WO2016177259A1

WO2016177259A1 - Similar image recognition method and device

Info

Publication number: WO2016177259A1
Application number: PCT/CN2016/079158
Authority: WO
Inventors: 陈岳峰
Original assignee: 阿里巴巴集团控股有限公司; 陈岳峰
Priority date: 2015-05-07
Filing date: 2016-04-13
Publication date: 2016-11-10
Also published as: CN106203242A; CN106203242B

Abstract

Disclosed is a similar image recognition method. After a to-be-compared area, corresponding to a specified feature, in a first to-be-recognized image is determined and an image in the to-be-recognized area is aligned with a preset standard image, the resolution of the aligned image in the to-be-recognized area is adjusted to a preset resolution and the adjusted image is used as a normalized image, and finally, a metric distance between the normalized image of the first to-be-recognized image and a normalized image of a second to-be-recognized image is acquired, and whether the specified features of the first to-be-recognized image and the second to-be-recognized image are similar to each other is determined according to the difference between the metric distance and a preset threshold. Thus on the premise that the accuracy is ensured, the similarity between one to-be-detected image and another to-be-detected image is recognized in a fast and efficient way, thereby providing a reference basis for improvements in the security of the existing systems.

Description

Similar image recognition method and device

Technical field

The present application relates to the field of communications technologies, and in particular, to a similar image recognition method. The application also relates to a similar image recognition device.

Background technique

With the development of the Internet and computer information technology, online shopping has become a new fashion for people to shop. For sales systems with large visits and large purchases, tens of millions of merchants sell goods through the sales system every day, but there are also many criminals who impersonate others in an attempt to process transactions on the sales system. This may result in various violations that may harm the rights of other legitimate users. Therefore, it is one of the problems to be solved by the sales system to determine whether the two photos are the same person based on the photos to be detected uploaded from the merchant user and the existing record photos.

The traditional face authentication method is mainly based on SIFT (Scale-invariant feature transform), LBP (Local Binary Patterns) and other features to describe the photos and the faces in the existing photos. Then, through the classifier, it is judged whether the two faces are the same person, wherein SIFT is a local feature descriptor for the field of image processing, and the description has scale invariance and can detect key points in the image, and the SIFT feature is Regardless of the size and rotation of the image based on some local appearance of interest points on the object, the tolerance for light, noise, and slight viewing angle changes is also quite high; LBP is an effective texture description operator that can measure and extract images. Local texture information, which is invariant to illumination.

However, in the process of implementing the present application, the inventors have found that the prior art has the following disadvantages: the traditional feature-based face authentication algorithm often extracts high-dimensional features from the face region and uses a classifier. Face authentication. Such algorithms are often only targeted at face features. Don't notice the pictures or photos to be effective. In the case that the background is complicated and the face changes greatly, the recognition technology in the prior art often cannot accurately pass the images in the two photos to be the same person. Therefore, how to ensure the recognition accuracy is The fast and efficient recognition of the image to be detected and the existing image has become a technical problem to be solved by those skilled in the art.

Summary of the invention

The present application provides a similar image recognition method for quickly and efficiently identifying an image to be detected and an existing image under the premise of ensuring accuracy, and the method includes:

Obtaining an area to be compared corresponding to the specified feature in the first to-be-identified image;

Aligning an image in the to-be-identified area with a preset standard image, and using the aligned image as a normalized image of the first to-be-identified image, the standard image corresponding to the specified feature;

Determining a metric distance between the normalized image and a normalized image of the second image to be recognized, the metric distance being characterized according to the normalized image and the normalized image of the second image to be recognized Distance generation in space, wherein the distance of the similar normalized image in the feature space is less than the distance of the non-similar normalized image in the feature space;

If the metric distance is greater than a preset threshold, confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image;

And if the metric distance is less than or equal to the threshold, confirming that the first to-be-identified image is similar to a specified feature of the second to-be-identified image.

Preferably, the area to be compared corresponding to the specified feature in the first to-be-identified image is obtained, specifically:

Determining the to-be-contrast area in the first to-be-identified image according to a detection algorithm corresponding to the specified feature;

The key point coordinates corresponding to the plurality of key point features of the specified feature in the to-be-contrast area are obtained by a preset key point regression model.

Preferably, the image in the area to be identified is aligned with a preset standard image, specifically:

Mapping the coordinates of each key point of the to-be-identified area to the key point coordinates of the aligned image according to the parameter M;

The parameter M is generated according to coordinates of each key point of the standard image and key point coordinates of an image corresponding to the specified feature in the labeled image.

Preferably, after the aligned image is used as the normalized image of the first to-be-identified image, the method further includes:

The resolution of the normalized image is adjusted to a preset resolution.

Preferably, determining a metric distance between the normalized image and the normalized image of the second to-be-identified image is specifically:

Extracting a specified feature in the normalized image by a convolutional neural network;

Determining, according to the convolutional neural network and the distance metric loss function, the feature value of the specified feature after mapping to the feature space, and using the feature value as the feature value of the normalized image;

Determining an Euclidean distance between a feature value of the normalized image and a feature value of a normalized image of the second to-be-identified image, the Euclidean distance being used as the metric distance.

Preferably, the designated feature is specifically a face region, and the key feature includes at least a left eye region, a right eye region, a nose region, a left corner region, and a right corner region.

Preferably, the convolutional neural network parameters are trained according to an annotated image comprising a normalized image in which the specified features are similar to each other and a normalized image in which the specified features are not similar to each other.

Correspondingly, the present application also proposes a similar image recognition device, including:

An acquiring module, configured to acquire an area to be compared corresponding to the specified feature in the first to-be-identified image;

An alignment module, configured to align an image in the area to be identified with a preset standard image, And using the aligned image as a normalized image of the first to-be-identified image, the standard image corresponding to the designated feature;

a determining module, configured to determine a metric distance between the normalized image of the first to-be-identified image and a normalized image of the second to-be-identified image, the metric distance according to the normalized image and the Calculating a distance of the normalized image of the second image to be recognized in the feature space, wherein a distance of the similar normalized image in the feature space is smaller than a distance of the non-similar normalized image in the feature space;

An identification module, configured to confirm, when the metric distance is greater than a preset threshold, that the first to-be-identified image is not similar to a specified feature of the second to-be-identified image, and that the metric distance is less than or equal to the threshold It is confirmed that the first to-be-identified image is similar to the specified feature of the second to-be-identified image.

Preferably, the determining module is specifically configured to:

Determining the to-be-contrast area in the first to-be-identified image according to a detection algorithm corresponding to the specified feature, and acquiring a plurality of keys in the to-be-contrast area and the specified feature by using a preset key point regression model The key point coordinates corresponding to the point feature.

Preferably, the alignment module is specifically configured to:

Mapping each key point coordinate of the to-be-identified area to a key point coordinate of the aligned image according to the parameter M, wherein the parameter M is according to each key point coordinate of the standard image and the labeled image Specifies the keypoint coordinates of the image corresponding to the feature.

Preferably, the method further comprises:

And an adjustment module, configured to adjust a resolution of the normalized image to a preset resolution.

Preferably, the obtaining module is specifically configured to:

Correspondingly, the present application also proposes a similar image recognition method, which is applied to a client, and includes the following steps:

Receiving an identity authentication request of the user, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

Sending the identity authentication request to the server, so that the server acquires a second to-be-identified image corresponding to the user according to the authentication information;

Receiving an identity authentication response sent by the server;

The client presents the authentication result to the user according to the identity authentication response.

Preferably, the user identity authentication request is received, specifically:

Obtaining an image uploaded by the user and information input by the user;

Using the image as the first to-be-identified image, and using the information as the authentication information;

And generating the identity authentication request according to the first to-be-identified image and the authentication information.

Preferably, the identity authentication response is an identity authentication success response or an identity authentication failure response, and further includes:

The identity authentication success response is generated by the server after confirming that the first to-be-identified image is similar to the specified feature of the second to-be-identified image;

The identity authentication failure response is generated by the server after confirming that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image.

Preferably, the authentication result is displayed to the user according to the identity authentication response, specifically:

When receiving the identity authentication success response, displaying, by the user, a preset interface corresponding to the identity authentication success response;

When receiving the identity authentication failure response, the user is presented with a preset interface corresponding to the identity authentication failure response, and prompting the user whether the manual verification is required.

Preferably, after the user is presented with a preset interface corresponding to the identity authentication failure response and a prompt to the user to indicate whether manual verification is required, the method further includes:

And if the manual verification request of the user is received, the identity authentication request is sent to a preset server.

Correspondingly, the application also proposes a client, including:

a receiving module, configured to receive an identity authentication request of the user, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

a sending module, configured to send the identity authentication request to the server, so that the server acquires a second to-be-identified image corresponding to the user according to the authentication information;

a receiving module, configured to receive an identity authentication response sent by the server;

And a display module, configured to display the authentication result to the user according to the identity authentication response.

Preferably, the receiving module is specifically configured to:

Acquiring the image uploaded by the user and the information input by the user, using the image as the first image to be recognized, and using the information as the authentication information, according to the first image to be recognized and the The authentication information generates the identity authentication request.

Preferably, the identity authentication response is an identity authentication success response or an identity authentication failure response. Also includes:

Preferably, the displaying module is configured to: when the receiving module receives the identity authentication success response, display the preset interface corresponding to the identity authentication success response to the user;

Or the displaying module is specifically configured to: when the receiving module receives the identity authentication failure response, display, to the user, a preset interface corresponding to the identity authentication failure response, and to the user Show tips for manual verification.

Preferably, when the display module displays the preset interface corresponding to the identity authentication failure response to the user and prompts the user whether the manual verification is required, the receiving module further receives the The manual verification request of the user, the receiving module instructing the sending module to send the identity authentication request to a preset server.

Correspondingly, the present application also proposes a similar image recognition method, which is applied to a server, and includes the following steps:

Receiving an identity authentication request sent by the client, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

Querying, according to the authentication information, a second to-be-identified image corresponding to the user;

Determining a metric distance between the normalized image and the normalized image of the second image to be recognized, The metric distance is generated according to a distance of the normalized image and the normalized image of the second image to be recognized in the feature space, wherein a distance of the similar normalized image in the feature space is less than a non-similar The normalized image of the distance in the feature space;

If the metric distance is greater than a preset threshold, confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image, and return an identity verification failure response to the client;

If the metric distance is less than or equal to the threshold, confirm that the first to-be-identified image is similar to the specified feature of the second to-be-identified image, and return an identity verification success response to the client.

The resolution of the normalized image is adjusted to a preset resolution.

Determining, according to the convolutional neural network and the distance metric loss function, the specified feature is mapped to Solving the feature value after the space, and using the feature value as the feature value of the normalized image;

Correspondingly, the present application also proposes a server, including:

Receiving, by the receiving module, an identity authentication request sent by the client, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

a querying module, configured to query, according to the authentication information, a second to-be-identified image corresponding to the user;

An alignment module, configured to align an image in the to-be-identified area with a preset standard image, and use the aligned image as a normalized image of the first to-be-identified image, the standard image and the Specify the feature correspondence;

An identification module, configured to confirm, when the metric distance is greater than a preset threshold, that the first to-be-identified image is not similar to a specified feature of the second to-be-identified image, and that the metric distance is less than or When the threshold is equal to the confirmation, the first to-be-identified image is similar to the specified feature of the second to-be-identified image;

a sending module, configured to return an identity verification failure response to the client when the identification module confirms that the first to-be-identified image is not similar to a specified feature of the second to-be-identified image, and confirm in the identification module And returning the identity verification success response to the client when the first to-be-identified image is similar to the specified feature of the second to-be-identified image.

Preferably, the determining module is specifically configured to:

Preferably, the alignment module is specifically configured to map coordinates of each key point of the to-be-identified area to key point coordinates of the aligned image according to the parameter M, wherein the parameter M is a key according to the standard image. Point coordinates and keypoint coordinates of the image corresponding to the specified feature in the annotated image.

Preferably, the method further comprises:

Preferably, the obtaining module is specifically configured to:

Preferably, the convolutional neural network parameters are obtained according to the labeled image training, and the labeled The annotation image includes a normalized image in which the specified features are similar to each other and a normalized image in which the specified features are not similar to each other.

It can be seen that, by applying the technical solution of the present application, after determining the to-be-compared area corresponding to the specified feature in the first to-be-identified image and aligning the image in the to-be-identified area with the preset standard image, the area to be identified is to be recognized. The resolution of the aligned image is adjusted to a preset resolution, and the adjusted image is used as a normalized image, and finally the normalized image of the first image to be recognized and the normalized image of the second image to be recognized are acquired. The metric distance between the images determines whether the specified features of the first to-be-identified image and the second to-be-identified image are similar according to a size between the metric distance and the preset threshold. Therefore, under the premise of ensuring accuracy, the similarity between the image to be detected and another image to be detected is quickly and efficiently identified, which provides a reference for improving the security of the existing system.

DRAWINGS

1 is a schematic flow chart of a similar image recognition method proposed in the present application;

2 is a structural diagram of a convolutional neural network for training face feature point positioning in a specific embodiment of the present application;

3 is a schematic flowchart of performing depth metric learning in a specific embodiment of the present application;

4 is a structural diagram of a convolutional neural network for training face authentication in a specific embodiment of the present application;

FIG. 5 is a schematic flowchart of a similar image recognition performed by a client in a specific embodiment of the present application; FIG.

6 is a schematic flowchart of performing similar image recognition by a server in a specific embodiment of the present application;

FIG. 7 is a schematic structural diagram of a similar image recognition device according to the present application; FIG.

FIG. 8 is a schematic structural diagram of a client according to the present application; FIG.

FIG. 9 is a schematic structural diagram of a server according to the present application.

detailed description

With the popularity of mobile devices, face authentication plays an important role in more and more places. However, the face authentication process is interfered by many other objective factors, plus angles, etc. Faces in images containing faces are often not directly compared and extracted. In view of this problem, the present application proposes a recognition method for similar images, which can be implemented by means of a computer device in a network environment. The main purpose of judging the similarity is the server in the background of the system, and the client-oriented client is either a mobile device compatible with key input and touch screen input, or a PC device, and the client and the server are wired or A wireless way to achieve network connectivity.

As shown in FIG. 1 , a schematic flowchart of a similar image recognition method proposed in the present application includes the following steps:

S101. Acquire an area to be compared corresponding to the specified feature in the first to-be-identified image.

In the process of similarity judgment on the face of the face class to accurately distinguish whether the two photos are the same person, accurately locating some key points of the face (such as eyes, nose, mouth, etc.) face alignment is indispensable Less steps. Therefore, in a preferred embodiment of the present application, the area to be compared can be obtained by determining the key point coordinates (related to the face). Specifically, in determining a region to be compared corresponding to the specified feature in the first to-be-identified image, the to-be-contrast region in the first to-be-identified image may be first determined according to a detection algorithm corresponding to the specified feature. Then, the key point coordinates corresponding to the plurality of key point features of the specified feature in the to-be-compared area are obtained by using a preset key point regression model, so as to accurately determine the area to be compared. Accordingly, the designated feature may be a face region, and the key feature includes at least a left eye region, a right eye region, a nose region, a left corner region, and a right corner region.

According to an embodiment of the present application, a deep convolutional neural network is used to implement regression of face key points. The structure of the neural network in this embodiment is as shown in FIG. 2, and includes four convolution layers and two fully connected layers. The first three convolutional layers contain the maximum pooling operation, and the last convolutional layer contains only the convolution operation. The first fully connected layer contains 100 nodes, and the second is fully connected to have 10 nodes, representing the coordinates of the five key points of the face. Regression uses the Euclidean distance as the loss function, and the expression is as follows:

x represents the coordinates of the key points of the annotation, representing the coordinates of the key points predicted by the convolutional neural network.

By minimizing the above loss function, the specific embodiment uses a stochastic gradient descent algorithm to optimize the parameters in the model, thereby training to obtain a model for predicting key points of the face.

Secondly, this step maps the coordinates of each key point of the to-be-identified area to the key point coordinates of the aligned image according to the parameter M, wherein the parameter M is the coordinate of each key point according to the standard image and the labeled image The key point coordinates of the image corresponding to the specified feature are generated.

Taking the parameters in the above specific embodiment as an example, the specific embodiment defines five key point positions in the standard human face, which are the left eye, the right eye, the nose, the left mouth corner, and the right mouth corner position, and are detected by The face is rotated, panned, and scaled to align to a standard face. Assuming that the position of the feature point in the standard face is (x, y) and the position of the predicted feature point is (x', y'), then the relationship between the two is:

The parameters of the position are a=s cosθ, b=s sinθ, c=t _x , d=t _y 4 unknown parameters. In order to solve these 4 parameters, 4 equations are needed. In order to make the result of the alignment more robust, the specific embodiment maps five points, establishes a linear equation group, and calculates a system of linear equations by the least squares method of the linear equations. details as follows:

Expressing the above equation as a linear system of equations can become:

By minimizing

Where the solution is x=(M ^T M) ^-1 y

The above process is a detailed generation process of the parameter M. Those skilled in the art can perform alignment processing on the face image according to the parameter M. On the basis of this, other improved implementation manners that can obtain the parameter M are all within the protection scope of the present application.

S102. Align an image in the to-be-identified area with a preset standard image, and use the aligned image as a normalized image of the first to-be-identified image.

In order to reduce the interference of other objective factors, the comparison result is more accurate. After determining the area to be compared corresponding to the specified feature, the application needs to align the image in the area to be identified with the preset standard image. In a preferred embodiment of the present application, this step aligns the face to a standard face, and those skilled in the art can set the face of the standard based on existing comparison criteria, which are all within the scope of the present application. .

Furthermore, in order to further normalize the image for processing, after the above process is finished, the present application adjusts the resolution of the normalized image to a preset resolution. According to an embodiment of the present application, if the face area needs to be scaled to the 39x39 specification according to the preset parameters, the step will be the face key. The point coordinate information is normalized to the 39x39 scale space.

S103. Determine a metric distance between the normalized image of the first to-be-identified image and a normalized image of the second to-be-identified image, the metric distance according to the normalized image and the second A normalized image of the image to be identified is generated in a distance in the feature space, wherein the distance of the similar normalized image in the feature space is less than the distance of the non-similar normalized image in the feature space.

Based on the above description, in a preferred embodiment of the present application, a specified feature in the normalized image is first extracted by a convolutional neural network, and then the specified feature is mapped to the convolutional neural network and the distance metric loss function. The feature value after the feature space, and the feature value is used as the feature value of the normalized image, and finally determining the feature value of the normalized image and the feature of the normalized image of the second image to be recognized The Euclidean distance between the values, the Euclidean distance is taken as the metric distance.

For the special scenario of face authentication (comparison of two faces), the technical solution of the present application combines a deep convolutional neural network and metric learning to train a face authentication model. Deep convolutional neural networks are widely used in the field of image understanding, including image classification, image retrieval, target detection, and face recognition. Compared with the traditional feature plus classifier method, the convolutional neural network has a feature self-learning, and the model generalization ability is good. Metric learning is a linear or non-linear mapping of feature spaces such that the same face feature distance is less than a different face feature distance.

It should be noted that the convolutional neural network parameters are obtained according to the labeled image training, and the labeled image includes a normalized image in which the specified features are similar to each other and a normalized image in which the specified features are not similar to each other.

Specifically, in order to obtain a face authentication model based on depth metric learning, in a specific embodiment of the present application, sample pairing is performed in a pair-wise manner, and each sample includes two portrait images, if two images are in the image Not the same person, indicating a negative sample, if the same person is expressed as Positive sample. A positive sample is generated by combining two pictures belonging to the same person, and a negative sample is generated by a picture that is not the same person. After performing a face detection on the sample, a face key prediction model obtained by training, predicting key points of the face, aligning the face to the standard face, and scaling the image resolution to 39x39, A face authentication model based on depth metric learning can be trained.

As shown in FIG. 3, after two images in each group of samples are subjected to face detection, key point positioning, and face alignment, they are input to a convolutional neural network, and the learned facial features are extracted by convolution. The parameters of the left and right networks are shared by W. Finally, the distance measure of the feature is performed in the high-level semantic space. The depth metric learning mainly consists of two parts. One of them is the parameter W, which represents the parameters of the resulting convolutional neural network that need to be trained, and the other is the distance metric loss function. Different from traditional face recognition, the input of this application is 2 faces, and the final loss is also the distance between 2 faces in the feature space. The structure of the convolutional neural network used in this embodiment is as shown in FIG. 4, and includes four convolutional layers and two fully connected layers, wherein three convolutional layers are followed by a maximum sampling layer. The maximum sampling layer makes the extracted features have translation invariance and reduces computational complexity. Finally, the features of the face are nonlinearly mapped into the 100-dimensional feature space.

It can be seen that metric learning is to find a transformation space in which the distance of similar samples is reduced, and the distance between different types of samples is increased. Therefore, this step first searches for a nonlinear transformation through metric learning, transforming the face from the original pixel to a feature space, so that the similar face distance is small and the dissimilar face distance is large in this space. Then the facial features are extracted by the deep convolutional neural network. Finally, the features learned by the convolutional neural network are mapped to a feature space in combination with metric learning. Since the convolutional neural network continues the non-linear mapping of the face image, the feature expression thus obtained is more robust than the artificially designed feature, and the face authentication accuracy is higher.

S104. If the metric distance is greater than a preset threshold, confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image.

S105. If the metric distance is less than or equal to the threshold, confirm that the first to-be-identified image is similar to the specified feature of the second to-be-identified image.

In a specific embodiment of S103, the resulting 100-dimensional feature will be subjected to metric learning, and the loss function employed in the process is as follows:

among them

Represents a generalized logical loss function. (X _i , X _j ) ∈ P denotes a sample set, l _ij denotes a class of samples, l _ij =1 means that X _i and X _j are the same person, and l _ij = -1 means that X _i and X _j are not the same person, W Is the parameter of the model, and F _W (X _i ) indicates the value of the feature mapped to 100-dimensional when the current model parameter is W.

Indicates the distance between two faces in the feature space. The smaller the distance, the more similar the two faces are. When (X _i , X _j ) is the same person, l _ij =1, the loss function follows

Increases and increases, correspondingly when (X _i , X _j ) is not the same person, the loss function

It increases and decreases, and τ indicates whether it is the threshold of the same person.

The parameter W of the model can be obtained by minimizing the loss function. Preferably, the technician can use the chain derivation rule to obtain the gradient of the corresponding parameter and use the stochastic gradient descent method (SGD) to optimize the parameters of the calculation model. Other calculation models capable of achieving the optimization effect are also within the protection scope of the present application. Inside.

Based on the above description, when a pair of images is input, the faces in the map are respectively detected, and feature point extraction and face alignment are performed according to the face region. Then, according to the model obtained in the previous step, the feature extraction is performed and the feature is mapped into the space of 100 dimensions. Finally, the Euclidean distance of the two facial features is calculated. When the distance is greater than or equal to τ, it means that it is not the same person, otherwise it is the same person.

The above solution describes in detail how to determine whether a group of images to be identified is similar or not. In a specific implementation scenario, the process can be completed by the client and the server. In this implementation scenario, the user can use a mobile terminal such as a smart phone or a tablet to upload images and information, and also upload images and related information through the PC terminal. As a subject for processing an image, the server may be a data server or a web server pre-configured by the system operator.

As a link between the user and the server, the client is mainly used to forward the user's input content to the server, and the server verifies the identity of the user according to the content input by the user, and finally the client displays the verification result according to the server. . The following first introduces the similar image recognition method on the client side, as shown in FIG. 5, including the following steps:

S501. Receive an identity authentication request of the user, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user.

It should be noted that, in this embodiment, the form of the client is not limited, and the client may be a PC device or a mobile device. However, both can provide the user with the function of image uploading and information input. Specifically, the client first acquires the image uploaded by the user and the information input by the user, and then uses the image as the first image to be recognized, and Using the information as the authentication information, and finally generating the identity authentication request according to the first to-be-identified image and the authentication information.

S502. Send the identity authentication request to the server, so that the server acquires a second to-be-identified image corresponding to the user according to the authentication information.

After obtaining the authentication information of the user, the server may obtain the second to-be-identified image corresponding to the user according to the data. In a specific embodiment, the server queries the database for the image in the user ID according to the identity information provided by the user, and uses the image as the second image to be identified, thereby determining whether the image uploaded by the user is the same as the ID card. Image matching.

S503. Receive an identity authentication response sent by the server.

In this embodiment, the identity authentication response is an identity authentication success response or an identity authentication failure response, wherein the identity authentication success response is that the server confirms that the first to-be-identified image is similar to the specified feature of the second to-be-identified image. And then generated, and the identity authentication failure response is generated by the server after confirming that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image.

S504. Display an authentication result to the user according to the identity authentication response.

Based on the identity authentication success response or the identity authentication failure response, the specific implementation process of this step is as follows:

(1) When the client receives the identity authentication success response, the client displays the preset interface corresponding to the identity authentication success response to the user;

(2) when the client receives the identity authentication failure response, the client displays the preset interface corresponding to the identity authentication failure response to the user, and shows whether the user needs to perform Manually verified prompt information.

Since the present application automatically judges a group of images to be recognized by the device, in order to further avoid the influence of the error, when the failure response is returned to the user, the prompt information indicating whether manual verification is required is simultaneously displayed to the user. . If the user thinks that the manual review needs to be resubmitted, then the client re-advertises the manual verification request, and after receiving the manual verification request from the user, the client sends the identity authentication request to the preset server.

The above is the process of the client, and is mainly used to implement the interaction between the user and the server. The following embodiment is a similar image recognition method on the server side, as shown in FIG. 6, including the following steps:

S601. Receive an identity authentication request sent by the client, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user.

S602. Query, according to the authentication information, a second to-be-identified image corresponding to the user.

S603. Acquire an area to be compared corresponding to the specified feature in the first to-be-identified image.

S604. Align an image in the to-be-identified area with a preset standard image, and use the aligned image as a normalized image of the first to-be-identified image, where the standard image corresponds to the specified feature. ;

S605. Determine a metric distance between the normalized image and a normalized image of the second to-be-identified image, the metric distance according to the normalized image and the normalized image of the second to-be-identified image a distance generation in the feature space, wherein a distance of the similar normalized image in the feature space is less than a distance of the non-similar normalized image in the feature space;

S606. If the metric distance is greater than a preset threshold, confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image, and return an identity verification failure response to the client.

S607. If the metric distance is less than or equal to the threshold, confirm that the first to-be-identified image is similar to the specified feature of the second to-be-identified image, and return an identity verification success response to the client.

To achieve the above technical purpose, the present application also proposes a similar image recognition device, as shown in FIG. 7, comprising:

The obtaining module 710 is configured to obtain an area to be compared corresponding to the specified feature in the first to-be-identified image;

The aligning module 720 is configured to align an image in the to-be-identified area with a preset standard image, and use the aligned image as a normalized image of the first to-be-identified image, the standard image and the Corresponding to the specified feature;

a determining module 730, configured to determine a metric distance between the normalized image of the first to-be-identified image and a normalized image of the second to-be-identified image, the metric distance according to the normalized image and A normalized image of the second image to be identified is generated in a distance in the feature space, wherein a distance of the similar normalized image in the feature space is smaller than a non-similar normalized image in the feature Distance of space;

The identification module 740 is configured to confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image when the metric distance is greater than a preset threshold, and that the metric distance is less than or equal to the The threshold is confirmed to be similar to the specified feature of the second image to be recognized.

In a specific application scenario, the determining module is specifically configured to:

In a specific application scenario, the alignment module is specifically configured to:

In specific application scenarios, it also includes:

In a specific application scenario, the acquiring module is specifically configured to:

In a specific application scenario, the designated feature is specifically a face region, and the key feature includes at least a left eye region, a right eye region, a nose region, a left corner region, and a right corner region.

In a specific application scenario, the convolutional neural network parameters are obtained according to the labeled image, and the labeled image includes normalized images with specified features being similar to each other and designated features are not mutually exclusive. A similar normalized image.

The application also proposes a client, as shown in FIG. 8, comprising:

The receiving module 810 is configured to receive an identity authentication request of the user, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

The sending module 820 is configured to send the identity authentication request to the server, so that the server acquires a second to-be-identified image corresponding to the user according to the authentication information;

The receiving module 810 is further configured to receive an identity authentication response sent by the server.

The displaying module 830 is configured to display the authentication result to the user according to the identity authentication response.

In a specific application scenario, the receiving module is specifically configured to:

In a specific application scenario, the identity authentication response is an identity authentication success response or an identity authentication failure response, and further includes:

In a specific application scenario, the displaying module is specifically configured to: when the receiving module receives the identity authentication success response, display the preset interface corresponding to the identity authentication success response to the user; Or the displaying module is specifically configured to: when the receiving module receives the identity authentication failure response, display, to the user, a preset interface corresponding to the identity authentication failure response, and to the user Show tips for manual verification.

In a specific application scenario, when the receiving module displays to the user in the display module Receiving a manual verification request corresponding to the identity authentication failure response and a prompt to the user to indicate whether manual verification is required, the receiving module instructing the sending module to The identity authentication request is sent to the preset server.

The embodiment of the present application further provides a server, as shown in FIG. 9, including:

The receiving module 910 is configured to receive an identity authentication request sent by the client, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

The querying module 920 is configured to query, according to the authentication information, a second to-be-identified image corresponding to the user;

The obtaining module 930 is configured to acquire an area to be compared corresponding to the specified feature in the first to-be-identified image;

An alignment module 940, configured to align an image in the to-be-identified area with a preset standard image, and use the aligned image as a normalized image of the first to-be-identified image, the standard image and the Corresponding to the specified feature;

a determining module 950, configured to determine a metric distance between the normalized image of the first to-be-identified image and the normalized image of the second to-be-identified image, the metric distance according to the normalized image and a normalized image of the second image to be identified is generated in a distance in the feature space, wherein a distance of the similar normalized image in the feature space is smaller than a distance of the non-similar normalized image in the feature space ;

The identification module 960 is configured to confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image when the metric distance is greater than a preset threshold, and that the metric distance is less than or equal to the Confirming, at the threshold, that the first to-be-identified image is similar to a specified feature of the second to-be-identified image;

The sending module 970 is configured to: when the identifying module confirms that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image, return an identity verification failure response to the client, and And when the identifying module confirms that the first to-be-identified image is similar to the specified feature of the second to-be-identified image, returning an identity verification success response to the client.

In specific application scenarios, it also includes:

In a specific application scenario, the convolutional neural network parameters are trained according to the labeled image, and the labeled image includes a normalized image in which the specified features are similar to each other and a normalized image in which the specified features are not similar to each other.

Through the description of the above embodiments, those skilled in the art can clearly understand the present application. It can be implemented in hardware or by means of software plus the necessary general hardware platform. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several The instructions are for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various implementation scenarios of the present application.

A person skilled in the art can understand that the drawings are only a schematic diagram of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily required to implement the application.

A person skilled in the art may understand that the modules in the apparatus in the implementation scenario may be distributed in the apparatus for implementing the scenario according to the implementation scenario description, or may be correspondingly changed in one or more devices different from the implementation scenario. The modules of the above implementation scenarios may be combined into one module, or may be further split into multiple sub-modules.

The above serial numbers are only for the description, and do not represent the advantages and disadvantages of the implementation scenario.

The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any changes that can be made by those skilled in the art should fall within the protection scope of the present application.

Claims

A similar image recognition method, comprising:

Obtaining an area to be compared corresponding to the specified feature in the first to-be-identified image;

Aligning an image in the to-be-identified area with a preset standard image, and using the aligned image as a normalized image of the first to-be-identified image, the standard image corresponding to the specified feature;

Determining a metric distance between the normalized image and a normalized image of the second image to be recognized, the metric distance being characterized according to the normalized image and the normalized image of the second image to be recognized Distance generation in space, wherein the distance of the similar normalized image in the feature space is less than the distance of the non-similar normalized image in the feature space;

If the metric distance is greater than a preset threshold, confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image;

And if the metric distance is less than or equal to the threshold, confirming that the first to-be-identified image is similar to a specified feature of the second to-be-identified image.
The method according to claim 1, wherein the area to be compared corresponding to the specified feature in the first to-be-identified image is obtained, specifically:

Determining the to-be-contrast area in the first to-be-identified image according to a detection algorithm corresponding to the specified feature;

The key point coordinates corresponding to the plurality of key point features of the specified feature in the to-be-contrast area are obtained by a preset key point regression model.
The method according to claim 2, wherein the image in the area to be identified is aligned with a preset standard image, specifically:

Mapping the coordinates of each key point of the to-be-identified area to the key point coordinates of the aligned image according to the parameter M;

Wherein the parameter M is a coordinate of each key point according to the standard image and an image that has been labeled The key point coordinates of the image corresponding to the specified feature are generated.
The method of claim 3, further comprising: after the aligned image is used as the normalized image of the first image to be recognized,

The resolution of the normalized image is adjusted to a preset resolution.
The method according to claim 1, wherein the metric distance between the normalized image and the normalized image of the second image to be recognized is determined, specifically:

Extracting a specified feature in the normalized image by a convolutional neural network;

Determining, according to the convolutional neural network and the distance metric loss function, the feature value of the specified feature after mapping to the feature space, and using the feature value as the feature value of the normalized image;

Determining an Euclidean distance between a feature value of the normalized image and a feature value of a normalized image of the second to-be-identified image, the Euclidean distance being used as the metric distance.
The method according to any one of claims 1 to 5, wherein the designated feature is specifically a face region, and the key feature includes at least a left eye region, a right eye region, a nose region, a left corner region, and Right corner area.
The method of claim 6 wherein:

The convolutional neural network parameters are trained based on an annotated image comprising a normalized image in which the specified features are similar to each other and a normalized image in which the specified features are not similar to each other.
A similar image recognition device, comprising:

An acquiring module, configured to acquire an area to be compared corresponding to the specified feature in the first to-be-identified image;

An alignment module, configured to align an image in the to-be-identified area with a preset standard image, and use the aligned image as a normalized image of the first to-be-identified image, the standard image and the Specify the feature correspondence;

a determining module, configured to determine a metric distance between the normalized image of the first to-be-identified image and a normalized image of the second to-be-identified image, the metric distance according to the normalized image and the Generating a normalized image of the second image to be recognized in the feature space, wherein The distance of the normalized image in the feature space is less than the distance of the non-similar normalized image in the feature space;

An identification module, configured to confirm, when the metric distance is greater than a preset threshold, that the first to-be-identified image is not similar to a specified feature of the second to-be-identified image, and that the metric distance is less than or equal to the threshold It is confirmed that the first to-be-identified image is similar to the specified feature of the second to-be-identified image.
The device according to claim 8, wherein the determining module is specifically configured to:

Determining the to-be-contrast area in the first to-be-identified image according to a detection algorithm corresponding to the specified feature, and acquiring a plurality of keys in the to-be-contrast area and the specified feature by using a preset key point regression model The key point coordinates corresponding to the point feature.
The device according to claim 9, wherein the alignment module is specifically configured to:

Mapping each key point coordinate of the to-be-identified area to a key point coordinate of the aligned image according to the parameter M, wherein the parameter M is according to each key point coordinate of the standard image and the labeled image Specifies the keypoint coordinates of the image corresponding to the feature.
The device according to claim 8, wherein the obtaining module is specifically configured to:

Extracting a specified feature in the normalized image by a convolutional neural network;

Determining, according to the convolutional neural network and the distance metric loss function, the feature value of the specified feature after mapping to the feature space, and using the feature value as the feature value of the normalized image;

Determining an Euclidean distance between a feature value of the normalized image and a feature value of a normalized image of the second to-be-identified image, the Euclidean distance being used as the metric distance.
A similar image recognition method is applied to a client, and the method includes:

Receiving an identity authentication request of the user, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

Sending the identity authentication request to the server, so that the server acquires a second to-be-identified image corresponding to the user according to the authentication information;

Receiving an identity authentication response sent by the server;

The authentication result is presented to the user according to the identity authentication response.
The method of claim 12, wherein the receiving the user's identity authentication request is:

Obtaining an image uploaded by the user and information input by the user;

Using the image as the first to-be-identified image, and using the information as the authentication information;

And generating the identity authentication request according to the first to-be-identified image and the authentication information.
The method of claim 13, wherein the identity authentication response is an identity authentication success response or an identity authentication failure response, and further includes:

The identity authentication success response is generated by the server after confirming that the first to-be-identified image is similar to the specified feature of the second to-be-identified image;

The identity authentication failure response is generated by the server after confirming that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image.
The method according to claim 14, wherein the authentication result is displayed to the user according to the identity authentication response, specifically:

When receiving the identity authentication success response, displaying, by the user, a preset interface corresponding to the identity authentication success response;

When receiving the identity authentication failure response, the user is presented with a preset interface corresponding to the identity authentication failure response, and prompting the user whether the manual verification is required.
The method according to claim 15, wherein after the user is presented with the preset interface corresponding to the identity authentication failure response and the user is prompted to perform manual verification, the method further includes:

Sending the identity authentication request to a preset if a manual verification request of the user is received Server.
A client, comprising:

a receiving module, configured to receive an identity authentication request of the user, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

a sending module, configured to send the identity authentication request to the server, so that the server acquires a second to-be-identified image corresponding to the user according to the authentication information;

The receiving module is further configured to receive an identity authentication response sent by the server;

And a display module, configured to display the authentication result to the user according to the identity authentication response.
A similar image recognition method is applied to a server, the method comprising:

Receiving an identity authentication request sent by the client, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

Querying, according to the authentication information, a second to-be-identified image corresponding to the user;

Obtaining an area to be compared corresponding to the specified feature in the first to-be-identified image;

Aligning an image in the to-be-identified area with a preset standard image, and using the aligned image as a normalized image of the first to-be-identified image, the standard image corresponding to the specified feature;

Determining a metric distance between the normalized image and a normalized image of the second image to be recognized, the metric distance being characterized according to the normalized image and the normalized image of the second image to be recognized Distance generation in space, wherein the distance of the similar normalized image in the feature space is less than the distance of the non-similar normalized image in the feature space;

If the metric distance is greater than a preset threshold, confirm that the first to-be-identified image is not similar to the specified feature of the second to-be-identified image, and return an identity verification failure response to the client;

If the metric distance is less than or equal to the threshold, confirm that the first to-be-identified image is similar to the specified feature of the second to-be-identified image, and return an identity verification success response to the client.
The method of claim 18, wherein acquiring the first image to be identified is Specify the area to be compared corresponding to the feature, specifically:

Determining the to-be-contrast area in the first to-be-identified image according to a detection algorithm corresponding to the specified feature;

The key point coordinates corresponding to the plurality of key point features of the specified feature in the to-be-contrast area are obtained by a preset key point regression model.
The method according to claim 19, wherein the image in the area to be identified is aligned with a preset standard image, specifically:

Mapping the coordinates of each key point of the to-be-identified area to the key point coordinates of the aligned image according to the parameter M;

The parameter M is generated according to coordinates of each key point of the standard image and key point coordinates of an image corresponding to the specified feature in the labeled image.
The method according to claim 18, wherein determining a metric distance between the normalized image and the normalized image of the second image to be recognized is specifically:

Extracting a specified feature in the normalized image by a convolutional neural network;

Determining, according to the convolutional neural network and the distance metric loss function, the feature value of the specified feature after mapping to the feature space, and using the feature value as the feature value of the normalized image;

Determining an Euclidean distance between a feature value of the normalized image and a feature value of a normalized image of the second to-be-identified image, the Euclidean distance being used as the metric distance.
A server, comprising:

Receiving, by the receiving module, an identity authentication request sent by the client, where the identity authentication request carries the first to-be-identified image uploaded by the user and the authentication information of the user;

a querying module, configured to query, according to the authentication information, a second to-be-identified image corresponding to the user;

An acquiring module, configured to acquire an area to be compared corresponding to the specified feature in the first to-be-identified image;

An alignment module, configured to align an image in the area to be identified with a preset standard image, And using the aligned image as a normalized image of the first to-be-identified image, the standard image corresponding to the designated feature;

a determining module, configured to determine a metric distance between the normalized image of the first to-be-identified image and a normalized image of the second to-be-identified image, the metric distance according to the normalized image and the Calculating a distance of the normalized image of the second image to be recognized in the feature space, wherein a distance of the similar normalized image in the feature space is smaller than a distance of the non-similar normalized image in the feature space;

An identification module, configured to confirm, when the metric distance is greater than a preset threshold, that the first to-be-identified image is not similar to a specified feature of the second to-be-identified image, and that the metric distance is less than or equal to the threshold Confirming that the first to-be-identified image is similar to a specified feature of the second to-be-identified image;

a sending module, configured to return an identity verification failure response to the client when the identification module confirms that the first to-be-identified image is not similar to a specified feature of the second to-be-identified image, and confirm in the identification module And returning the identity verification success response to the client when the first to-be-identified image is similar to the specified feature of the second to-be-identified image.
The server according to claim 22, wherein the determining module is specifically configured to:

Determining the to-be-contrast area in the first to-be-identified image according to a detection algorithm corresponding to the specified feature, and acquiring a plurality of keys in the to-be-contrast area and the specified feature by using a preset key point regression model The key point coordinates corresponding to the point feature.
The server according to claim 23, wherein the alignment module is specifically configured to:

Mapping each key point coordinate of the to-be-identified area to a key point coordinate of the aligned image according to the parameter M, wherein the parameter M is according to each key point coordinate of the standard image and the labeled image Specifies the keypoint coordinates of the image corresponding to the feature.
The server according to claim 22, wherein the obtaining module is specifically configured to:

Extracting a specified feature in the normalized image by a convolutional neural network;

Determining, according to the convolutional neural network and the distance metric loss function, the feature value of the specified feature after mapping to the feature space, and using the feature value as the feature value of the normalized image;

Determining an Euclidean distance between a feature value of the normalized image and a feature value of a normalized image of the second to-be-identified image, the Euclidean distance being used as the metric distance.