CN115798005A - Reference photo processing method and device, processor and electronic equipment - Google Patents
Reference photo processing method and device, processor and electronic equipment Download PDFInfo
- Publication number
- CN115798005A CN115798005A CN202211502432.3A CN202211502432A CN115798005A CN 115798005 A CN115798005 A CN 115798005A CN 202211502432 A CN202211502432 A CN 202211502432A CN 115798005 A CN115798005 A CN 115798005A
- Authority
- CN
- China
- Prior art keywords
- age
- photo
- picture
- reference picture
- value
- 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.)
- Pending
Links
Images
Abstract
The application discloses a reference photo processing method and device, a processor and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: respectively acquiring identity characteristic information corresponding to a reference photo and a field photo, wherein the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the field photo is a photo of the target object acquired on the field, and the target object is an object to be subjected to face recognition; respectively acquiring age characteristic information corresponding to the reference picture and the live picture; and updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information. By the method and the device, the problem that the accuracy of face recognition by the face recognition system through the reference picture is low due to the fact that the reference picture of the user in the face recognition system is difficult to update according to the age information in the related technology is solved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a method and a device for processing a reference picture, a processor and electronic equipment.
Background
In recent years, the technology and application of artificial intelligence are rapidly developed, and the technology of extracting biological characteristic information by means of an artificial intelligence method to perform identity authentication is gradually mature. In addition, the human face is widely used in the identity authentication scene as the inherent biological feature information. However, the face of a user may change greatly with the age, and therefore, in the practical application process, as the age increases, a reference picture stored in the face recognition system by the user may have a large difference from a real face picture, thereby causing a failure in face recognition. Therefore, the age difference between the reference photo and the real photo in the user face recognition system is evaluated, the user is reminded of updating the reference photo in time, and the method has important significance for improving the performance of the face recognition system.
Moreover, a face comparison module in the face recognition system generally matches a reference photo stored in the system with a field photo collected by a user to confirm the identity of the user, so that the quality of the reference photo directly affects the performance of the system. The reference quality can be evaluated from two angles: firstly, the quality of the picture, such as whether the face picture is clear or not, whether the face posture is normal or not, and the like; the second is the difference between the benchmark photo and the user himself, which is caused by the face change caused by the user's own factors (such as the age increase). However, in the related art, for a face picture, the face picture is scored according to multiple dimensions such as a shooting angle of the face picture, an image blur degree, an illumination intensity, whether the face picture is blocked or not, and an overall evaluation of the face picture is obtained. Moreover, the image blurring degree and the illumination intensity belong to the quality category of the face picture, and the shooting angle and whether the face is shielded belong to the content category of the picture, which are essentially the quality problems of the picture, and factors such as the difference between the face reference picture and the field picture are not considered. That is, the method for evaluating the quality of the face image in the related art mainly focuses on the quality of the image, such as the definition of the image, the illumination condition, the face shielding condition, and the like, and the quality problem caused by the difference between the reference image and the user is not considered.
Aiming at the problem that the accuracy of face recognition by using a reference photo of a face recognition system is low due to the fact that the reference photo of a user in the face recognition system is difficult to update according to age information in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The present application mainly aims to provide a method and an apparatus for processing a reference photo, a processor, and an electronic device, so as to solve the problem in the related art that it is difficult to update the reference photo of a user in a face recognition system according to age information, which results in a low accuracy of the face recognition system using the reference photo for face recognition.
In order to achieve the above object, according to an aspect of the present application, there is provided a reference photograph processing method. The method comprises the following steps: respectively acquiring identity characteristic information corresponding to a reference photo and a live photo, wherein the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the live photo is a photo of the target object acquired in the field, and the target object is an object to be subjected to face recognition; respectively acquiring age characteristic information corresponding to the reference picture and the live picture; and updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information.
Further, according to the identity feature information and the age feature information, updating the reference picture in the face recognition system includes: comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result; if the comparison result shows that the reference photo and the field photo are successfully compared, obtaining an absolute value of an age difference value according to the age characteristic information, wherein the age difference value is a difference value between a first age corresponding to the reference photo and a second age corresponding to the field photo; and updating the reference picture in the face recognition system according to the absolute value of the age difference value.
Further, updating the reference picture in the face recognition system according to the absolute value of the age difference value includes: judging whether the absolute value of the age difference value is larger than a first preset threshold value or not; if the absolute value of the age difference value is larger than the first preset threshold value, updating the reference picture in the face recognition system; and if the absolute value of the age difference value is not larger than the first preset threshold value, not updating the reference picture in the face recognition system.
Further, according to the identity feature information, comparing the reference picture with the live picture to obtain a comparison result, including: inputting the identity characteristic information into an identity recognition model for recognition to obtain the similarity between the reference picture and the field picture; judging whether the similarity is greater than a second preset threshold value or not; if the similarity is greater than the second preset threshold, the comparison between the reference picture and the live picture is successful; and if the similarity is not greater than the second preset threshold, indicating that the comparison between the reference picture and the live picture fails.
Further, if the comparison result indicates that the comparison between the reference picture and the live picture is successful, obtaining an absolute value of an age difference according to the age characteristic information includes: if the comparison result shows that the reference photo and the field photo are successfully compared, inputting the age characteristic information into an age calculation model for calculation to obtain the first age corresponding to the reference photo and the second age corresponding to the field photo; calculating the difference between the first age and the second age to obtain the age difference; and calculating the absolute value of the age difference value based on the age difference value.
Further, the step of respectively acquiring age characteristic information corresponding to the reference photograph and the live photograph includes: inputting the reference picture and the field picture into a target model for processing respectively to obtain first characteristic values corresponding to the reference picture and the field picture; inputting the first characteristic value into a channel attention model to obtain a second characteristic value; inputting the first characteristic value into a space attention model to obtain a third characteristic value; adding the second characteristic value and the third characteristic value to obtain an attention mask; and multiplying the first characteristic value by the attention mask to obtain the age characteristic information corresponding to the reference picture and the live picture.
Further, respectively acquiring the identity feature information corresponding to the reference photo and the live photo includes: subtracting the attention mask by using a preset value to obtain a target numerical value; and multiplying the first characteristic value and the target numerical value to obtain the identity characteristic information corresponding to the reference picture and the field picture.
In order to achieve the above object, according to another aspect of the present application, there is provided a processing apparatus of a reference photograph. The device includes: the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for respectively acquiring identity characteristic information corresponding to a reference photo and a field photo, the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the field photo is a photo of the target object acquired in the field, and the target object is an object to be subjected to face recognition; the second acquisition unit is used for respectively acquiring age characteristic information corresponding to the reference photo and the live photo; and the first processing unit is used for updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information.
Further, the first processing unit includes: the first comparison module is used for comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result; a first determining module, configured to obtain an absolute value of an age difference according to the age characteristic information if the comparison result indicates that the comparison between the reference photo and the field photo is successful, where the age difference is a difference between a first age corresponding to the reference photo and a second age corresponding to the field photo; and the first processing module is used for updating the reference picture in the face recognition system according to the absolute value of the age difference value.
Further, the first processing module comprises: the first judgment sub-module is used for judging whether the absolute value of the age difference value is larger than a first preset threshold value or not; the first processing submodule is used for updating the reference picture in the face recognition system if the absolute value of the age difference value is greater than the first preset threshold value; and the second processing submodule is used for not updating the reference picture in the face recognition system if the absolute value of the age difference value is not greater than the first preset threshold value.
Further, the first comparison module comprises: the first determining submodule is used for inputting the identity characteristic information into an identity recognition model for recognition to obtain the similarity between the reference picture and the field picture; the second judgment sub-module is used for judging whether the similarity is larger than a second preset threshold value or not; the second determining submodule is used for indicating that the comparison between the reference picture and the field picture is successful if the similarity is greater than the second preset threshold value; and the third determining sub-module is used for indicating that the comparison between the reference picture and the live picture fails if the similarity is not greater than the second preset threshold.
Further, the first determining module comprises: the first calculation submodule is used for inputting the age characteristic information into an age calculation model for calculation to obtain the first age corresponding to the reference photo and the second age corresponding to the field photo if the comparison result shows that the reference photo and the field photo are successfully compared; the second calculation submodule is used for calculating the difference between the first age and the second age to obtain the age difference; and calculating the absolute value of the age difference value based on the age difference value.
Further, the second acquisition unit includes: the second processing module is used for inputting the reference picture and the field picture into a target model for processing to obtain first characteristic values corresponding to the reference picture and the field picture; the first input module is used for inputting the first characteristic value into a channel attention model to obtain a second characteristic value; the second input module is used for inputting the first characteristic value into a space attention model to obtain a third characteristic value; a first adding module, configured to add the second feature value and the third feature value to obtain an attention mask; and the first multiplying module is used for multiplying the first characteristic value and the attention mask to obtain the age characteristic information corresponding to the reference picture and the live picture.
Further, the first acquisition unit includes: the first subtraction module is used for subtracting the attention mask by using a preset value to obtain a target numerical value; and the second multiplying module is used for multiplying the first characteristic value and the target numerical value to obtain the identity characteristic information corresponding to the reference picture and the field picture.
In order to achieve the above object, according to another aspect of the present application, there is provided a processor for running a program, wherein the program executes the method for processing the reference picture.
In order to achieve the above object, according to another aspect of the present application, there is provided an electronic device including one or more processors and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for processing a reference photograph as described in any one of the above.
Through the application, the following steps are adopted: respectively acquiring identity characteristic information corresponding to a reference photo and a field photo, wherein the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the field photo is a photo of the target object acquired on the field, and the target object is an object to be subjected to face recognition; respectively acquiring age characteristic information corresponding to the reference picture and the live picture; the reference picture in the face recognition system is updated according to the identity characteristic information and the age characteristic information, and the problem that the accuracy of face recognition by the face recognition system using the reference picture is low due to the fact that the reference picture of a user in the face recognition system is difficult to update according to the age information in the related technology is solved. The reference picture in the face recognition system is updated according to the identity characteristic information and the age characteristic information, so that the reference picture of a user in the face recognition system can be updated according to the age information, and the effect of improving the accuracy of the face recognition system for carrying out face recognition by using the reference picture is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a flowchart of a method for processing a reference photograph provided according to an embodiment of the present application;
FIG. 2 is a block diagram of a feature extraction and separation module in an embodiment of the present application;
FIG. 3 is a block diagram of a channel attention mechanism in an embodiment of the present application;
FIG. 4 is a block diagram of a spatial attention mechanism in an embodiment of the present application;
FIG. 5 is a first flowchart of a method for processing a reference picture according to an embodiment of the present disclosure;
FIG. 6 is a flow chart of an alternative reference photograph processing method provided in accordance with an embodiment of the present application;
FIG. 7 is a schematic diagram of a processing device for reference photos provided according to an embodiment of the present application;
fig. 8 is a schematic diagram of an electronic device provided according to an embodiment of the application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for presentation, analyzed data, etc.) referred to in the present disclosure are information and data authorized by the user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, and before obtaining the relevant information, an obtaining request needs to be sent to the user or institution through the interface, and after receiving the consent information fed back by the user or institution, the relevant information needs to be obtained.
The present invention is described below with reference to preferred implementation steps, and fig. 1 is a flowchart of a method for processing a reference photograph according to an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:
step S101, respectively obtaining identity characteristic information corresponding to a reference photo and a live photo, wherein the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the live photo is a photo of the target object collected on site, and the target object is an object to be subjected to face recognition.
For example, a reference photo in the face recognition system and a field photo of a client to be subjected to face recognition collected on the field can be respectively input into the feature extraction and separation module to obtain the identity-related features corresponding to the reference photo and the identity-related features corresponding to the field photo. Moreover, the identity-related feature can be information representing identity, such as features of face, hair and the like, and whether the reference picture and the field picture correspond to the same person can be judged through the identity-related feature.
Step S102, acquiring age characteristic information corresponding to the reference picture and the live picture respectively.
For example, the reference photograph and the live photograph may be input into the feature extraction and separation module, respectively, to obtain the age-related feature corresponding to the reference photograph and the age-related feature corresponding to the live photograph. Furthermore, the age range of the client corresponding to the reference picture and the age range of the client corresponding to the scene picture can be obtained according to the age-related characteristics.
And step S103, updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information.
For example, if the reference photograph and the field photograph are determined to correspond to the same person based on the identity-related characteristic, the age difference between the reference photograph and the field photograph is determined based on the age-related characteristic. And if the absolute value of the age difference is larger than a preset threshold value, reminding the user to update the reference picture, otherwise, not updating the reference picture.
Through the steps S101 to S103, the identity characteristic information and the age characteristic information corresponding to the reference picture and the live picture respectively are obtained, and then the reference picture in the face recognition system is updated according to the identity characteristic information and the age characteristic information, so that the reference picture of the user in the face recognition system can be updated according to the age information, and further, the effect of improving the accuracy of the face recognition system in using the reference picture for face recognition is achieved.
In order to quickly and accurately obtain age characteristic information corresponding to a reference photo and a live photo, in the processing method of the reference photo provided by the embodiment of the application, the age characteristic information corresponding to the reference photo and the live photo can be obtained through the following steps: inputting the reference picture and the field picture into a target model for processing respectively to obtain first characteristic values corresponding to the reference picture and the field picture; inputting the first characteristic value into a channel attention model to obtain a second characteristic value; inputting the first characteristic value into a space attention model to obtain a third characteristic value; adding the second characteristic value and the third characteristic value to obtain an attention mask; and multiplying the first characteristic value by the attention mask to obtain age characteristic information corresponding to the reference picture and the live picture.
For example, the reference photograph and the live photograph are respectively input into the feature extraction and separation module to obtain the age-related feature and the identity-related feature. Moreover, fig. 2 is a block diagram of a feature extraction and separation module in an embodiment of the present application, and as shown in fig. 2, a picture X (reference picture or field picture) is input into a CNN (Convolutional Neural Network) to obtain a hybrid feature F (X), where the CNN may use a relatively classical Network model, such as ResNet (Residual Network). And respectively inputting the mixed feature F (X) into the channel attention mechanism model and the space attention model, adding the outputs of the two models to obtain an attention mask A (F (X)), and multiplying the mixed feature F (X) by the attention mask to obtain the age-related feature. The specific calculation method is as follows:
F(X)＝F age +F id
＝F(X)*A(F(X))+F(X)*(1-A(F(X)))
A(X)＝C(X)+S(X)
wherein, the element-level multiplication is representedC (X) denotes a channel attention module, S (X) denotes a spatial attention module, A (X) denotes an attention mechanism module (i.e., a channel attention module and a spatial attention module), F age Representing age-related features, F id Representing identity-related features. The Channel Attention mechanism may use a CAM (Channel Attention Module) in a CBAM (Convolutional Module of Attention mechanism), the Spatial Attention mechanism may use an SAM (Spatial Attention Module) in the CBAM, and the calculation manner of the Channel Attention mechanism is as follows:
where σ denotes a sigmoid activation function (used as an activation function for neural networks), avgPool (X) denotes an average pooling operation of channel directions
Maxpool (X) represents the maximum pooling operation in channel orientation
Wherein C all represent channel characteristics, W 0 And W 1 Weight values of a hidden layer and an output layer of an MLP (Multi layer Perceptron) are respectively expressed, and W 0 The activation function of (1) is a Relu function (Linear rectification function).
In addition, the spatial attention mechanism is calculated as follows:
wherein σ denotes sigmoid activation function, avgPool (X) denotes average pooling operation in spatial direction,
MaxPoint (X) represents a spatial squareThe operation of the pond is performed to the maximum,
wherein H and W respectively represent the dimension of the matrix vector, H represents the length, W represents the width, f 7x7 Represents a convolution kernel of 7 × 7 (corresponding to the convolution layer in fig. 4), [.]Indicating a connect operation. In addition, fig. 3 is a frame diagram of a channel attention mechanism in the embodiment of the present application, and fig. 4 is a frame diagram of a space attention mechanism in the embodiment of the present application. Also, the input feature X in fig. 3 and 4 may be an age-related feature or an identity-related feature of the reference picture.
In conclusion, the attention mechanism model is added to further process the features extracted by the CNN model, and an attention mask is obtained for separating the features, so that the age-related features can be quickly and accurately obtained.
In order to quickly and accurately obtain the identity characteristic information corresponding to the reference photo and the field photo, in the method for processing the reference photo provided by the embodiment of the application, the identity characteristic information corresponding to the reference photo and the field photo can be obtained through the following steps: in the method for processing a reference picture provided in the embodiment of the present application, respectively obtaining the identity feature information corresponding to the reference picture and the live picture includes: subtracting the attention mask by using a preset value to obtain a target numerical value; and multiplying the first characteristic value by the target value to obtain the identity characteristic information corresponding to the reference picture and the field picture.
For example, the reference photograph and the live photograph are respectively input into the feature extraction and separation module to obtain the age-related feature and the identity-related feature. As shown in fig. 2, the picture X (reference picture or scene picture) is input into a CNN network to obtain a mixed feature F (X), the mixed feature F (X) is input into the channel attention mechanism model and the spatial attention model, respectively, the outputs of the two models are added to obtain an attention mask a (F (X)), and the attention mask is subtracted from 1 (the preset value mentioned above) and multiplied by the mixed feature F (X) to obtain the identity-related feature.
By the scheme, the CNN which is successfully applied in the image field is used for extracting the human face image characteristics, so that the influence of subjective factors in a manual identification mode is effectively avoided. Meanwhile, an attention mechanism model is added to further process the features extracted by the CNN model, and an attention mask is obtained for separating the features, so that the identity related features can be quickly and accurately obtained.
Fig. 5 is a first flowchart of a method for processing a reference picture according to an embodiment of the present application, and as shown in fig. 5, in the method for processing a reference picture according to the embodiment of the present application, updating a reference picture in a face recognition system according to identity feature information and age feature information includes:
step S501, comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result;
step S502, if the comparison result shows that the comparison between the reference photo and the field photo is successful, obtaining an absolute value of an age difference value according to the age characteristic information, wherein the age difference value is a difference value between a first age corresponding to the reference photo and a second age corresponding to the field photo;
in step S503, the reference picture in the face recognition system is updated according to the absolute value of the age difference.
For example, comparing the obtained identity-related features of the field photo and the reference photo, if the comparison is successful, and the fact that the user of the field photo and the user of the reference photo are the same person is indicated, classifying the obtained age-related features to obtain the specific age ranges of the field photo and the reference photo, calculating the absolute value of the age difference of the two photos, and if the absolute value of the age difference is larger than a threshold k, reminding the user to update the reference photo, otherwise, not updating the photos, and ending the task.
To sum up, the quality of the picture in the face recognition system is judged in a poor age mode, a user is reminded to update the database reference picture in time, face recognition failure caused by the difference between the field picture and the reference picture due to age increase is avoided, and the performance of the face recognition system is improved.
In order to quickly and accurately compare the reference picture with the field picture according to the identity characteristic information to obtain a comparison result, in the processing method of the reference picture provided by the embodiment of the application, the reference picture and the field picture can be compared according to the identity characteristic information through the following steps to obtain the comparison result: inputting the identity characteristic information into an identity recognition model for recognition to obtain the similarity between the reference picture and the field picture; judging whether the similarity is greater than a second preset threshold value or not; if the similarity is greater than a second preset threshold value, the comparison between the reference picture and the field picture is successful; and if the similarity is not greater than the second preset threshold, the comparison between the reference picture and the live picture fails.
For example, the processed data set related to the identity is input into the identity recognition model, then the identity recognition model outputs the similarity of the two input pictures, and if the similarity is greater than the set threshold γ (the second preset threshold mentioned above), it is considered that the faces of the two pictures belong to the same person, that is, the comparison is successful. If the similarity is not greater than the set threshold γ (the second preset threshold mentioned above), it is determined that the faces of the two pictures do not belong to the same person, i.e., the comparison fails.
In addition, in the model training process, for the identity authentication model (identity recognition model), the data set generation algorithm is as follows:
(1) Let D be the original face data set, D 1 To construct a training data set, two images I are then randomly selected from the original face data set D 1 And I 2 In which I 1 E.g. D and I 2 ∈D；
(2) If I 1 And I 2 Belonging to the same picture, and returning to the step (1);
(3) Judgment of I 1 And I 2 If the person is not the same person, the given label 1 forms a pair of negative examples S p (I 1 ，I 2 1); if the same person, given label 0, form a pair of positive samples S n (I 1 ，I 2 ，0)；
(4) Judgment S p And S n Whether or not at D 1 If yes, returning to the step (1), and if not, returning to the step (1) p And S n Put into D 1 And (3) returning to the step (1), and circulating the steps until D 1 The number of samples in (1) reaches a preset value.
Finally, a training data set D 1 After the generation, the processed data sets are input into a model to train an identity recognition model, the similarity of two input pictures is output by the identity recognition model, and if the similarity is greater than a set threshold gamma, the faces of the two pictures are considered to belong to the same person.
By the scheme, whether the reference photo and the field photo are the same person can be quickly and accurately compared.
In order to obtain the absolute value of the age difference value quickly and accurately, in the processing method of the reference photograph provided in the embodiment of the present application, the absolute value of the age difference value may also be obtained through the following steps: if the comparison result shows that the comparison between the reference photo and the field photo is successful, inputting the age characteristic information into an age calculation model for calculation to obtain a first age corresponding to the reference photo and a second age corresponding to the field photo; calculating the difference between the first age and the second age to obtain an age difference value; and calculating an absolute value of the age difference value based on the age difference value.
For example, the obtained age-related features are classified to obtain specific age ranges of the live view and the reference view, the age difference between the two views is calculated, and the absolute value of the age difference is obtained by taking the absolute value of the calculated age difference.
In addition, in the model training process, for the age calculation model, the method for marking data is as follows:
(1) Dividing the collected data into 10 groups according to the age of the collected data, wherein the 10 groups are respectively 0-10, 11-20, 21-30, 31-40, 41-50, 51-60, 61-70, 71-80, 81-90 and 90+;
(2) The labeled data is input into a model to train an age classification model, and the output of the model is the range of ages of the predicted users, such as 21-30.
By the scheme, the absolute value of the age difference between the reference picture and the field picture can be quickly and accurately obtained.
In order to quickly and accurately update the reference picture in the face recognition system, in the processing method of the reference picture provided in the embodiment of the present application, the reference picture in the face recognition system may also be updated through the following steps: judging whether the absolute value of the age difference value is larger than a first preset threshold value or not; if the absolute value of the age difference value is larger than a first preset threshold value, updating the reference picture in the face recognition system; and if the absolute value of the age difference value is not larger than the first preset threshold value, the reference picture in the face recognition system is not updated.
For example, after the age difference between two photos is calculated, if the absolute value of the age difference is greater than a threshold k, the user is reminded to update the reference photo, otherwise, the photos do not need to be updated, and the task is ended.
Through the scheme, the quality of the reference picture is evaluated from the perspective of the age difference of the user, the user is reminded to update the picture of the system in time, and the performance of the face recognition system is improved.
For example, fig. 6 is a flowchart of an optional reference picture processing method provided according to an embodiment of the present application, and as shown in fig. 6, the optional reference picture processing method mainly includes three parts, namely, feature extraction and separation, feature comparison, and age difference calculation, which are specifically as follows:
(1) And (3) feature extraction and separation: respectively inputting the reference photo and the field photo into a feature extraction and separation module to obtain age-related features and identity-related features;
(2) And (3) feature comparison: comparing the identity-related characteristics of the field photo and the reference photo obtained in the step (1), and if the comparison is successful, indicating that the users of the field photo and the reference photo are the same person, entering the step (3); if the comparison between the extracted features of the field photo and all the reference photos in the system fails, the system is considered to have no information of the user, and the identity authentication fails;
(3) Calculating the age difference: classifying the age-related features obtained in the step (1) to obtain specific age ranges of the field photo and the reference photo, calculating an absolute value of the age difference of the two photos, reminding a user to update the reference photo if the absolute value of the age difference is larger than a threshold k, and ending the task if the absolute value of the age difference is not larger than the threshold k.
To sum up, in the method for processing a reference picture provided in the embodiment of the present application, identity feature information corresponding to the reference picture and the live picture is respectively obtained, where the reference picture is a picture used for performing face recognition on a target object in a face recognition system, the live picture is a picture of the target object acquired on site, and the target object is an object to be subjected to face recognition; respectively acquiring age characteristic information corresponding to the reference picture and the live picture; the reference picture in the face recognition system is updated according to the identity characteristic information and the age characteristic information, and the problem that the accuracy of face recognition by the face recognition system using the reference picture is low due to the fact that the reference picture of a user in the face recognition system is difficult to update according to the age information in the related technology is solved. The reference picture in the face recognition system is updated according to the identity characteristic information and the age characteristic information, so that the reference picture of a user in the face recognition system can be updated according to the age information, and the effect of improving the accuracy of the face recognition system for carrying out face recognition by using the reference picture is achieved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
The embodiment of the present application further provides a processing apparatus for reference photos, and it should be noted that the processing apparatus for reference photos of the embodiment of the present application can be used to execute the processing method for reference photos provided in the embodiment of the present application. The following describes a reference photograph processing apparatus according to an embodiment of the present application.
Fig. 7 is a schematic diagram of a processing apparatus for reference photographs according to an embodiment of the present application. As shown in fig. 7, the apparatus includes: a first acquisition unit 701, a second acquisition unit 702, and a first processing unit 703.
Specifically, the first obtaining unit 701 is configured to obtain identity feature information corresponding to a reference photo and a live photo respectively, where the reference photo is a photo used in a face recognition system to perform face recognition on a target object, the live photo is a photo of the target object acquired in the field, and the target object is an object to be subjected to face recognition;
a second obtaining unit 702, configured to obtain age characteristic information corresponding to the reference photo and the live photo respectively;
the first processing unit 703 is configured to update the reference picture in the face recognition system according to the identity feature information and the age feature information.
To sum up, in the apparatus for processing a reference picture provided in this embodiment of the present application, the first obtaining unit 701 obtains the identity feature information corresponding to the reference picture and the live picture respectively, where the reference picture is a picture used for performing face recognition on a target object in a face recognition system, the live picture is a picture of the target object acquired in the field, and the target object is an object to be subjected to face recognition; the second obtaining unit 702 obtains age characteristic information corresponding to the reference picture and the live picture respectively; the first processing unit 703 updates the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information, thereby solving the problem that it is difficult to update the reference picture of the user in the face recognition system according to the age information in the related art, which results in the face recognition system having low accuracy of face recognition using the reference picture. The reference picture in the face recognition system is updated according to the identity characteristic information and the age characteristic information, so that the reference picture of a user in the face recognition system can be updated according to the age information, and the effect of improving the accuracy of the face recognition system for carrying out face recognition by using the reference picture is achieved.
Optionally, in the apparatus for processing a reference picture provided in an embodiment of the present application, the first processing unit includes: the first comparison module is used for comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result; the first determining module is used for obtaining an absolute value of an age difference value according to the age characteristic information if the comparison result shows that the comparison between the reference photo and the field photo is successful, wherein the age difference value is a difference value between a first age corresponding to the reference photo and a second age corresponding to the field photo; and the first processing module is used for updating the reference picture in the face recognition system according to the absolute value of the age difference value.
Optionally, in the processing apparatus for reference photos provided in the embodiment of the present application, the first processing module includes: the first judgment submodule is used for judging whether the absolute value of the age difference value is larger than a first preset threshold value or not; the first processing submodule is used for updating the reference picture in the face recognition system if the absolute value of the age difference value is larger than a first preset threshold value; and the second processing submodule is used for not updating the reference picture in the face recognition system if the absolute value of the age difference value is not greater than the first preset threshold value.
Optionally, in the apparatus for processing a reference photograph provided in this embodiment of the present application, the first comparison module includes: the first determining submodule is used for inputting the identity characteristic information into the identity recognition model for recognition to obtain the similarity between the reference picture and the field picture; the second judgment sub-module is used for judging whether the similarity is larger than a second preset threshold value or not; the second determining submodule is used for indicating that the comparison between the reference picture and the live picture is successful if the similarity is greater than a second preset threshold value; and the third determining sub-module is used for indicating that the comparison between the reference picture and the live picture fails if the similarity is not greater than a second preset threshold.
Optionally, in the apparatus for processing a reference picture provided in an embodiment of the present application, the first determining module includes: the first calculation submodule is used for inputting the age characteristic information into an age calculation model for calculation to obtain a first age corresponding to the reference picture and a second age corresponding to the field picture if the comparison result shows that the reference picture and the field picture are successfully compared; the second calculating submodule is used for calculating the difference between the first age and the second age to obtain an age difference value; and calculating the absolute value of the age difference value based on the age difference value.
Optionally, in the apparatus for processing the reference picture provided in the embodiment of the present application, the second obtaining unit includes: the second processing module is used for inputting the reference picture and the field picture into the target model for processing respectively to obtain first characteristic values corresponding to the reference picture and the field picture; the first input module is used for inputting the first characteristic value into the channel attention model to obtain a second characteristic value; the second input module is used for inputting the first characteristic value into the space attention model to obtain a third characteristic value; the first adding module is used for adding the second characteristic value and the third characteristic value to obtain an attention mask; and the first multiplying module is used for multiplying the first characteristic value and the attention mask to obtain age characteristic information corresponding to the reference picture and the live picture.
Optionally, in the apparatus for processing a reference picture provided in an embodiment of the present application, the first obtaining unit includes: the first subtraction module is used for subtracting the attention mask code by using a preset value to obtain a target numerical value; and the second multiplying module is used for multiplying the first characteristic value by the target value to obtain the identity characteristic information corresponding to the reference picture and the live picture.
The processing device for the reference picture comprises a processor and a memory, wherein the first acquiring unit 701, the second acquiring unit 702, the first processing unit 703 and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the accuracy of the face recognition system for performing face recognition by using the reference picture is improved by adjusting kernel parameters.
The memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The embodiment of the invention provides a processor, which is used for running a program, wherein the processing method of the reference photo is executed when the program runs.
As shown in fig. 8, an embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: respectively acquiring identity characteristic information corresponding to a reference photo and a field photo, wherein the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the field photo is a photo of the target object acquired on the field, and the target object is an object to be subjected to face recognition; respectively acquiring age characteristic information corresponding to the reference picture and the live picture; and updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information.
The processor executes the program and further realizes the following steps: according to the identity characteristic information and the age characteristic information, the updating processing of the reference picture in the face recognition system comprises the following steps: comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result; if the comparison result shows that the reference photo and the field photo are successfully compared, obtaining an absolute value of an age difference value according to the age characteristic information, wherein the age difference value is a difference value between a first age corresponding to the reference photo and a second age corresponding to the field photo; and updating the reference picture in the face recognition system according to the absolute value of the age difference.
The processor executes the program and further realizes the following steps: according to the absolute value of the age difference value, the updating processing of the reference picture in the face recognition system comprises the following steps: judging whether the absolute value of the age difference value is larger than a first preset threshold value or not; if the absolute value of the age difference value is larger than the first preset threshold value, updating the reference picture in the face recognition system; and if the absolute value of the age difference value is not larger than the first preset threshold value, not updating the reference picture in the face recognition system.
The processor executes the program and further realizes the following steps: according to the identity characteristic information, comparing the reference picture with the field picture to obtain a comparison result, wherein the comparison result comprises the following steps: inputting the identity characteristic information into an identity recognition model for recognition to obtain the similarity between the reference picture and the field picture; judging whether the similarity is greater than a second preset threshold value or not; if the similarity is larger than the second preset threshold, the reference picture and the field picture are successfully compared; and if the similarity is not greater than the second preset threshold, indicating that the comparison between the reference picture and the live picture fails.
The processor executes the program and further realizes the following steps: if the comparison result shows that the reference picture and the field picture are successfully compared, obtaining an absolute value of an age difference value according to the age characteristic information comprises: if the comparison result shows that the reference photo and the field photo are successfully compared, inputting the age characteristic information into an age calculation model for calculation to obtain the first age corresponding to the reference photo and the second age corresponding to the field photo; calculating the difference between the first age and the second age to obtain the age difference; and calculating an absolute value of the age difference value based on the age difference value.
The processor executes the program and further realizes the following steps: the step of respectively acquiring age characteristic information corresponding to the reference picture and the live picture comprises the following steps: inputting the reference picture and the field picture into a target model for processing respectively to obtain first characteristic values corresponding to the reference picture and the field picture; inputting the first characteristic value into a channel attention model to obtain a second characteristic value; inputting the first characteristic value into a space attention model to obtain a third characteristic value; adding the second characteristic value and the third characteristic value to obtain an attention mask; and multiplying the first characteristic value and the attention mask to obtain the age characteristic information corresponding to the reference photo and the live photo.
The processor executes the program and further realizes the following steps: respectively acquiring the identity characteristic information corresponding to the reference picture and the live picture comprises the following steps: subtracting the attention mask by using a preset value to obtain a target numerical value; and multiplying the first characteristic value by the target numerical value to obtain the identity characteristic information corresponding to the reference picture and the field picture.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: respectively acquiring identity characteristic information corresponding to a reference photo and a field photo, wherein the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the field photo is a photo of the target object acquired on the field, and the target object is an object to be subjected to face recognition; respectively acquiring age characteristic information corresponding to the reference photo and the live photo; and updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: according to the identity characteristic information and the age characteristic information, the updating processing of the reference picture in the face recognition system comprises the following steps: comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result; if the comparison result shows that the reference photo and the field photo are successfully compared, obtaining an absolute value of an age difference value according to the age characteristic information, wherein the age difference value is a difference value between a first age corresponding to the reference photo and a second age corresponding to the field photo; and updating the reference picture in the face recognition system according to the absolute value of the age difference value.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: according to the absolute value of the age difference value, the updating processing of the reference picture in the face recognition system comprises the following steps: judging whether the absolute value of the age difference value is larger than a first preset threshold value or not; if the absolute value of the age difference value is larger than the first preset threshold value, updating the reference picture in the face recognition system; and if the absolute value of the age difference value is not larger than the first preset threshold value, not updating the reference picture in the face recognition system.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result, wherein the comparison result comprises: inputting the identity characteristic information into an identity recognition model for recognition to obtain the similarity between the reference picture and the field picture; judging whether the similarity is greater than a second preset threshold value or not; if the similarity is greater than the second preset threshold, the comparison between the reference picture and the live picture is successful; and if the similarity is not greater than the second preset threshold, indicating that the comparison between the reference picture and the live picture fails.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: if the comparison result shows that the reference picture and the field picture are successfully compared, obtaining an absolute value of an age difference value according to the age characteristic information comprises: if the comparison result shows that the reference picture and the field picture are successfully compared, inputting the age characteristic information into an age calculation model for calculation to obtain the first age corresponding to the reference picture and the second age corresponding to the field picture; calculating the difference between the first age and the second age to obtain the age difference; and calculating the absolute value of the age difference value based on the age difference value.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: the step of respectively acquiring age characteristic information corresponding to the reference picture and the live picture comprises the following steps: inputting the reference picture and the field picture into a target model for processing respectively to obtain first characteristic values corresponding to the reference picture and the field picture; inputting the first characteristic value into a channel attention model to obtain a second characteristic value; inputting the first characteristic value into a space attention model to obtain a third characteristic value; adding the second characteristic value and the third characteristic value to obtain an attention mask; and multiplying the first characteristic value and the attention mask to obtain the age characteristic information corresponding to the reference photo and the live photo.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: respectively acquiring the identity characteristic information corresponding to the reference picture and the live picture comprises the following steps: subtracting the attention mask by using a preset value to obtain a target numerical value; and multiplying the first characteristic value and the target numerical value to obtain the identity characteristic information corresponding to the reference picture and the field picture.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for processing a reference picture, comprising:
respectively acquiring identity characteristic information corresponding to a reference photo and a live photo, wherein the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the live photo is a photo of the target object acquired in the field, and the target object is an object to be subjected to face recognition;
respectively acquiring age characteristic information corresponding to the reference photo and the live photo;
and updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information.
2. The method of claim 1, wherein updating the reference picture in the face recognition system according to the identity feature information and the age feature information comprises:
comparing the reference picture with the field picture according to the identity characteristic information to obtain a comparison result;
if the comparison result shows that the reference photo and the field photo are successfully compared, obtaining an absolute value of an age difference value according to the age characteristic information, wherein the age difference value is a difference value between a first age corresponding to the reference photo and a second age corresponding to the field photo;
and updating the reference picture in the face recognition system according to the absolute value of the age difference.
3. The method of claim 2, wherein the updating the reference picture in the face recognition system according to the absolute value of the age difference comprises:
judging whether the absolute value of the age difference value is larger than a first preset threshold value or not;
if the absolute value of the age difference value is larger than the first preset threshold value, updating the reference picture in the face recognition system;
and if the absolute value of the age difference value is not larger than the first preset threshold value, not updating the reference picture in the face recognition system.
4. The method of claim 2, wherein comparing the reference picture with the live picture according to the identity feature information to obtain a comparison result comprises:
inputting the identity characteristic information into an identity recognition model for recognition to obtain the similarity between the reference picture and the field picture;
judging whether the similarity is greater than a second preset threshold value or not;
if the similarity is greater than the second preset threshold, the comparison between the reference picture and the live picture is successful;
if the similarity is not larger than the second preset threshold, it indicates that the comparison between the reference picture and the live picture fails.
5. The method of claim 2, wherein if the comparison result indicates that the comparison between the reference picture and the live picture is successful, obtaining an absolute value of an age difference according to the age characteristic information comprises:
if the comparison result shows that the reference photo and the field photo are successfully compared, inputting the age characteristic information into an age calculation model for calculation to obtain the first age corresponding to the reference photo and the second age corresponding to the field photo;
calculating the difference between the first age and the second age to obtain the age difference;
and calculating the absolute value of the age difference value based on the age difference value.
6. The method of claim 1, wherein obtaining age characteristic information corresponding to the reference photograph and the live photograph, respectively, comprises:
inputting the reference picture and the field picture into a target model for processing respectively to obtain first characteristic values corresponding to the reference picture and the field picture;
inputting the first characteristic value into a channel attention model to obtain a second characteristic value;
inputting the first characteristic value into a space attention model to obtain a third characteristic value;
adding the second characteristic value and the third characteristic value to obtain an attention mask;
and multiplying the first characteristic value and the attention mask to obtain the age characteristic information corresponding to the reference photo and the live photo.
7. The method of claim 6, wherein obtaining the identity feature information corresponding to the reference picture and the live picture respectively comprises:
subtracting the attention mask by using a preset value to obtain a target numerical value;
and multiplying the first characteristic value and the target numerical value to obtain the identity characteristic information corresponding to the reference picture and the field picture.
8. An apparatus for processing a reference photograph, comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for respectively acquiring identity characteristic information corresponding to a reference photo and a field photo, the reference photo is a photo used for carrying out face recognition on a target object in a face recognition system, the field photo is a photo of the target object acquired in the field, and the target object is an object to be subjected to face recognition;
the second acquisition unit is used for respectively acquiring age characteristic information corresponding to the reference photo and the live photo;
and the first processing unit is used for updating the reference picture in the face recognition system according to the identity characteristic information and the age characteristic information.
9. A processor, characterized in that the processor is configured to run a program, wherein the program is configured to execute the method for processing the reference picture according to any one of claims 1 to 7 when running.
10. An electronic device comprising one or more processors and memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of processing a reference photograph of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502432.3A CN115798005A (en) | 2022-11-28 | 2022-11-28 | Reference photo processing method and device, processor and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502432.3A CN115798005A (en) | 2022-11-28 | 2022-11-28 | Reference photo processing method and device, processor and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115798005A true CN115798005A (en) | 2023-03-14 |
Family
ID=85442269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211502432.3A Pending CN115798005A (en) | 2022-11-28 | 2022-11-28 | Reference photo processing method and device, processor and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115798005A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117058803A (en) * | 2023-10-13 | 2023-11-14 | 浪潮智慧科技创新(山东)有限公司 | Intelligent data acquisition method and system based on deep learning |
-
2022
- 2022-11-28 CN CN202211502432.3A patent/CN115798005A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117058803A (en) * | 2023-10-13 | 2023-11-14 | 浪潮智慧科技创新(山东)有限公司 | Intelligent data acquisition method and system based on deep learning |
| CN117058803B (en) * | 2023-10-13 | 2024-01-05 | 浪潮智慧科技创新(山东)有限公司 | Intelligent data acquisition method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6798183B2 (en) | Image analyzer, image analysis method and program | |
| CN109416727B (en) | Method and device for removing glasses in face image | |
| CN110807757B (en) | Image quality evaluation method and device based on artificial intelligence and computer equipment | |
| TW202008310A (en) | Method, device and apparatus for binocular image depth estimation, program and storage medium thereof | |
| CN111695421B (en) | Image recognition method and device and electronic equipment | |
| CN112418195B (en) | Face key point detection method and device, electronic equipment and storage medium | |
| CN111738243A (en) | Method, device and equipment for selecting face image and storage medium | |
| CN108665421B (en) | Highlight component removing device and method for face image and storage medium product | |
| CN111008935B (en) | Face image enhancement method, device, system and storage medium | |
| US20240119707A1 (en) | Method for training image generation model, method for generating images, and devices thereof | |
| Abiko et al. | Single image reflection removal based on GAN with gradient constraint | |
| CN110648289A (en) | Image denoising processing method and device | |
| CN111914908A (en) | Image recognition model training method, image recognition method and related equipment | |
| Park et al. | An optimal low dynamic range image generation method using a neural network | |
| CN113505797A (en) | Model training method and device, computer equipment and storage medium | |
| CN115798005A (en) | Reference photo processing method and device, processor and electronic equipment | |
| Chen et al. | Learning to rank retargeted images | |
| CN113179421B (en) | Video cover selection method and device, computer equipment and storage medium | |
| CN115115552B (en) | Image correction model training method, image correction device and computer equipment | |
| CN112348808A (en) | Screen perspective detection method and device | |
| CN116797504A (en) | Image fusion method, electronic device and storage medium | |
| CN111353330A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| Gomez-Nieto et al. | Quality aware features for performance prediction and time reduction in video object tracking | |
| CN111126177B (en) | Method and device for counting number of people | |
| CN111310528B (en) | Image detection method, identity verification method, payment method and payment device |
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 |