CN111369427A - Image processing method, image processing device, readable medium and electronic equipment - Google Patents
Image processing method, image processing device, readable medium and electronic equipment Download PDFInfo
- Publication number
- CN111369427A CN111369427A CN202010152455.0A CN202010152455A CN111369427A CN 111369427 A CN111369427 A CN 111369427A CN 202010152455 A CN202010152455 A CN 202010152455A CN 111369427 A CN111369427 A CN 111369427A
- Authority
- CN
- China
- Prior art keywords
- image
- target face
- recognition model
- mask
- face image
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 47
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 46
- 230000004927 fusion Effects 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 18
- 230000006870 function Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The disclosure relates to an image processing method, an image processing device, a readable medium and an electronic device, and relates to the technical field of image processing, wherein the method comprises the following steps: the method comprises the steps of identifying an image to be processed according to a preset face identification algorithm to obtain a target face image, inputting the target face image into a pre-trained image identification model to obtain key points and mask masks of specified parts in the target face image output by the image identification model, and executing preset operation on the specified parts in the target face image according to the key points and the mask masks. According to the method, the target face image is firstly identified, the key points and the mask in the target face image are determined through the image identification model, the target face image is subjected to preset operation according to the key points and the mask, the key points and the mask can be simultaneously determined according to the target face image, the identification accuracy of the key points and the mask is improved, the calculation amount is reduced, and the image processing efficiency and accuracy are improved.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, a readable medium, and an electronic device.
Background
With the continuous development of terminal technology and image processing technology, image processing operations provided on a terminal are more and more abundant. The user can take pictures and make video at any time and any place, and share the pictures through the network. Accordingly, various kinds of beauty treatment for the face in the image are generated to meet various demands of the user. When performing the face beautifying processing on the face in the image, it is necessary to identify each part (for example, eyes, mouth, nose, ears, etc.) of the face in the image, and then perform the face beautifying processing on each part. In general, key points of a face in an image are acquired, and then a mask (chinese: mask) of a designated part in the image is obtained according to the key points. The mask can divide the designated part from the image, so that the designated part is subjected to beautifying processing. The method has large calculation amount and low speed, and reduces the efficiency of image processing.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, the present disclosure provides a method of image processing, the method comprising:
identifying an image to be processed according to a preset face identification algorithm to obtain a target face image;
inputting the target face image into a pre-trained image recognition model to obtain key points and mask of a specified part in the target face image output by the image recognition model;
and executing preset operation on the specified part in the target face image according to the key point and the mask.
In a second aspect, the present disclosure provides an image processing apparatus, the apparatus comprising:
the recognition module is used for recognizing the image to be processed according to a preset face recognition algorithm so as to obtain a target face image;
the acquisition module is used for inputting the target face image into a pre-trained image recognition model so as to acquire key points and mask of a specified part in the target face image output by the image recognition model;
and the processing module is used for executing preset operation on the specified part in the target face image according to the key point and the mask.
In a third aspect, the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processing apparatus, performs the steps of the method of the first aspect of the present disclosure.
In a fourth aspect, the present disclosure provides an electronic device comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to implement the steps of the method of the first aspect of the present disclosure.
According to the technical scheme, the method comprises the steps of firstly identifying the target face image to be processed according to a preset face identification algorithm to obtain the target face image, then using the target face image as the input of a pre-trained image identification model to obtain the key points and the mask of the specified part in the target face image output by the image identification model, and finally executing preset operation on the specified part in the target face image according to the key points and the mask. According to the method, the target face image is firstly identified, the key points and the mask in the target face image are determined through the image identification model, the target face image is subjected to preset operation according to the key points and the mask, the key points and the mask can be simultaneously determined according to the target face image, the key points and the mask can be mutually verified, the identification accuracy of the key points and the mask is improved, the calculation amount is reduced, and the efficiency and the accuracy of image processing are improved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
In the drawings:
FIG. 1 is a flow diagram illustrating an image processing method according to an exemplary embodiment;
FIG. 2 is a flow diagram illustrating another method of image processing according to an exemplary embodiment;
FIG. 3 is a flow diagram illustrating the training of an image recognition model in accordance with an exemplary embodiment;
FIG. 4 is a flow diagram illustrating training of another image recognition model in accordance with an exemplary embodiment;
FIG. 5 is a block diagram illustrating an image processing apparatus according to an exemplary embodiment;
FIG. 6 is a block diagram illustrating another image processing apparatus according to an exemplary embodiment;
FIG. 7 is a block diagram of an electronic device shown in accordance with an example embodiment.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
Fig. 1 is a flow chart illustrating an image processing method according to an exemplary embodiment, as shown in fig. 1, the method including:
For example, the image to be processed may be an image captured by the terminal device by the user (e.g., a shot photo, or a certain frame in a shot video), or may be an image selected by the user on the terminal device (e.g., an image selected on a display interface of the terminal device). The image to be processed can be identified according to a preset face identification algorithm so as to obtain a target face image comprising a face. It can be understood that the image to be processed may include other information besides the face, so that the face information in the image to be processed may be extracted by a face recognition algorithm to obtain the target face image. The target face image may be an image obtained by directly capturing an area including a face in the image to be processed, or an image obtained by capturing an area including a face in the image to be processed and then performing processing such as denoising and amplifying on the captured image.
And 102, inputting the target face image into a pre-trained image recognition model to obtain key points and mask of a specified part in the target face image output by the image recognition model.
Illustratively, a target face image is used as an input of a pre-trained image recognition model, wherein the image recognition model may be a Convolutional Neural Network (CNN) trained according to a preset sample input set and a sample output set, the image recognition model can extract a plurality of Feature maps (english: Feature maps) of the target face image, and simultaneously output Key points (english: Key points) and masks of specified parts in the target face image according to the plurality of Feature maps, and the Key points and the masks can be verified mutually, so that the recognition accuracy of the Key points and the masks is improved. Instead of obtaining the key points of the designated part first and then determining the mask of the designated part in the target face image according to the key points of the designated part, two models are not needed, and two times of feature extraction are not needed, so that the calculation amount can be reduced, and the processing speed can be improved. The designated parts may be preset or determined according to specific requirements of a user, and different designated parts may correspond to different image recognition models, that is, an image recognition model corresponding to each designated part in a plurality of designated parts may be trained in advance. The designated sites may include, for example: the eyebrow, eye, mouth, nose, ear, or eye corner, mouth corner, nose, and nose head. The mask output by the image recognition model can be understood as a two-dimensional matrix corresponding to the target face image, each element in the two-dimensional matrix corresponds to each pixel point in the target face image, the element in the two-dimensional matrix can be 0 or 1, if a certain element is 0, it indicates that the pixel point of the element corresponding to the target face image does not belong to the designated part, and if a certain element is 1, it indicates that the pixel point of the element corresponding to the target face image belongs to the designated part. It should be noted that the convolutional neural network described above is only one example of the image recognition model according to the embodiment of the present disclosure, and the present disclosure is not limited thereto, and may also include other various neural networks.
And 103, executing preset operation on a specified position in the target face image according to the key point and the mask.
For example, after the key points and the mask of the designated part in the target face image are obtained, a preset operation may be performed on the target face image to implement a special effect operation on the designated part in the target face image. Taking the designated region as an eye region for example, then the key points of the eyes and the mask of the eyes in the target face image are determined in step 102. Then the positions of the eyes in the target face image can be determined according to the key points of the eyes, and then the following steps are implemented on the positions of the eyes: and presetting operations such as pasting paper, drawing eye lines and the like. The area where the eyes in the target face image are located can be determined according to the mask of the eyes, and then the following steps are carried out on the area of the eyes: and performing preset operations such as liquefaction, denoising, amplification, smoothing and the like. After the preset operation is executed on the specific position in the target face image, the target face image after the preset operation is executed can be stored in the specified storage path of the terminal device, and the target face image after the preset operation is executed can be shared through the network.
In summary, the present disclosure first identifies a target face image to be processed according to a preset face identification algorithm to obtain the target face image, then uses the target face image as an input of a pre-trained image identification model to obtain a key point and a mask of a specified portion in the target face image output by the image identification model, and finally performs a preset operation on the specified portion in the target face image according to the key point and the mask. According to the method, the target face image is firstly identified, the key points and the mask in the target face image are determined through the image identification model, the target face image is subjected to preset operation according to the key points and the mask, the key points and the mask can be simultaneously determined according to the target face image, the key points and the mask can be mutually verified, the identification accuracy of the key points and the mask is improved, the calculation amount is reduced, and the efficiency and the accuracy of image processing are improved.
Specifically, the implementation manner of step 103 may include:
in the first mode, a first preset operation is executed at the area indicated by the mask in the target face image. And/or the presence of a gas in the gas,
in the second mode, a second preset operation is executed at the position indicated by the key point in the target face image.
In a specific application scenario, preset operations may be performed on the target face image according to the key points and the mask of the specified portion determined in step 102. The preset operation may be divided into a first preset operation for the mask and a second preset operation for the key point. The first preset operation may be understood as an operation on the area where the designated portion is located, for example, operations such as liquefaction, denoising, amplification, smoothing and the like may be performed on all pixels in the area where the designated portion is located. The second preset operation may be understood as an operation on the position indicated by the key point of the designated portion, for example: the operation is performed by referring to the key points of the designated portion as a coordinate reference, such as a sticker operation based on the coordinates of the key points, and a special effect operation based on the coordinates of the key points.
FIG. 2 is a flow diagram illustrating another image processing method according to an exemplary embodiment, where the image recognition model is a convolutional neural network, as shown in FIG. 2, and step 102 may include the following steps:
For example, the image recognition model may be a convolutional neural network, which may include, for example, a convolutional layer, a feedback layer, a fully-connected layer, and an output layer. Firstly, inputting a target face image into a convolution layer, and extracting the characteristics of the convolution layer, namely the preset number of characteristic images of the target face image, from the target face image through the convolution layer. And then, according to the part area corresponding to the designated part, dividing each feature map in a preset number of feature maps to obtain a sub-feature map corresponding to each feature map. Each sub-feature map is a part of the corresponding feature map, i.e. each sub-feature map comprises only elements of the corresponding feature map indicated by the region of interest. The part region may be understood as a region corresponding to a specified part obtained by statistics by labeling a large number of face images in advance, and may be a coordinate range. Taking the designated part as an eye for example, the eye is usually located in the upper center part of the face image, the normalized abscissa may be 0.2-0.8, and the normalized ordinate may be 0.3-0.6, so that the region of the part corresponding to the eye is (0.2-0.8, 0.3-0.6). Inputting the target face image into a convolution layer to obtain N500 × 500 feature maps, then segmenting each feature map in the N feature maps according to a part region corresponding to an eye, and intercepting elements of which the abscissa is 20% -80% and the ordinate is 30% -60% in each feature map to obtain N150 × 300 sub-feature maps.
And 1023, performing feature fusion on a preset number of feature graphs according to the image recognition model to obtain key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain a mask.
Furthermore, through a feedback layer in the image recognition model, combining the last feedback layer characteristic and the next feedback layer characteristic, extracting the current feedback layer characteristic from a preset number of characteristic graphs output by the convolutional layer, and then abstracting the feedback layer characteristic through a full connection layer, so as to realize the characteristic fusion of the preset number of characteristic graphs, and obtain the key point of the specified part in the target face image. Meanwhile, the feedback layer in the image recognition model can also combine the previous feedback layer characteristic and the next feedback layer characteristic to extract the current feedback layer characteristic from the preset number of sub-characteristic graphs output by the convolution layer, and then abstract the feedback layer characteristic through the full-connection layer to realize the characteristic fusion of the preset number of sub-characteristic graphs so as to obtain the mask of the specified part in the target face image. And finally, outputting the key points and the mask through an output layer.
The method can be understood that the image recognition model can simultaneously extract the key points and the mask of the specified part in the target face image according to the target face image, the basis of obtaining the key points and the mask is the same (namely the same target face image), the key points and the mask can be mutually verified, so that the recognition accuracy of the key points and the mask is improved, only one image recognition model needs to be established, only one-time feature extraction is needed, the operation amount can be reduced, and the processing speed is improved.
FIG. 3 is a flow chart illustrating training of an image recognition model according to an exemplary embodiment, where the image recognition model is trained as shown in FIG. 3 by:
And 105, taking the sample input set as the input of the image recognition model, and taking the sample output set as the output of the image recognition model so as to train the image recognition model.
In a specific application scenario, different designated parts may correspond to different image recognition models, and an image recognition model corresponding to each designated part may be trained in advance. The image recognition model may be trained by first obtaining a sample input set and a sample output set. The sample input set comprises a plurality of sample inputs, each sample input can be a sample image, the sample output set comprises sample outputs which are in one-to-one correspondence with the sample inputs in the sample input set, and each sample output is a key point and a mask of a specified part marked by the sample image in the corresponding sample input. For example, a large number of sample images containing human faces may be obtained on the internet, and then the sample images are labeled, and the key points and masks in each sample image are labeled and output as corresponding samples. When the image recognition model is trained, the sample input set can be used as the input of the image recognition model, and the sample output set can be used as the output of the image recognition model for training, so that when the image recognition model is input into the sample input set, the key points and the mask output by the image recognition model can be matched with the sample output set.
FIG. 4 is a flow chart illustrating another training of an image recognition model according to an exemplary embodiment, as shown in FIG. 4, step 105 includes:
And 1053, performing feature fusion on the preset number of feature graphs according to the initial convolutional neural network to obtain initial key points, and performing feature fusion on the preset number of sub-feature graphs according to the image recognition model to obtain an initial mask.
And 1054, comparing the initial key points with the key points of the appointed parts marked by the sample image, and comparing the initial mask with the mask of the appointed parts marked by the sample image so as to correct the parameters of each neuron in the initial convolutional neural network.
And 1055, repeating 1051 to 1054 until the initial convolutional neural network meets the preset condition.
And 1056, taking the initial convolutional neural network meeting the preset conditions as an image recognition model.
Specifically, an initial convolutional neural network may be pre-selected (the depth of the convolutional neural network, the parameters of the neurons, etc. may be selected according to specific requirements). Taking any sample image as an input of a convolutional layer of an initial convolutional neural network to obtain a preset number of feature maps output by the convolutional layer, and then segmenting each feature map in the preset number of feature maps according to a part area corresponding to a specified part to obtain a sub-feature map corresponding to each feature map in the preset number of feature maps. And performing feature fusion on a preset number of feature graphs according to the initial convolutional neural network to obtain initial key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain an initial mask.
Comparing the initial key points with the key points marked by the sample image, and comparing the initial mask with the mask marked by the sample imageA comparison is made to modify the parameters of each neuron in the initial convolutional neural network. The parameters of the neuron may be, for example, the Weight (Weight) and the Bias (Bias) of the neuron. And repeating the steps to enable the initial convolutional neural network to meet the preset conditions, and finally taking the initial convolutional neural network meeting the preset conditions as an image recognition model. The predetermined condition may be, for example, a predetermined loss function minimum, and the loss function may be, for example,/1Loss function or2A loss function.
In summary, the present disclosure first identifies a target face image to be processed according to a preset face identification algorithm to obtain the target face image, then uses the target face image as an input of a pre-trained image identification model to obtain a key point and a mask of a specified portion in the target face image output by the image identification model, and finally performs a preset operation on the specified portion in the target face image according to the key point and the mask. According to the method, the target face image is firstly identified, the key points and the mask in the target face image are determined through the image identification model, the target face image is subjected to preset operation according to the key points and the mask, the key points and the mask can be simultaneously determined according to the target face image, the key points and the mask can be mutually verified, the identification accuracy of the key points and the mask is improved, the calculation amount is reduced, and the efficiency and the accuracy of image processing are improved.
Fig. 5 is a block diagram illustrating an image processing apparatus according to an exemplary embodiment, and as shown in fig. 5, the apparatus 200 includes:
the recognition module 201 is configured to recognize the image to be processed according to a preset face recognition algorithm to obtain a target face image.
The obtaining module 202 is configured to input the target face image into a pre-trained image recognition model, so as to obtain a key point and a mask of a specified portion in the target face image output by the image recognition model.
And the processing module 203 is configured to execute a preset operation on a specified position in the target face image according to the key point and the mask.
Optionally, the processing module 203 may be configured to perform the following steps:
and executing a first preset operation at the area indicated by the mask in the target face image. And/or the presence of a gas in the gas,
and executing a second preset operation at the position indicated by the key point in the target face image.
Fig. 6 is a block diagram illustrating another image processing apparatus according to an exemplary embodiment, and as shown in fig. 6, the obtaining module 202 includes:
the input sub-module 2021 is configured to input the target face image into the convolution layer of the image recognition model to obtain a preset number of feature maps input by the convolution layer of the image recognition model.
The segmentation sub-module 2022 is configured to segment each feature map of the preset number of feature maps according to a region corresponding to the designated region, so as to obtain a preset number of sub-feature maps.
The fusion sub-module 2023 is configured to perform feature fusion on the preset number of feature maps according to the image recognition model to obtain key points, and perform feature fusion on the preset number of sub-feature maps according to the image recognition model to obtain a mask.
In the above embodiment, the image recognition model is trained as follows:
step A) a sample input set and a sample output set are obtained, wherein each sample input in the sample input set comprises a sample image, the sample output set comprises a sample output corresponding to each sample input, and each sample output comprises a key point and a mask of a specified part marked by the corresponding sample image.
And B) taking the sample input set as the input of the image recognition model, and taking the sample output set as the output of the image recognition model so as to train the image recognition model.
Further, the implementation manner of step B) may include:
step B1) inputting each sample image into the convolution layer of the initial convolutional neural network to obtain a preset number of feature maps output by the convolution layer of the initial convolutional neural network.
Step B2) according to the area corresponding to the appointed area, each characteristic diagram in the preset number of characteristic diagrams is divided to obtain the preset number of sub-characteristic diagrams.
And step B3) performing feature fusion on a preset number of feature graphs according to the initial convolutional neural network to obtain initial key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain an initial mask.
Step B4) the initial key points are compared with the key points of the appointed parts marked by the sample image, and the initial mask is compared with the mask of the appointed parts marked by the sample image, so as to correct the parameters of each neuron in the initial convolutional neural network.
Step B5) repeatedly executing the steps B1) to B4) until the initial convolutional neural network satisfies the preset condition.
Step B6) takes the initial convolutional neural network satisfying the preset condition as the image recognition model.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In summary, the present disclosure first identifies a target face image to be processed according to a preset face identification algorithm to obtain the target face image, then uses the target face image as an input of a pre-trained image identification model to obtain a key point and a mask of a specified portion in the target face image output by the image identification model, and finally performs a preset operation on the specified portion in the target face image according to the key point and the mask. According to the method, the target face image is firstly identified, the key points and the mask in the target face image are determined through the image identification model, the target face image is subjected to preset operation according to the key points and the mask, the key points and the mask can be simultaneously determined according to the target face image, the key points and the mask can be mutually verified, the identification accuracy of the key points and the mask is improved, the calculation amount is reduced, and the efficiency and the accuracy of image processing are improved.
Referring now to FIG. 7, a block diagram of an electronic device 300 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device (i.e., the execution subject of the above-described image processing method) in the embodiments of the present disclosure may be a server, which may be, for example, a local server or a cloud server, or may be a terminal device, including, for example, but not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. The user can log in the server to upload the image to be processed, can directly upload the image to be processed through the terminal equipment, or acquire the image to be processed through the terminal equipment. The electronic device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 7, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 7 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 309, or installed from the storage means 308, or installed from the ROM 302. The computer program, when executed by the processing device 301, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the terminal devices, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText transfer protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: identifying an image to be processed according to a preset face identification algorithm to obtain a target face image; inputting the target face image into a pre-trained image recognition model to obtain key points and mask of a specified part in the target face image output by the image recognition model; and executing preset operation on the specified part in the target face image according to the key point and the mask.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. The name of a module does not in some cases constitute a limitation of the module itself, and for example, a recognition module may also be described as a "module that recognizes a target face image".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Example 1 provides an image processing method according to one or more embodiments of the present disclosure, including: identifying an image to be processed according to a preset face identification algorithm to obtain a target face image; inputting the target face image into a pre-trained image recognition model to obtain key points and mask of a specified part in the target face image output by the image recognition model; and executing preset operation on the specified part in the target face image according to the key point and the mask.
Example 2 provides the method of example 1, wherein performing a preset operation on the specified part in the target face image according to the key point and the mask includes: executing a first preset operation at the area indicated by the mask in the target face image; and/or executing a second preset operation at the position indicated by the key point in the target face image.
Example 3 provides the method of example 1, where the image recognition model is a convolutional neural network, and the inputting the target face image into a pre-trained image recognition model to obtain the key points and mask masks of the specified parts in the target face image output by the image recognition model includes: inputting the target face image into a convolution layer of the image recognition model to obtain a preset number of feature maps input by the convolution layer of the image recognition model; according to the part area corresponding to the designated part, dividing each feature map in a preset number of feature maps to obtain a preset number of sub-feature maps; and performing feature fusion on a preset number of feature graphs according to the image recognition model to obtain the key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain the mask.
Example 4 provides the method of any one of examples 1 to 3, the image recognition model being trained by: acquiring a sample input set and a sample output set, wherein each sample input in the sample input set comprises a sample image, the sample output set comprises a sample output corresponding to each sample input, and each sample output comprises a key point and a mask of the specified part marked by the corresponding sample image; and taking the sample input set as the input of the image recognition model, and taking the sample output set as the output of the image recognition model so as to train the image recognition model.
Example 5 provides the method of example 4, the taking the set of sample inputs as inputs to the image recognition model and the set of sample outputs as outputs of the image recognition model to train the image recognition model, comprising: inputting each sample image into a convolutional layer of an initial convolutional neural network to obtain a preset number of characteristic graphs output by the convolutional layer of the initial convolutional neural network; according to the part area corresponding to the designated part, dividing each feature map in a preset number of feature maps to obtain a preset number of sub-feature maps; performing feature fusion on a preset number of feature graphs according to the initial convolutional neural network to obtain initial key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain an initial mask; comparing the initial key points with the key points of the specified positions marked by the sample image, and comparing the initial mask with the mask of the specified positions marked by the sample image so as to correct the parameters of each neuron in the initial convolutional neural network; repeatedly executing the step of inputting each sample image into the convolution layer of the initial convolutional neural network to obtain a preset number of feature maps output by the convolution layer of the initial convolutional neural network, comparing the initial key points with the key points of the specified positions marked by the sample image, and comparing the initial mask with the mask of the specified positions marked by the sample image to correct the parameters of each neuron in the initial convolutional neural network until the initial convolutional neural network meets a preset condition; and taking the initial convolutional neural network meeting the preset condition as the image recognition model.
Example 6 provides an image processing apparatus according to one or more embodiments of the present disclosure, including: the recognition module is used for recognizing the image to be processed according to a preset face recognition algorithm so as to obtain a target face image; the acquisition module is used for inputting the target face image into a pre-trained image recognition model so as to acquire key points and mask of a specified part in the target face image output by the image recognition model; and the processing module is used for executing preset operation on the specified part in the target face image according to the key point and the mask.
Example 7 provides the apparatus of example 6, the processing module to: executing a first preset operation at the area indicated by the mask in the target face image; and/or executing a second preset operation at the position indicated by the key point in the target face image.
Example 8 provides the apparatus of example 6, the image recognition model being a convolutional neural network, the acquisition module comprising: the input submodule is used for inputting the target face image into the convolution layer of the image recognition model so as to obtain a preset number of characteristic graphs input by the convolution layer of the image recognition model; the segmentation submodule is used for segmenting each feature map in a preset number of feature maps according to the part area corresponding to the designated part to obtain a preset number of sub-feature maps; and the fusion submodule is used for performing feature fusion on a preset number of feature graphs according to the image recognition model to obtain the key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain the mask.
Example 9 provides a computer readable medium having stored thereon a computer program that, when executed by a processing apparatus, implements the steps of the methods of examples 1-5, in accordance with one or more embodiments of the present disclosure.
Example 10 provides, in accordance with one or more embodiments of the present disclosure, an electronic device comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to implement the steps of the methods of examples 1 to 5.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims (10)
1. An image processing method, characterized in that the method comprises:
identifying an image to be processed according to a preset face identification algorithm to obtain a target face image;
inputting the target face image into a pre-trained image recognition model to obtain key points and mask of a specified part in the target face image output by the image recognition model;
and executing preset operation on the specified part in the target face image according to the key point and the mask.
2. The method according to claim 1, wherein said performing a preset operation on the designated part in the target face image according to the key point and the mask comprises:
executing a first preset operation at the area indicated by the mask in the target face image; and/or the presence of a gas in the gas,
and executing a second preset operation at the position indicated by the key point in the target face image.
3. The method of claim 1, wherein the image recognition model is a convolutional neural network, and the inputting the target face image into a pre-trained image recognition model to obtain the key points and mask of the specified part in the target face image output by the image recognition model comprises:
inputting the target face image into a convolution layer of the image recognition model to obtain a preset number of feature maps input by the convolution layer of the image recognition model;
according to the part area corresponding to the designated part, dividing each feature map in a preset number of feature maps to obtain a preset number of sub-feature maps;
and performing feature fusion on a preset number of feature graphs according to the image recognition model to obtain the key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain the mask.
4. The method of any of claims 1-3, wherein the image recognition model is trained by:
acquiring a sample input set and a sample output set, wherein each sample input in the sample input set comprises a sample image, the sample output set comprises a sample output corresponding to each sample input, and each sample output comprises a key point and a mask of the specified part marked by the corresponding sample image;
and taking the sample input set as the input of the image recognition model, and taking the sample output set as the output of the image recognition model so as to train the image recognition model.
5. The method of claim 4, wherein the using the sample input set as an input to the image recognition model and the sample output set as an output to the image recognition model to train the image recognition model comprises:
inputting each sample image into a convolutional layer of an initial convolutional neural network to obtain a preset number of characteristic graphs output by the convolutional layer of the initial convolutional neural network;
according to the part area corresponding to the designated part, dividing each feature map in a preset number of feature maps to obtain a preset number of sub-feature maps;
performing feature fusion on a preset number of feature graphs according to the initial convolutional neural network to obtain initial key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain an initial mask;
comparing the initial key points with the key points of the specified positions marked by the sample image, and comparing the initial mask with the mask of the specified positions marked by the sample image so as to correct the parameters of each neuron in the initial convolutional neural network;
repeatedly executing the step of inputting each sample image into the convolution layer of the initial convolutional neural network to obtain a preset number of feature maps output by the convolution layer of the initial convolutional neural network, comparing the initial key points with the key points of the specified positions marked by the sample image, and comparing the initial mask with the mask of the specified positions marked by the sample image to correct the parameters of each neuron in the initial convolutional neural network until the initial convolutional neural network meets a preset condition;
and taking the initial convolutional neural network meeting the preset condition as the image recognition model.
6. An image processing apparatus, characterized in that the apparatus comprises:
the recognition module is used for recognizing the image to be processed according to a preset face recognition algorithm so as to obtain a target face image;
the acquisition module is used for inputting the target face image into a pre-trained image recognition model so as to acquire key points and mask of a specified part in the target face image output by the image recognition model;
and the processing module is used for executing preset operation on the specified part in the target face image according to the key point and the mask.
7. The apparatus of claim 6, wherein the processing module is configured to:
executing a first preset operation at the area indicated by the mask in the target face image; and/or the presence of a gas in the gas,
and executing a second preset operation at the position indicated by the key point in the target face image.
8. The apparatus of claim 6, wherein the image recognition model is a convolutional neural network, and the obtaining module comprises:
the input submodule is used for inputting the target face image into the convolution layer of the image recognition model so as to obtain a preset number of characteristic graphs input by the convolution layer of the image recognition model;
the segmentation submodule is used for segmenting each feature map in a preset number of feature maps according to the part area corresponding to the designated part to obtain a preset number of sub-feature maps;
and the fusion submodule is used for performing feature fusion on a preset number of feature graphs according to the image recognition model to obtain the key points, and performing feature fusion on a preset number of sub-feature graphs according to the image recognition model to obtain the mask.
9. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by processing means, carries out the steps of the method of any one of claims 1 to 5.
10. An electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010152455.0A CN111369427B (en) | 2020-03-06 | 2020-03-06 | Image processing method, image processing device, readable medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010152455.0A CN111369427B (en) | 2020-03-06 | 2020-03-06 | Image processing method, image processing device, readable medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111369427A true CN111369427A (en) | 2020-07-03 |
| CN111369427B CN111369427B (en) | 2023-04-18 |
Family
ID=71206746
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010152455.0A Active CN111369427B (en) | 2020-03-06 | 2020-03-06 | Image processing method, image processing device, readable medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111369427B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931908A (en) * | 2020-07-23 | 2020-11-13 | 北京电子科技学院 | Face image automatic generation method based on face contour |
| CN112381709A (en) * | 2020-11-13 | 2021-02-19 | 北京字节跳动网络技术有限公司 | Image processing method, model training method, device, equipment and medium |
| CN112465717A (en) * | 2020-11-25 | 2021-03-09 | 北京字跳网络技术有限公司 | Face image processing model training method and device, electronic equipment and medium |
| CN112633119A (en) * | 2020-12-17 | 2021-04-09 | 北京赢识科技有限公司 | Human body attribute identification method and device, electronic equipment and medium |
| CN113034580A (en) * | 2021-03-05 | 2021-06-25 | 北京字跳网络技术有限公司 | Image information detection method and device and electronic equipment |
| CN113065408A (en) * | 2021-03-09 | 2021-07-02 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN113240696A (en) * | 2021-05-20 | 2021-08-10 | 推想医疗科技股份有限公司 | Image processing method and device, model training method and device, and electronic equipment |
| CN113284219A (en) * | 2021-06-10 | 2021-08-20 | 北京字跳网络技术有限公司 | Image processing method, device, equipment and storage medium |
| CN113378696A (en) * | 2021-06-08 | 2021-09-10 | 北京百度网讯科技有限公司 | Image processing method, device, equipment and storage medium |
| CN113808044A (en) * | 2021-09-17 | 2021-12-17 | 北京百度网讯科技有限公司 | Encryption mask determining method, device, equipment and storage medium |
| WO2023040749A1 (en) * | 2021-09-16 | 2023-03-23 | 北京字跳网络技术有限公司 | Image processing method and apparatus, electronic device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229575A (en) * | 2018-01-19 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | For detecting the method and apparatus of target |
| US20180253622A1 (en) * | 2017-03-06 | 2018-09-06 | Honda Motor Co., Ltd. | Systems for performing semantic segmentation and methods thereof |
| CN109978930A (en) * | 2019-03-27 | 2019-07-05 | 杭州相芯科技有限公司 | A kind of stylized human face three-dimensional model automatic generation method based on single image |
| CN110399849A (en) * | 2019-07-30 | 2019-11-01 | 北京市商汤科技开发有限公司 | Image processing method and device, processor, electronic equipment and storage medium |
-
2020
- 2020-03-06 CN CN202010152455.0A patent/CN111369427B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180253622A1 (en) * | 2017-03-06 | 2018-09-06 | Honda Motor Co., Ltd. | Systems for performing semantic segmentation and methods thereof |
| CN108229575A (en) * | 2018-01-19 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | For detecting the method and apparatus of target |
| CN109978930A (en) * | 2019-03-27 | 2019-07-05 | 杭州相芯科技有限公司 | A kind of stylized human face three-dimensional model automatic generation method based on single image |
| CN110399849A (en) * | 2019-07-30 | 2019-11-01 | 北京市商汤科技开发有限公司 | Image processing method and device, processor, electronic equipment and storage medium |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931908B (en) * | 2020-07-23 | 2024-06-11 | 北京电子科技学院 | Face image automatic generation method based on face contour |
| CN111931908A (en) * | 2020-07-23 | 2020-11-13 | 北京电子科技学院 | Face image automatic generation method based on face contour |
| CN112381709B (en) * | 2020-11-13 | 2022-06-21 | 北京字节跳动网络技术有限公司 | Image processing method, model training method, device, equipment and medium |
| CN112381709A (en) * | 2020-11-13 | 2021-02-19 | 北京字节跳动网络技术有限公司 | Image processing method, model training method, device, equipment and medium |
| CN112465717A (en) * | 2020-11-25 | 2021-03-09 | 北京字跳网络技术有限公司 | Face image processing model training method and device, electronic equipment and medium |
| CN112465717B (en) * | 2020-11-25 | 2024-05-31 | 北京字跳网络技术有限公司 | Face image processing model training method, device, electronic equipment and medium |
| CN112633119A (en) * | 2020-12-17 | 2021-04-09 | 北京赢识科技有限公司 | Human body attribute identification method and device, electronic equipment and medium |
| CN113034580A (en) * | 2021-03-05 | 2021-06-25 | 北京字跳网络技术有限公司 | Image information detection method and device and electronic equipment |
| CN113065408A (en) * | 2021-03-09 | 2021-07-02 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN113240696A (en) * | 2021-05-20 | 2021-08-10 | 推想医疗科技股份有限公司 | Image processing method and device, model training method and device, and electronic equipment |
| CN113240696B (en) * | 2021-05-20 | 2022-02-08 | 推想医疗科技股份有限公司 | Image processing method and device, model training method and device, and electronic equipment |
| CN113378696A (en) * | 2021-06-08 | 2021-09-10 | 北京百度网讯科技有限公司 | Image processing method, device, equipment and storage medium |
| CN113284219A (en) * | 2021-06-10 | 2021-08-20 | 北京字跳网络技术有限公司 | Image processing method, device, equipment and storage medium |
| WO2023040749A1 (en) * | 2021-09-16 | 2023-03-23 | 北京字跳网络技术有限公司 | Image processing method and apparatus, electronic device, and storage medium |
| JP2022101645A (en) * | 2021-09-17 | 2022-07-06 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド | Encryption mask determination method, image recognition method, model training method, apparatus, electronic device, storage medium, and computer program |
| JP7282474B2 (en) | 2021-09-17 | 2023-05-29 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド | Encryption mask determination method, encryption mask determination device, electronic device, storage medium, and computer program |
| CN113808044A (en) * | 2021-09-17 | 2021-12-17 | 北京百度网讯科技有限公司 | Encryption mask determining method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111369427B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111369427B (en) | Image processing method, image processing device, readable medium and electronic equipment | |
| CN111368685B (en) | Method and device for identifying key points, readable medium and electronic equipment | |
| CN109829432B (en) | Method and apparatus for generating information | |
| US11443438B2 (en) | Network module and distribution method and apparatus, electronic device, and storage medium | |
| CN111414879B (en) | Face shielding degree identification method and device, electronic equipment and readable storage medium | |
| CN113313064A (en) | Character recognition method and device, readable medium and electronic equipment | |
| CN109784304B (en) | Method and apparatus for labeling dental images | |
| CN111915480B (en) | Method, apparatus, device and computer readable medium for generating feature extraction network | |
| CN111402122A (en) | Image mapping processing method and device, readable medium and electronic equipment | |
| CN110826567B (en) | Optical character recognition method, device, equipment and storage medium | |
| CN111696176A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN110059623B (en) | Method and apparatus for generating information | |
| CN110211195B (en) | Method, device, electronic equipment and computer-readable storage medium for generating image set | |
| CN111950570B (en) | Target image extraction method, neural network training method and device | |
| CN115311178A (en) | Image splicing method, device, equipment and medium | |
| CN112418249A (en) | Mask image generation method and device, electronic equipment and computer readable medium | |
| CN112101258A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN109829431B (en) | Method and apparatus for generating information | |
| CN111126159A (en) | Method, apparatus, electronic device, and medium for tracking pedestrian in real time | |
| CN110619602B (en) | Image generation method and device, electronic equipment and storage medium | |
| CN110288691B (en) | Method, apparatus, electronic device and computer-readable storage medium for rendering image | |
| CN112418054A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN110765304A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN111353470B (en) | Image processing method and device, readable medium and electronic equipment | |
| CN114049417B (en) | Virtual character image generation method and device, readable medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |