前述第一方面中的任一所述动物脸部的图像处理方法。
第四方面，本公开实施例提供一种非暂态计算机可读存储介质，其特征在于，该非暂态计算机可读存储介质存储计算机指令，该计算机指令用于使计算机执行前述第一方面中的任一所述动物脸部的图像处理方法。
本公开实施例提供一种动物脸部的图像处理方法、装置、电子设备和计算机可读存储介质。其中所述动物脸部的图像处理方法包括：获取输入图像，所述图像中包括至少一个动物；识别所述图像中的动物的脸部图像；读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部 图像。本公开实施例通过识别图像中的动物脸部图像，并根据配置文件中的图像处理的配置，对动物的脸部图像进行处理，得到不同的特效，解决了现有技术中需要通过后期制作对动物脸部图像进行处理，特效制作不灵活的问题。
上述说明仅是本公开技术方案的概述，为了能更清楚了解本公开的技术手段，而可依照说明书的内容予以实施，并且为让本公开的上述和其他目的、特征和优点能够更明显易懂，以下特举较佳实施例，并配合附图，详细说明如下。
附图说明
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的动物脸部的图像处理方法实施例一的流程图；
图2a为本公开实施例提供的动物脸部的图像处理方法中所使用的猫脸关键点的示意图；
图2b为本公开实施例提供的动物脸部的图像处理方法中所述用的狗脸关键点的示意图；
图3为公开实施例提供的动物脸部的图像处理方法实施例二的流程图；
图4为本公开实施例提供的动物脸部的图像处理装置实施例一的结构示意图；
图5为本公开实施例提供的动物脸部的图像处理装置实施例二中动物脸部识别模块和配置文件读取模块的结构示意图。
图6为根据本公开实施例提供的电子设备的结构示意图。
具体实施方式
以下通过特定的具体实例说明本公开的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本公开的其他优点与功效。显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。本公开还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可 以基于不同观点与应用，在没有背离本公开的精神下进行各种修饰或改变。需说明的是，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。基于本公开中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
需要说明的是，下文描述在所附权利要求书的范围内的实施例的各种方面。应显而易见，本文中所描述的方面可体现于广泛多种形式中，且本文中所描述的任何特定结构及/或功能仅为说明性的。基于本公开，所属领域的技术人员应了解，本文中所描述的一个方面可与任何其它方面独立地实施，且可以各种方式组合这些方面中的两者或两者以上。举例来说，可使用本文中所阐述的任何数目个方面来实施设备及/或实践方法。另外，可使用除了本文中所阐述的方面中的一或多者之外的其它结构及/或功能性实施此设备及/或实践此方法。
还需要说明的是，以下实施例中所提供的图示仅以示意方式说明本公开的基本构想，图式中仅显示与本公开中有关的组件而非按照实际实施时的组件数目、形状及尺寸绘制，其实际实施时各组件的型态、数量及比例可为一种随意的改变，且其组件布局型态也可能更为复杂。
另外，在以下描述中，提供具体细节是为了便于透彻理解实例。然而，所属领域的技术人员将理解，可在没有这些特定细节的情况下实践所述方面。
图1为本公开实施例提供的动物脸部的图像处理方法实施例一的流程图，本实施例提供的该动物脸部的图像处理方法可以由一动物脸部的图像处理装置来执行，该动物脸部的图像处理装置可以实现为软件，或者实现为软件和硬件的组合，该动物脸部的图像处理装置可以集成设置在图像处理系统中的某设备中，比如图像处理服务器或者图像处理终端设备中。如图1所示，该方法包括如下步骤：
步骤S101，获取输入图像，所述图像中包括至少一个动物；
在一个实施例中，所述获取输入图像，包括从本地存储空间中获取所述输入图像或者从网络存储空间中获取输入图像，无论从哪里获取输入图像，首选需要获取输入图像的存储地址，之后从该存储地址获取输入图像，所述输入图像可以是视频图像也可以是图片，或者是带有动态效果的图片，在此不再赘述。
在一个实施例中，所述获取输入图像，包括获取视频图像，所述视频图像包括多个视频帧，所述多个视频帧中的至少一个视频帧中包括至少一个动物。在该实施例中，所述输入视频图像可以通过图像传感器来获取，图像传感器指可以采集图像的各种设备，典型的图像传感器为摄像机、摄像头、相机等。在该实施例中，所述图像传感器可以是移动终端上的摄像头，比如智能手机上的前置或者后置摄像头，摄像头采集的视频图像可以直接显示在手机的显示屏上，在该步骤中，获取图像传感器所拍摄的图像视频，用于在下一步进一步识别图像。
在该步骤中，所述输入图像中包括至少一个动物，动物图像是识别动物脸部图像的基础，在该实施例中，如果所述输入图像为图片，则图片中至少包括一个动物的图像，如果所述输入图像为视频，则所述输入图像中的视频帧中至少有一个视频帧中包括至少一个动物的图像。
步骤S102，识别所述图像中的动物的脸部图像；
在该步骤中，所述识别所述图像中的动物的脸部图像，包括：识别所述图像中的动物的脸部区域，在所述脸部区域中检测出所述动物的脸部图像的关键点。识别所述图像中的动物的脸部区域，可以是粗略的在图像中识别出带有所述动物的脸部的图像区域，并将该区域框选出来，以便进一步在所述脸部区域中检测关键点。在识别动物的脸部区域时，可以使用分类器对图像中的动物脸部进行分类以得到动物的脸部区域，具体的可以使用多次分类的方式，先进行粗分类再将粗分类的图像进行细分类以得到最终的分类结果。
在一个具体的实施方式中，可以首先对动物脸图像进行灰度化，将图像转换为灰度图，之后提取灰度图的第一特征，所述的第一特征为图像上多个形状大小相同的矩形内的所有像素的灰度值之和的差值，该第一特征反应了图像局部的灰度变化。使用训练集中的图像的第一特征来训练一个基本分类器，在把分类能力最优的前N个基本分类器组合起来，得到一个第一分类器。对训练集中的样本和基本分类器，可以使用权重值来加强或者削弱，样本的权重值表示其被正确分类的困难程度，开始时每个样本对应的权重值相同，在此样本分布下训练出一个基本分类器h1,对于h1分错的样本，增加其对应的权重值，对于h1分对的样本，降低其权重值，这样使得新的样本分布更加突出分错的样本的，使得再下一轮的训练中，基本分类器能够更专注于这 些分错的样本。而基本分类器的权重值则表示其分类能力的强弱，错分的样本越少的基本分类器的权重越大，以表示其分类的能力越好。在新的样本分布下，在此对弱分类器h1进行训练，得到基本分类器h2及其权重，以此类推，经过N轮迭代，得到N个基本分类器h1,h2,h3,……,hN，以及N个对应的权重值，最后将h1,h2,h3,……,hN按照权重值累加，形成第一分类器。其中所述的训练集中包括正样本和负样本，其中正样本中包括动物的脸部图像，负样本中不包括动物的脸部图像，其中所述的动物的脸部图像为一种动物，比如均为狗的脸部图像或者均为猫的脸部图像，对每种动物可以单独训练处单独的第一分类器。使用第一分类器对图像进行分类，得到第一分类结果。
将第一分类器的分类结果通过第二分类器继续分类，第二分类器可以使用第二特征对动物脸图像进行分类。其中第二特征可以是方向梯度直方图特征，第二分类器可以是支持向量机分类器。获取第一分类器的分类结果中的图像的方向梯度直方图特征，通过支持向量机分类器将所述分类结果中的图像进行二次分类，得到最终的分类结果，即包含特定动物脸图像的输入图像以及所述特定动物的脸部图像的图像区域。第二分类器分错的样本，也可以放入第一分类器的负样本中，并调整其权重值，为第一分类器的调整提供反馈。
在上述第一分类器和第二分类器的分类下，得到图像中的动物的脸部区域，在该区域中进一步检测动物脸部的关键点。该检测可以通过深度学习的方法实现，在脸部图像区域的基础上，可以先在区域中预测出动物脸上的关键点的位置，之后根据动物脸上的不同区域进行细化定位，所述的不同区域可以根据动物脸部的器官来确定，如眼睛区域、鼻子区域、嘴巴区域等等，最后检测脸部的轮廓关键点，将这些关键点联合形成完整的关键点。
典型的动物脸关键点如图2a和2b所示，其中2a为82个关键点的猫脸，2b为90个关键点的狗脸，其中带有数字标记的关键点为语义点，如猫脸中标号为0的点为左侧下耳根，标号为8的点为下巴点，而标号1-7没有具体的含义，其实0-8之间的等分点，紧贴轮廓边缘。其他关键点类似，不再赘述。在识别出这些关键之后，后续的图像处理便有了根据。
在一个实施例中，在步骤S101中，所述输入图像为视频图像，因此所述识别所述图像中的动物的脸部图像，包括：识别当前视频帧中的动物的脸 部图像。在该实施例中，将每一帧图像作为一个输入图像通过上述识别方法，识别出动物的脸部图像的关键点，这样即便在视频中动物的脸部发生移动，也可以动态的识别和跟踪动物的脸部图像。
可以理解是的，上述动物脸部的识别方法仅仅是举例，实际上任何可以识别动物的脸部图像以及检测出动物脸部的关键点的方法均可以应用到本公开的技术方案中，本公开对此不做限制。
步骤S103，读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；
在该步骤中，所述的配置文件中包括有所述图像处理的类型参数以及位置参数。其中所述类型参数决定图像处理的类型，可选的，所述类型可以为贴图处理类型或形变处理类型；其中所述的位置参数标识需要进行图像处理的位置，可选的，所述位置参数可以是图像的绝对位置，如图像的UV坐标或者其他各种坐标，可选的，所述位置参数可以与步骤S102中所识别出来的关键点关联，由于每个关键点与动物的脸部关联，因此可以实现图像的处理效果随动物脸部的移动而移动的效果。
典型的，对于贴图类型，当所述位置参数与关键点相关联，所述位置参数描述图像处理的素材的显示位置关联哪几个动物脸关键点，默认可以关联所有关键点，也可以设置跟随其中的几个关键点。除了位置参数外，配置文件中还包括素材与关键点的位置关系参数"point"，"point"中可以包括两组关联点，"point0"表示第一组关联点，"point1"表示第二组。对于每一组关联点，"point"描述了摄像头中的锚点位置，通过对若干组关键点及其权重，求加权平均得到；使用"idx"字段描述了关键点的序号，具体来说，设置素材跟随动物脸的4个关键点，分别为9号、10号、11号和12号关键点，且每个关键点的权重为0.25，其中每个关键点的坐标分别为(X9，Y9)，(X10，Y10)，(X11，Y11)，(X12，Y12)，则可以得到素材所跟随的锚点的X轴坐标为Xa＝X9*0.25+X10*0.25+X11*0.25+X12*0.25，锚点的Y轴坐标为Ya＝Y9*0.25+Y10*0.25+Y11*0.25+Y12*0.25。可以理解的是，"point"中可以包括任一组关联点，并不局限于两组。在上述具体实例中，可以得到两个锚点，素材跟随这两个锚点的位置发生移动。而实际上，锚点可以不止两个，这与所使用的关联点的组数有关。其中每个关键点的坐标可以由步骤S102中所 检测的关键点获得。
对于贴图类型，所述配置文件中还可以包括素材的缩放程度与关键点的关系，使用参数"scaleX"和"scaleY"分别描述了x和y方向的缩放需求。对于每个方向，都包括两个参数"start_idx"和"end_idx"，其对应了两个关键点，这两个关键点之间的距离乘以"factor"的值后得到缩放的强度。其中factor为预先设置的值，可以为任意值。对于缩放来说，如果"position"中只有一组关联点"point0"，那么x方向就是实际的水平向右方向；y方向为实际垂直向下方向；"scaleX"和"scaleY"都会生效，如果任一有缺失，则按照存在的那个参数保持素材原始长宽比进行缩放。如果"position"中"point0"和"point1"都有，那么x方向为point1.anchor-point0.anchor得到的向量方向；y方向由x方向顺时针旋转90度确定；"scaleX"无效，x方向的缩放由锚点跟随决定。"scaleY"会生效，若"scaleY"缺失，则保持素材原始长宽比进行缩放。
对于贴图类型，所述配置文件中还可以包括素材的旋转参数"rotationtype"，其只有在"position"中只有"point0"时，才会生效，其可以包括0和1两个值，其中：0：不需要旋转；1：需要根据关键点的相关角度值进行旋转。
对于贴图类型，所述配置文件中还可以包括渲染混合模式，所述渲染混合是指将两种颜色混合在一起，具体到本公开中是指将某一像素位置的颜色与将要画上去的颜色混合在一起，从而实现特殊效果，而渲染混合模式是指混合所使用的方式，一般来说混合方式是指将源颜色和目标颜色做计算，得出混合后的颜色，在实际应用中常常将源颜色乘以源因子得到的结果与目标颜色乘以目标因子得到的结果做计算，得到混合后的颜色，举例来说，所述计算为加，则BLENDcolor＝SRC_color*SCR_factor+DST_color*DST_factor，其中0≤SCR_factor≤1，0≤DST_factor≤1。根据上述运算公式，假设源颜色的四个分量(指红色，绿色，蓝色，alpha值)是(Rs,Gs,Bs,As)，目标颜色的四个分量是(Rd,Gd,Bd,Ad)，设源因子为(Sr,Sg,Sb,Sa)，目标因子为(Dr,Dg,Db,Da)。则混合产生的新颜色可以表示为：(Rs*Sr+Rd*Dr,Gs*Sg+Gd*Dg,Bs*Sb+Bd*Db,As*Sa+Ad*Da)，其中alpha值表示透明度，0≤alpha≤1。上述混合方式仅仅是举例，实际应用中，可以自行定义或者选择混合方式，所述计算可以是加、减、乘、除、取两者中较大的、取两者中较 小的、逻辑运算(和、或、异或等等)。上述混合方式仅仅是举例，实际应用中，可以自行定义或者选择混合方式，所述计算可以是加、减、乘、除、取两者中较大的、取两者中较小的、逻辑运算(和、或、异或等等)。
对于贴图类型，所述配置文件中还可以包括渲染顺序，所述渲染顺序包括两个层次，一个是素材的序列帧之间的渲染顺序，该顺序可以使用参数"zorder"来定义，"zorder"的值越小，表示渲染的顺序越靠前；第二个层次是素材和动物脸图像之间的渲染顺序，该顺序可以通过多种方式来确定，典型的，也可以使用与"zorder"类似的方式，可以直接设置动物脸先渲染或者素材先渲染。
对于形变类型，当所述位置参数与关键点相关联，所述位置参数描述形变的位置关联哪几个动物脸关键点。可选的，形变类型具体可以为放大，则可以通过关键点确定放大的区域，如对动物脸上的眼睛放大，则位置参数为表示眼睛的关键点；可选的，所述形变类型具体可以为拖拽，所述位置参数可以为所所拖拽的关键点等等。所述形变类型至少可以为放大、缩小、平移、旋转、拖拽中的一种或多种的组合。
对于形变类型，所述配置文件中还可以包括形变的程度参数。所述形变的程度可以是例如放大缩小的倍数、平移的距离、旋转的角度、拖拽的距离等等。当所述形变类型为平移时，所述形变程度参数中包括目标点的位置以及从中心点平移向目标点的幅度，所述幅度可以是负数，表示反方向的平移；所述形变程度参数中还可以包括平移衰减系数，所述平移衰减系数越大，平移幅度在远离中心点的方向上的衰减越小。所述形变类型还包括一种特殊的形变类型：灵活的放大/缩小，可以自由调整形变区域内到中心点不用距离的图像位置的图像形变程度。
可以理解的是，上述图像处理类型和图像处理类型所对应的具体参数均是为了说明本公开的技术方案的具体举例，而不是对本公开的限制，实际上符合本公开场景的图像处理类型，比如滤镜、美颜、模糊等等图像处理均可以应用于本公开中，其所使用参数等可以与上述具体中的不同，在此不再赘述。
步骤S104，根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像；
在该步骤中，可以包括根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
具体的，当所述图像处理的类型参数为贴图处理，获取所述图像处理所需的素材；根据所述动物的脸部图像的关键点，将所述素材渲染到动物脸部图像的预定位置，得到带有所述素材的动物脸部图像。在该实施例中，所述贴图中包括多个素材，所述素材的存储地址可以存储于步骤S103中的配置文件中，可选的，所述素材可以为一副眼镜，此时根据所述动物的脸部图像的关键点中的关键点为步骤S103中的位置参数，在此具体实例中可以为动物的眼睛位置，将所述眼镜渲染到所述动物的眼睛的位置，得到带眼镜的动物脸部图像。
具体的，当所述图像处理的类型参数为形变类型，获取与所述形变类型相关的关键点；将所述与所述形变类型相关的关键点移动到预定的位置，得到形变后的动物脸部图像。可选的，所述形变类型为放大，与所述形变类型相关的关键点为眼睛关键点，则根据所述配置文件中的形变程度参数，可以得到放大的程度，计算得到放大后眼睛关键点的位置，移动所有眼睛的关键点到放大后的位置，得到放大了眼睛的动物脸部图像。
可以理解的是，上述贴图处理和形变处理，仅仅是为了说明技术方案的举例，不够成对本公开的限制，任何其他的处理均可以在配置文件中配置并应用到本公开中来，在此不再赘述。
如图2所示，在本公开的动画生成方法的另一个实施例中，所述步骤S102，所述识别所述图像中的动物的脸部图像，包括：
步骤S301，识别所述图像中的多个动物的脸部图像，并对每个动物的脸部图像按照识别顺序分配动物脸部ID。
所述步骤S103，读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数，包括：
步骤S302，读取图像处理的配置文件，根据所述动物脸部ID获取与所述动物脸部ID对应的图像处理的参数。
在该实施例中，实现了对图像中的多个动物的脸部图像同时进行图像处理的方法，在识别出多个动物脸部图像时，对每个识别出来的动物脸部图像 按照识别顺序或者其他任意顺序分配动物脸部ID，在配置文件中事先配置好每个ID所对应的处理参数，包括处理类型以及处理位置以及其他各种必要的处理参数。这样，根据配置文件中的配置，可以针对每个识别出的动物脸做不同的处理，以达到更好的效果。
本公开实施例提供一种动物脸部的图像处理方法、装置、电子设备和计算机可读存储介质。其中所述动物脸部的图像处理方法包括：获取输入图像，所述图像中包括至少一个动物；识别所述图像中的动物的脸部图像；读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。本公开实施例通过识别图像中的动物脸部图像，并根据配置文件中的图像处理的配置，对动物的脸部图像进行处理，得到不同的特效，解决了现有技术中需要通过后期制作对动物脸部图像进行处理，特效制作不灵活的问题。
图4为本公开实施例提供的动物脸部的图像处理装置400实施例一的结构示意图，如图4所示，该装置包括：图像获取模块401、动物脸部识别模块402、配置文件读取模块403和图像处理模块404。其中，
图像获取模块401，用于获取输入图像，所述图像中包括至少一个动物；
动物脸部识别模块402，用于识别所述图像中的动物的脸部图像；
配置文件读取模块403，用于读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；
图像处理模块404，用于根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
进一步的，所述图像获取模块401，还包括:
视频图像获取模块，用于获取视频图像，所述视频图像包括多个视频帧，所述多个视频帧中的至少一个视频帧中包括至少一个动物。
进一步的，所述动物脸部识别模块402，还包括：
视频动物脸部识别模块，用于识别当前视频帧中的动物的脸部图像。
进一步的，所述动物脸部识别模块402，还包括：
关键点检测模块，用于识别所述图像中的动物的脸部区域，在所述脸部区域中检测出所述动物的脸部图像的关键点。
进一步的，所述配置文件读取模块403，包括：
第一配置文件读取模块，用于读取图像处理的配置文件，所述配置文件中包括有所述图像处理的类型参数以及位置参数，其中所述位置参数与所述关键点相关联。
进一步的，所述图像处理模块404，还包括：
第一图像处理模块，用于根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
进一步的，所述第一图像处理模块，还包括：
素材获取模块，用于当所述图像处理的类型参数为贴图处理，获取所述图像处理所需的素材；
贴图处理模块，用于根据所述动物的脸部图像的关键点，将所述素材渲染到动物脸部图像的预定位置，得到带有所述素材的动物脸部图像。
进一步的，所述第一图像处理模块，还包括：
关键点获取模块，用于当所述图像处理的类型参数为形变类型，获取与所述形变类型相关的关键点；
形变处理模块，用于将所述与所述形变类型相关的关键点移动到预定的位置，得到形变后的动物脸部图像。
图4所示装置可以执行图1所示实施例的方法，本实施例未详细描述的部分，可参考对图1所示实施例的相关说明。该技术方案的执行过程和技术效果参见图1所示实施例中的描述，在此不再赘述。
在本公开实施例提供的动物脸部的图像处理装置实施例二中，如图5所示，所述动物脸部识别模块402，还包括：ID分配模块501，用于识别所述图像中的多个动物的脸部图像，并对每个动物的脸部图像按照识别顺序分配动物脸部ID。所述配置文件读取模块403，还包括：处理参数获取模块502，用于读取图像处理的配置文件，根据所述动物脸部ID获取与所述动物脸部ID对应的图像处理的参数。
上述实施例二中的装置可以执行图3所示实施例的方法，本实施例未详细描述的部分，可参考对图3所示实施例的相关说明。该技术方案的执行过程和技术效果参见图3所示实施例中的描述，在此不再赘述。
下面参考图6，其示出了适于用来实现本公开实施例的电子设备600的结构示意图。本公开实施例中的电子设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图6示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图6所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储装置608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有电子设备600操作所需的各种程序和数据。处理装置601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储装置608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置609从网络上被下载和安装，或者从存储装置608被安装，或者从ROM602被安装。在该计算机程序被处理装置601执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，本公开上述的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或者是上述两者的任意组合。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 子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(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。在本公开中，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。而在本公开中，计算机可读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，该计算机可读信号介质可以发送、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：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取输入图像，所述图像中包括至少一个动物；识别所述图像中的动物的脸部图像；读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
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公开的操作的计算机程序代码，上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)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (13)

  1. 一种动物脸部的图像处理方法，其特征在于，包括：
    获取输入图像，所述图像中包括至少一个动物；
    识别所述图像中的动物的脸部图像；
    读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；
    根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
  2. 如权利要求1所述的动物脸部的图像处理方法，其特征在于，所述获取输入图像，所述图像中包括至少一个动物，包括：
    获取视频图像，所述视频图像包括多个视频帧，所述多个视频帧中的至少一个视频帧中包括至少一个动物。
  3. 如权利要求2所述的动物脸部的图像处理方法，其特征在于，所述识别所述图像中的动物的脸部图像，包括：
    识别当前视频帧中的动物的脸部图像。
  4. 如权利要求1所述的动物脸部的图像处理方法，其特征在于，所述识别所述图像中的动物的脸部图像，包括：
    识别所述图像中的动物的脸部区域，在所述脸部区域中检测出所述动物的脸部图像的关键点。
  5. 如权利要求4所述的动物脸部的图像处理方法，其特征在于，所述读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数，包括：
    读取图像处理的配置文件，所述配置文件中包括有所述图像处理的类型参数以及位置参数，其中所述位置参数与所述关键点相关联。
  6. 如权利要求5所述的动物脸部的图像处理方法，其特征在于，所述根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像，包括：
    根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
  7. 如权利要求6所述的动物脸部的图像处理方法，其特征在于，所述根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动 物的脸部图像进行处理，得到处理后的动物脸部图像，包括：
    当所述图像处理的类型参数为贴图处理，获取所述图像处理所需的素材；
    根据所述动物的脸部图像的关键点，将所述素材渲染到动物脸部图像的预定位置，得到带有所述素材的动物脸部图像。
  8. 如权利要求6所述的动物脸部的图像处理方法，其特征在于，所述根据所述图像处理的类型参数以及所述动物的脸部图像的关键点，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像，包括：
    当所述图像处理的类型参数为形变类型，获取与所述形变类型相关的关键点；
    将所述与所述形变类型相关的关键点移动到预定的位置，得到形变后的动物脸部图像。
  9. 如权利要求1所述的动物脸部的图像处理方法，其特征在于，所述识别所述图像中的动物的脸部图像，包括：
    识别所述图像中的多个动物的脸部图像，并对每个动物的脸部图像按照识别顺序分配动物脸部ID。
  10. 如权利要求9所述的动物脸部的图像处理方法，其特征在于，所述读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数，包括：
    读取图像处理的配置文件，根据所述动物脸部ID获取与所述动物脸部ID对应的图像处理的参数。
  11. 一种动物脸部的图像处理装置，其特征在于，包括：
    图像获取模块，用于获取输入图像，所述图像中包括至少一个动物；
    动物脸部识别模块，用于识别所述图像中的动物的脸部图像；
    配置文件读取模块，用于读取图像处理的配置文件，所述配置文件中包括有所述图像处理的参数；
    图像处理模块，用于根据所述图像处理的参数，对所述动物的脸部图像进行处理，得到处理后的动物脸部图像。
  12. 一种电子设备，包括：
    存储器，用于存储非暂时性计算机可读指令；以及
    处理器，用于运行所述计算机可读指令，使得所述处理器执行时实现根 据权利要求1-10中任意一项所述的动物脸部的图像处理方法。
  13. 一种计算机可读存储介质，用于存储非暂时性计算机可读指令，当所述非暂时性计算机可读指令由计算机执行时，使得所述计算机执行权利要求1-10中任意一项所述的动物脸部的图像处理方法。
PCT/CN2019/129119 2019-01-25 2019-12-27 动物脸部的图像处理方法和装置 Ceased WO2020151456A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/425,579 US20220101645A1 (en) 2019-01-25 2019-12-27 Method and device for processing image having animal face
JP2021542562A JP7383714B2 (ja) 2019-01-25 2019-12-27 動物顔部の画像処理方法と装置
GB2110696.8A GB2595094B (en) 2019-01-25 2019-12-27 Method and device for processing image having animal face

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910073609.4 2019-01-25
CN201910073609.4A CN111488759A (zh) 2019-01-25 2019-01-25 动物脸部的图像处理方法和装置

Publications (1)

Publication Number Publication Date
WO2020151456A1 true WO2020151456A1 (zh) 2020-07-30

Family

ID=71736107

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/129119 Ceased WO2020151456A1 (zh) 2019-01-25 2019-12-27 动物脸部的图像处理方法和装置

Country Status (5)

Country Link
US (1) US20220101645A1 (zh)
JP (1) JP7383714B2 (zh)
CN (1) CN111488759A (zh)
GB (1) GB2595094B (zh)
WO (1) WO2020151456A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113673439A (zh) * 2021-08-23 2021-11-19 平安科技（深圳）有限公司 基于人工智能的宠物狗识别方法、装置、设备及存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112991358A (zh) * 2020-09-30 2021-06-18 北京字节跳动网络技术有限公司 风格图像生成方法、模型训练方法、装置、设备和介质
CN112565863B (zh) * 2020-11-26 2024-07-05 深圳Tcl新技术有限公司 视频播放方法、装置、终端设备及计算机可读存储介质
CN115147258B (zh) * 2021-03-29 2026-03-03 北京新氧科技有限公司 脸型变换方法、装置、设备及存储介质
CN113822177A (zh) * 2021-09-06 2021-12-21 苏州中科先进技术研究院有限公司 一种宠物脸关键点检测方法、装置、存储介质及设备
CN114327705B (zh) * 2021-12-10 2023-07-14 重庆长安汽车股份有限公司 车载助手虚拟形象自定义方法
CN114926858B (zh) * 2022-05-10 2024-06-28 吉林大学 一种基于特征点信息的深度学习的猪脸识别方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180204052A1 (en) * 2015-08-28 2018-07-19 Baidu Online Network Technology (Beijing) Co., Ltd. A method and apparatus for human face image processing
CN108805961A (zh) * 2018-06-11 2018-11-13 广州酷狗计算机科技有限公司 数据处理方法、装置及存储介质
CN108833779A (zh) * 2018-06-15 2018-11-16 Oppo广东移动通信有限公司 拍摄控制方法及相关产品
CN108876704A (zh) * 2017-07-10 2018-11-23 北京旷视科技有限公司 人脸图像变形的方法、装置及计算机存储介质
CN109147012A (zh) * 2018-09-20 2019-01-04 麒麟合盛网络技术股份有限公司 图像处理方法和装置
CN109147017A (zh) * 2018-08-28 2019-01-04 百度在线网络技术（北京）有限公司 动态图像生成方法、装置、设备及存储介质
CN109254775A (zh) * 2018-08-30 2019-01-22 广州酷狗计算机科技有限公司 基于人脸的图像处理方法、终端及存储介质

Family Cites Families (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6661906B1 (en) * 1996-12-19 2003-12-09 Omron Corporation Image creating apparatus
US20050231512A1 (en) * 2004-04-16 2005-10-20 Niles Gregory E Animation of an object using behaviors
JP2006053718A (ja) * 2004-08-11 2006-02-23 Noritsu Koki Co Ltd 写真処理装置
JP4327773B2 (ja) * 2005-07-12 2009-09-09 ソフトバンクモバイル株式会社 携帯電話装置
JP4577252B2 (ja) * 2006-03-31 2010-11-10 カシオ計算機株式会社 カメラ、ベストショット撮影方法、プログラム
JP2007282119A (ja) * 2006-04-11 2007-10-25 Nikon Corp 電子カメラおよび画像処理装置
EP2094602A2 (en) * 2006-11-20 2009-09-02 Nxp B.V. A sealing structure and a method of manufacturing the same
JP5423379B2 (ja) * 2009-08-31 2014-02-19 ソニー株式会社 画像処理装置および画像処理方法、並びにプログラム
JP5385752B2 (ja) * 2009-10-20 2014-01-08 キヤノン株式会社 画像認識装置、その処理方法及びプログラム
JP5463866B2 (ja) * 2009-11-16 2014-04-09 ソニー株式会社 画像処理装置および画像処理方法、並びにプログラム
WO2012126135A1 (en) * 2011-03-21 2012-09-27 Intel Corporation Method of augmented makeover with 3d face modeling and landmark alignment
JP2014139701A (ja) * 2011-03-30 2014-07-31 Pitmedia Marketings Inc 三次元情報を用いたモザイク画像処理装置、方法およびプログラム
CN104284055A (zh) * 2013-07-01 2015-01-14 索尼公司 图像处理方法、装置以及电子设备
CN108229278B (zh) * 2017-04-14 2020-11-17 深圳市商汤科技有限公司 人脸图像处理方法、装置和电子设备
CN107832843B (zh) * 2017-10-30 2021-09-21 上海寒武纪信息科技有限公司 一种信息处理方法及相关产品
CN108012081B (zh) * 2017-12-08 2020-02-04 北京百度网讯科技有限公司 智能美颜方法、装置、终端和计算机可读存储介质
US11068741B2 (en) * 2017-12-28 2021-07-20 Qualcomm Incorporated Multi-resolution feature description for object recognition
US10699126B2 (en) * 2018-01-09 2020-06-30 Qualcomm Incorporated Adaptive object detection and recognition
CN108073914B (zh) * 2018-01-10 2022-02-18 成都品果科技有限公司 一种动物面部关键点标注方法
US10706577B2 (en) * 2018-03-06 2020-07-07 Fotonation Limited Facial features tracker with advanced training for natural rendering of human faces in real-time
CN108876713B (zh) * 2018-06-28 2022-07-22 北京字节跳动网络技术有限公司 二维模板图像的映射方法、装置、终端设备和存储介质
CN109087239B (zh) * 2018-07-25 2023-03-21 腾讯科技（深圳）有限公司 一种人脸图像处理方法、装置及存储介质
CN109064388A (zh) * 2018-07-27 2018-12-21 北京微播视界科技有限公司 人脸图像效果生成方法、装置和电子设备
CN109003224B (zh) * 2018-07-27 2024-10-15 北京微播视界科技有限公司 基于人脸的形变图像生成方法和装置
CN110826371A (zh) * 2018-08-10 2020-02-21 京东数字科技控股有限公司 一种动物识别方法、装置、介质及电子设备
CN109242765B (zh) * 2018-08-31 2023-03-10 腾讯科技（深圳）有限公司 一种人脸图像处理方法、装置和存储介质
CN111382612A (zh) * 2018-12-28 2020-07-07 北京市商汤科技开发有限公司 动物面部检测方法及装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180204052A1 (en) * 2015-08-28 2018-07-19 Baidu Online Network Technology (Beijing) Co., Ltd. A method and apparatus for human face image processing
CN108876704A (zh) * 2017-07-10 2018-11-23 北京旷视科技有限公司 人脸图像变形的方法、装置及计算机存储介质
CN108805961A (zh) * 2018-06-11 2018-11-13 广州酷狗计算机科技有限公司 数据处理方法、装置及存储介质
CN108833779A (zh) * 2018-06-15 2018-11-16 Oppo广东移动通信有限公司 拍摄控制方法及相关产品
CN109147017A (zh) * 2018-08-28 2019-01-04 百度在线网络技术（北京）有限公司 动态图像生成方法、装置、设备及存储介质
CN109254775A (zh) * 2018-08-30 2019-01-22 广州酷狗计算机科技有限公司 基于人脸的图像处理方法、终端及存储介质
CN109147012A (zh) * 2018-09-20 2019-01-04 麒麟合盛网络技术股份有限公司 图像处理方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113673439A (zh) * 2021-08-23 2021-11-19 平安科技（深圳）有限公司 基于人工智能的宠物狗识别方法、装置、设备及存储介质
CN113673439B (zh) * 2021-08-23 2024-03-05 平安科技（深圳）有限公司 基于人工智能的宠物狗识别方法、装置、设备及存储介质

Also Published As

Publication number Publication date
US20220101645A1 (en) 2022-03-31
JP2022518276A (ja) 2022-03-14
CN111488759A (zh) 2020-08-04
GB2595094B (en) 2023-03-08
JP7383714B2 (ja) 2023-11-20
GB202110696D0 (en) 2021-09-08
GB2595094A (en) 2021-11-17

Similar Documents

Publication Publication Date Title
WO2020151456A1 (zh) 动物脸部的图像处理方法和装置
CN111091610B (zh) 图像处理方法及装置、电子设备和存储介质
CN110689478B (zh) 图像风格化处理方法、装置、电子设备及可读介质
WO2020248900A1 (zh) 全景视频的处理方法、装置及存储介质
CN110062157B (zh) 渲染图像的方法、装置、电子设备和计算机可读存储介质
CN110070495B (zh) 图像的处理方法、装置和电子设备
CN113902636A (zh) 图像去模糊方法及装置、计算机可读介质和电子设备
US12573009B2 (en) Image processing method, image generating method, apparatus, device, and medium
CN115937033A (zh) 图像生成方法、装置及电子设备
WO2024125267A1 (zh) 图像处理方法、装置、计算机可读存储介质、电子设备及计算机程序产品
CN108154515A (zh) 图片展现方法和装置
CN115330610A (zh) 图像处理方法、装置、电子设备以及存储介质
CN106548117B (zh) 一种人脸图像处理方法和装置
WO2020155981A1 (zh) 表情图像效果生成方法、装置和电子设备
CN117095006A (zh) 图像美学评估方法、装置、电子设备及存储介质
CN110942033B (zh) 用于推送信息的方法、装置、电子设备和计算机介质
CN111292245B (zh) 图像处理方法和装置
WO2020215854A1 (zh) 渲染图像的方法、装置、电子设备和计算机可读存储介质
CN111292276B (zh) 图像处理方法和装置
CN110047126B (zh) 渲染图像的方法、装置、电子设备和计算机可读存储介质
CN110059739B (zh) 图像合成方法、装置、电子设备和计算机可读存储介质
CN110070482B (zh) 图像处理方法、装置和计算机可读存储介质
CN107864333A (zh) 图像处理方法、装置、终端及存储介质
WO2021073204A1 (zh) 对象的显示方法、装置、电子设备及计算机可读存储介质
US20220319062A1 (en) Image processing method, apparatus, electronic device and computer readable storage medium

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: 19911817

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021542562

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 202110696

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20191227

WWE Wipo information: entry into national phase

Ref document number: 2110696.8

Country of ref document: GB

NENP Non-entry into the national phase

Ref country code: DE

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 15/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19911817

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 2110696.8

Country of ref document: GB