Intelligent gate system and method based on picture recognition technology

Abstract

The invention provides an intelligent gate system and method based on a picture recognition technology, and relates to the field of intelligent recognition. A face reference image and age information are obtained from an identity card recognition image, and a camera collects a face detection image; face feature analysis is carried out on the face reference image and the face detection image by adopting a deep learning-based data processing algorithm, and information coding is carried out on the age information; therefore, whether the identity is matched or not is intelligently judged according to the face comparison feature obtained by calculating the difference between the face reference correction feature obtained under the assistance of the age information and the face detection feature, and a gate opening instruction is controlled. Thus, the accuracy of cross-age identity recognition can be remarkably improved, meanwhile, data processing is conducted through an efficient algorithm, the processing speed of face recognition is also improved, and efficient passing in crowded occasions such as public transportation is ensured.

Description

Technical Field

[0001] The present application relates to the field of intelligent recognition, and more specifically, to an intelligent gate system and method based on image recognition technology. Background Art

[0002] Gates are an automated access control device that is widely used in various places that need to control the flow of people in and out, such as subway stations, railway stations, airports, office buildings, residential areas, scenic spots, etc. With the rapid development of science and technology, especially in the fields of artificial intelligence and big data, safe and convenient management of human flow has become crucial, and the demand for efficient and intelligent access control gate systems in modern society is growing.

[0003] However, traditional face recognition technology has limitations in many aspects, such as not fully considering the impact of age changes on facial features. Specifically, as people age, facial features change significantly, such as changes in wrinkles, skin color, and facial contours, which makes it difficult for traditional algorithms to accurately recognize faces that have changed over time. In addition, in terms of real-time performance, traditional algorithms are usually complex to calculate and slow to process, especially in crowded places, where recognition delays may affect traffic efficiency. This limitation is particularly evident in scenarios such as public transportation where rapid identity verification is required, which may lead to queues and congestion, affecting user experience.

[0004] Therefore, an optimized intelligent gate solution is needed. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an intelligent gate system and method based on image recognition technology, which obtains a face reference image and age information from an ID card recognition image, and collects a face detection image by a camera, and uses a data processing algorithm based on deep learning to perform facial feature analysis on the face reference image and the face detection image, and encodes the age information, thereby intelligently judging whether the identity matches based on the face comparison features obtained by calculating the difference between the face reference correction features obtained with the assistance of age information and the face detection features, and controlling the gate opening command. In this way, the accuracy of cross-age identity recognition can be significantly improved, and at the same time, thanks to the efficient algorithm for data processing, the processing speed of face recognition is also improved, thereby ensuring efficient passage in crowded places such as public transportation.

[0006] According to one aspect of the present application, there is provided an intelligent gate system based on image recognition technology, which includes:

[0007] A face reference image age information acquisition module is used to obtain a face reference image and age information from an ID card recognition image;

[0008] A face reference feature extraction module, used for inputting the face reference image into a face feature extractor to obtain a face reference feature map;

[0009] An age information one-hot encoding module, used for performing one-hot encoding on the age information to obtain an age information one-hot encoding vector;

[0010] An age information-face reference feature joint encoding module, used for inputting the age information one-hot encoding vector and the face reference feature map into a modality-assisted heterogeneous Transformer cross-domain joint encoder to obtain an age-assisted face reference corrected feature map;

[0011] A face detection image acquisition module is used to obtain a face detection image acquired by a camera;

[0012] A face detection feature extraction module, used for inputting the face detection image into the face feature extractor to obtain a face detection feature map;

[0013] A face feature difference calculation module, used for calculating a difference feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map as a face comparison high-dimensional feature;

[0014] The identity authentication result generation module is used to obtain the identity authentication result based on the face comparison high-dimensional features, and based on the identity authentication result, determine whether to generate a gate opening instruction.

[0015] In the above-mentioned intelligent gate system based on image recognition technology, the face reference feature extraction module is used to: input the face reference image into a face feature extractor based on a hole convolutional neural network model to obtain the face reference feature map.

[0016] In the above-mentioned intelligent gate system based on image recognition technology, the age information-face reference feature joint encoding module includes: an age information feature linear transformation shape reshaping unit, which is used to perform linear transformation and feature shape reshaping on the age information one-hot encoding vector to obtain an age information one-hot encoding modulation matrix; a face reference feature linear transformation unit, which is used to perform a first linear transformation and a second linear transformation on the face reference feature map to obtain a first linear transformation face reference feature map and a second linear transformation face reference feature map; a face reference feature linear transformation reshaping unit, which is used to perform feature shape reshaping on the first linear transformation face reference feature map and the second linear transformation face reference feature map to obtain a first linear transformation face reference feature matrix and a second linear transformation face reference feature matrix; age information one-hot encoding attention A calculation unit, used to use the first linear transformation face reference feature matrix and the second linear transformation face reference feature matrix as a key matrix and a value matrix and use the age information one-hot encoding modulation matrix as a query matrix, and input the query matrix, the key matrix and the value matrix into a Transformer structure to obtain an age information one-hot encoding attention query face reference matrix; an age information feature encoding reshaping unit, used to reshape and perform point convolution encoding on the age information one-hot encoding attention query face reference matrix to obtain an age information one-hot encoding attention query face reference feature map; an age-auxiliary face feature correction unit, used to perform positional point multiplication on the age information one-hot encoding attention query face reference feature map and the face reference feature map to obtain the age-auxiliary face reference correction feature map.

[0017] In the above-mentioned intelligent gate system based on image recognition technology, the age information feature linear transformation shape reshaping unit is used to: after matrix multiplying the age information one-hot encoding vector and the age information modulation matrix to obtain the age information modulation vector, the age information modulation vector and the age information bias vector are added by position to obtain the age information one-hot encoding modulation bias vector; the age information one-hot encoding modulation bias vector is input into the sigmoid function for activation processing to obtain the age information one-hot encoding modulation activation vector; and the age information one-hot encoding modulation activation vector is reshaped to obtain the age information one-hot encoding modulation matrix.

[0018] In the above-mentioned intelligent gate system based on image recognition technology, the face reference feature linear transformation unit is used to: multiply each feature matrix along the channel dimension in the face reference feature map by position with the first face reference modulation matrix, and then add them by position with the first face reference bias matrix to obtain a first face reference bias feature map; input the first face reference bias feature map into the Sigmoid function for activation processing to obtain the first linear transformation face reference feature map; multiply each feature matrix along the channel dimension in the face reference feature map by position with the second face reference modulation matrix, and then add them by position with the second face reference bias matrix to obtain a second face reference bias feature map; input the second face reference bias feature map into the Sigmoid function for activation processing to obtain the second linear transformation face reference feature map.

[0019] In the above-mentioned intelligent gate system based on image recognition technology, the age information one-hot encoding attention calculation unit is used to: calculate the matrix product between the transposed matrix of the age information one-hot encoding modulation matrix and the first linear transformation face reference feature matrix and then input it into the softmax function to obtain the age information-face reference feature association matrix; use the age information-face reference feature association matrix as the weight matrix, calculate the matrix product between the weight matrix and the second linear transformation face reference feature matrix to obtain the age information one-hot encoding attention query face reference matrix.

[0020] In the above-mentioned intelligent gate system based on image recognition technology, the face detection feature extraction module is used to: input the face detection image into the face feature extractor based on the void convolutional neural network model to obtain the face detection feature map.

[0021] In the above-mentioned intelligent gate system based on image recognition technology, the identity authentication result generation module includes: a facial feature analysis unit, which is used to input the face comparison high-dimensional feature map into a classifier-based identity authentication device to obtain the identity authentication result, and the identity authentication result is used to indicate whether the identity matches; a gate opening instruction generation unit, which is used to generate a gate opening instruction in response to the identity authentication result being an identity match.

[0022] According to another aspect of the present application, a smart gate method based on image recognition technology is provided, which includes:

[0023] Obtain a face reference image and age information from the ID card recognition image;

[0024] Inputting the face reference image into a face feature extractor to obtain a face reference feature map;

[0025] One-hot encoding the age information to obtain a one-hot encoding vector of the age information;

[0026] Inputting the age information one-hot encoding vector and the face reference feature map into a modality-assisted heterogeneous Transformer cross-domain joint encoder to obtain an age-assisted face reference corrected feature map;

[0027] Obtaining a face detection image captured by a camera;

[0028] Inputting the face detection image into the face feature extractor to obtain a face detection feature map;

[0029] Calculating a differential feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map as a face comparison high-dimensional feature;

[0030] Based on the face comparison high-dimensional features, an identity authentication result is obtained, and based on the identity authentication result, it is determined whether to generate a gate opening instruction.

[0031] In the above-mentioned intelligent gate method based on image recognition technology, the face reference image is input into a face feature extractor to obtain a face reference feature map, including: inputting the face reference image into a face feature extractor based on a void convolutional neural network model to obtain the face reference feature map.

[0032] Compared with the prior art, the intelligent gate system and method based on image recognition technology provided by the present application obtains a face reference image and age information from an ID card recognition image, and collects a face detection image by a camera, and uses a data processing algorithm based on deep learning to perform face feature analysis on the face reference image and the face detection image, and encodes the age information, thereby intelligently judging whether the identity matches based on the face comparison features obtained by calculating the difference between the face reference correction features obtained with the assistance of age information and the face detection features, and controlling the gate opening command. In this way, the accuracy of cross-age identity recognition can be significantly improved, and at the same time, thanks to the efficient algorithm for data processing, the processing speed of face recognition is also improved, thereby ensuring efficient passage in crowded places such as public transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0034] Figure 1 4 is a system block diagram of an intelligent gate system based on image recognition technology according to an embodiment of the present application.

[0035] Figure 2 Schematic diagram of data flow of an intelligent gate system based on image recognition technology according to an embodiment of the present application.

[0036] Figure 3 It is a block diagram of the age information-face reference feature joint encoding module in the intelligent gate system based on image recognition technology according to an embodiment of the present application.

[0037] Figure 4 This is a block diagram of an identity authentication result generation module in an intelligent gate system based on image recognition technology according to an embodiment of the present application.

[0038] Figure 5 The figure is a flow chart of a smart gate method based on image recognition technology according to an embodiment of the present application. DETAILED DESCRIPTION

[0039] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0040] As an automated access control device, gates are widely used in various places where people need to be controlled, such as subway stations, railway stations, airports, office buildings, residential areas, and scenic spots. With the rapid advancement of technology, especially in the fields of artificial intelligence and big data, safe and convenient dynamic management of people flow is becoming more and more critical. The demand for efficient and intelligent access control gate systems in modern society is increasing day by day.

[0041] However, traditional face recognition technology has limitations in many aspects. For example, it does not fully consider the impact of age changes on facial features. Specifically, as age increases, facial features will change significantly, such as more wrinkles, changes in skin color, and changes in facial contours, which makes it difficult for traditional algorithms to accurately identify faces after the passage of time. In addition, from a real-time perspective, traditional algorithms are usually cumbersome to calculate and slow to process, especially in crowded places, where recognition delays are likely to have a negative impact on traffic efficiency. Such limitations are particularly prominent in scenarios such as public transportation where identity verification is required quickly, which may cause queues and congestion, thus giving users a bad experience.

[0042] Therefore, in response to the above technical problems, the present application proposes an intelligent gate system based on image recognition technology, which obtains a face reference image and age information from an ID card recognition image, and collects a face detection image by a camera, and uses image recognition technology and information processing algorithms based on deep learning to perform face feature analysis on the face reference image and the face detection image, and encodes the age information, so as to intelligently judge whether the identity matches according to the face comparison features obtained by calculating the difference between the face reference correction features obtained with the assistance of age information and the face detection features, and control the gate opening instruction. In this way, by using the age information on the ID card, the system can predict and adapt to the facial features of the face that change over time, such as wrinkles and changes in facial contours, thereby improving the recognition accuracy across ages. At the same time, an efficient deep learning model and an optimized algorithm are used to accurately compare the face reference features and the detection features, which improves the processing speed and accuracy of face recognition, thereby ensuring efficient passage in crowded places such as public transportation.

[0043] Figure 1 4 is a system block diagram of an intelligent gate system based on image recognition technology according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the intelligent gate system based on image recognition technology according to an embodiment of the present application. Figure 1 and Figure 2 As shown, in the intelligent gate system 100 based on image recognition technology, it includes: a face reference image age information acquisition module 110, which is used to obtain a face reference image and age information from an ID card recognition image; a face reference feature extraction module 120, which is used to input the face reference image into a face feature extractor to obtain a face reference feature map; an age information one-hot encoding module 130, which is used to one-hot encode the age information to obtain an age information one-hot encoding vector; an age information-face reference feature joint encoding module 140, which is used to input the age information one-hot encoding vector and the face reference feature map into a heterogeneous Transformer cross-domain joint encoder based on modality assistance. To obtain an age-assisted face reference correction feature map; a face detection image acquisition module 150, used to obtain a face detection image collected by a camera; a face detection feature extraction module 160, used to input the face detection image into the face feature extractor to obtain a face detection feature map; a face feature difference calculation module 170, used to calculate the difference feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map as a face comparison high-dimensional feature; an identity authentication result generation module 180, used to obtain an identity authentication result based on the face comparison high-dimensional feature, and based on the identity authentication result, determine whether to generate a gate opening instruction.

[0044] In the embodiment of the present application, the face reference image age information acquisition module 110 is used to obtain the face reference image and age information from the ID card recognition image. It should be understood that the face reference image information in the ID card recognition image is the core data for the gate machine to identify the individual identity. It provides a standard facial feature image for comparison with the real-time captured face image to perform identity authentication. The age information in the ID card image is used to adjust the face reference image to adapt to the influence of facial features changing with age. As people age, their facial features will change (such as wrinkles, skin color changes, etc.), which may cause the recognition accuracy to decrease by relying solely on static reference images. The present application combines age information with face information to generate an age-assisted corrected feature map, thereby improving the accuracy of the gate machine in identifying individuals of different age groups. In particular, in a specific implementation method of the embodiment of the present application, the face detection algorithm in the library such as OpenCV or Dlib can be used to identify and locate the face in the ID card image, and extract the corresponding face reference image data; and the age information on the ID card can be extracted using optical character recognition technology.

[0045] In an embodiment of the present application, the face reference feature extraction module 120 is used to input the face reference image into a face feature extractor to obtain a face reference feature map. Specifically, in an embodiment of the present application, the face reference feature extraction module is used to: input the face reference image into a face feature extractor based on a dilated convolutional neural network model to obtain the face reference feature map. It should be understood that the face reference image contains key face feature information of different scales. The dilated convolution has a good advantage in image processing, and can extract face features at different scales to enhance the recognition ability of faces of different resolutions and sizes. Therefore, in the technical solution of the present application, the face reference image is input into a face feature extractor based on a dilated convolutional neural network model to capture and mine rich face feature detail information to obtain a face reference feature map. The face feature extractor based on a dilated convolutional neural network model described here is a dilated convolutional neural network model.

[0046] In an embodiment of the present application, the age information unique hot encoding module 130 is used to uniquely encode the age information to obtain the unique hot encoding vector of the age information. Accordingly, considering that age is usually a continuous variable, if it is directly input as a numerical value, the model may mistakenly understand it as having a sequential relationship. Therefore, in order to convert the age information into the input numerical data required by the machine learning algorithm, so as to better understand and analyze the age information, in the technical solution of the present application, the age information is uniquely encoded to obtain the unique hot encoding vector of the age information. Unique hot encoding is a coding method for converting categorical variables into numerical formats. Its main idea is to represent each category (such as the year, month, and day category on the ID card) as a binary vector, in which only one position is 1 and the rest of the positions are 0. By uniquely encoding the age information, the model can better understand and process these features, thereby improving the accuracy and efficiency of subsequent identity judgment.

[0047] In an embodiment of the present application, the age information-face reference feature joint encoding module 140 is used to input the age information one-hot encoding vector and the face reference feature map into a heterogeneous Transformer cross-domain joint encoder based on modality assistance to obtain an age-assisted face reference correction feature map. Accordingly, considering that there is a mutual correlation between the age information one-hot encoding vector and the face reference feature map, for example, certain facial features of the face may be related to age. Based on this, in order to more accurately analyze and understand the interaction and influence relationship between age information and face reference features, in the technical solution of the present application, the age information one-hot encoding vector is used as modality auxiliary information to enhance the face feature representation, that is, the age information is used as additional contextual information to enrich the face features. Specifically, the age information one-hot encoding vector and the face reference feature map are input into a heterogeneous Transformer cross-domain joint encoder based on modality assistance to obtain an age-assisted face reference correction feature map.

[0048] It is worth mentioning that the modality-assisted heterogeneous Transformer cross-domain joint encoder is a processing technology between cross-modal data, which realizes the effective fusion and optimization of different modal features through fine feature processing and the self-attention mechanism of the Transformer structure. In detail, first, the age information one-hot encoding vector is linearly transformed and the feature shape is reshaped to generate an age information one-hot encoding modulation matrix as auxiliary information of the facial features. At the same time, the facial reference feature map is linearly transformed and reshaped to extract the most critical information of the facial features, and the first linear transformation face reference feature matrix and the second linear transformation face reference feature matrix are obtained. Subsequently, the first linear transformation face reference feature matrix and the second linear transformation face reference feature matrix are used as the key matrix and the value matrix respectively, and the age information one-hot encoding modulation matrix is ​​input into the Transformer structure as the query matrix to realize the cross-modal dynamic interaction and mutual correlation between the age information and the facial feature information. Then, the age-information one-hot encoding attention query face reference matrix obtained after the interaction is reshaped and dot convolutional encoded to further capture and extract key features in the features, generating the age-information one-hot encoding attention query face reference feature map. Finally, by calculating the positional dot product between the age-information one-hot encoding attention query face reference feature map and the face reference feature map, the cross-modal features between age information and face features and the information of the original face feature map are integrated to generate the final age-assisted face reference correction feature map.

[0049] Specifically, Figure 3 FIG. 1 is a block diagram of an age information-face reference feature joint encoding module in an intelligent gate system based on image recognition technology according to an embodiment of the present application. Figure 3As shown, the age information-face reference feature joint encoding module 140 includes: an age information feature linear transformation shape reshaping unit 141, which is used to perform linear transformation and feature shape reshaping on the age information one-hot encoding vector to obtain an age information one-hot encoding modulation matrix; a face reference feature linear transformation unit 142, which is used to perform a first linear transformation and a second linear transformation on the face reference feature map to obtain a first linear transformation face reference feature map and a second linear transformation face reference feature map; a face reference feature linear transformation reshaping unit 143, which is used to perform feature shape reshaping on the first linear transformation face reference feature map and the second linear transformation face reference feature map to obtain a first linear transformation face reference feature matrix and a second linear transformation face reference feature matrix; an age information one-hot encoding attention calculation unit 144 , used to use the first linear transformation face reference feature matrix and the second linear transformation face reference feature matrix as the key matrix and the value matrix and the age information one-hot encoding modulation matrix as the query matrix, input the query matrix, the key matrix and the value matrix into the Transformer structure to obtain the age information one-hot encoding attention query face reference matrix; the age information feature encoding reshaping unit 145, used to reshape and point convolutionally encode the age information one-hot encoding attention query face reference matrix to obtain the age information one-hot encoding attention query face reference feature map; the age-auxiliary face feature correction unit 146, used to perform positional point multiplication of the age information one-hot encoding attention query face reference feature map with the face reference feature map to obtain the age-auxiliary face reference correction feature map.

[0050] More specifically, in an embodiment of the present application, the age information feature linear transformation reshape reshaping unit is used to: after matrix multiplying the age information one-hot encoding vector and the age information modulation matrix to obtain the age information modulation vector, positionally add the age information modulation vector and the age information bias vector to obtain the age information one-hot encoding modulation bias vector; input the age information one-hot encoding modulation bias vector into the Sigmo id function for activation processing to obtain the age information one-hot encoding modulation activation vector; and reshape the age information one-hot encoding modulation activation vector to obtain the age information one-hot encoding modulation matrix.

[0051] More specifically, in an embodiment of the present application, the face reference feature linear transformation unit is used to: multiply each feature matrix along the channel dimension in the face reference feature map by position with the first face reference modulation matrix, and then add the matrix by position with the first face reference bias matrix to obtain a first face reference bias feature map; input the first face reference bias feature map into the Sigmoid function for activation processing to obtain the first linear transformation face reference feature map; multiply each feature matrix along the channel dimension in the face reference feature map by position with the second face reference modulation matrix, and then add the matrix by position with the second face reference bias matrix to obtain a second face reference bias feature map; input the second face reference bias feature map into the Sigmoid function for activation processing to obtain the second linear transformation face reference feature map.

[0052] More specifically, in an embodiment of the present application, the age information one-hot encoding attention calculation unit is used to: calculate the matrix product between the transposed matrix of the age information one-hot encoding modulation matrix and the first linear transformation face reference feature matrix and then input the matrix product into a softmax function to obtain an age information-face reference feature association matrix; use the age information-face reference feature association matrix as a weight matrix, calculate the matrix product between the weight matrix and the second linear transformation face reference feature matrix to obtain the age information one-hot encoding attention query face reference matrix.

[0053] In the embodiment of the present application, specifically, the age information-face reference feature joint encoding module is used to: input the age information one-hot encoding vector and the face reference feature map into a heterogeneous Transformer cross-domain joint encoder based on modality assistance, and process them with the following cross-domain joint encoding formula to obtain the age-assisted face reference correction feature map; wherein the cross-domain joint encoding formula is:

[0054] V l =σ(W l V s +B l )

[0055] M l = reshape(V l )

[0056] F1=σ(W1F i +B1)

[0057] F2=σ(W2F i +B2)

[0058] M1=reshape(F1)

[0059] M2=reshape(F2)

[0060]

[0061]

[0062] F w =Conv 1×1 [reshape(M t )]

[0063] F i ′=F w ⊙F i

[0064] Among them, V s is the one-hot encoding vector of the age information, W l is the age information modulation matrix, B l is the age information bias vector, σ(·) is the Sigmoid function, V l is the age information one-hot encoding modulation activation vector, reshape(·) is the shape reshaping operation, M l is the one-hot encoding modulation matrix of the age information, F i is the face reference feature map, W1 and W2 are the first face reference modulation matrix and the second face reference modulation matrix, B1 and B2 are the first face reference bias matrix and the second face reference bias matrix, F1 and F2 are the first linear transformation face reference feature map and the second linear transformation face reference feature map, M1 and M2 are the first linear transformation face reference feature matrix and the second linear transformation face reference feature matrix, M l T is the transposed matrix of the one-hot encoding modulation matrix of the age information, softmax(·) is the softmax function, M a is the age information-face reference feature association matrix, is the matrix product, M t The age information is one-hot encoded attention query face reference matrix, Conv 1×1 (·) is the point convolution operation, F w is the age information uniquely encoded attention query face reference feature map, ⊙ is the position point multiplication, F s ' is the age-assisted face reference correction feature map.

[0065] In the embodiment of the present application, the face detection image acquisition module 150 is used to obtain the face detection image acquired by the camera. It should be understood that the face detection image acquired by the camera is the basic data for identity authentication. By capturing the user's facial features in real time, it can be compared with the stored identity information to confirm the user's identity.

[0066] In an embodiment of the present application, the face detection feature extraction module 160 is used to input the face detection image into the face feature extractor to obtain a face detection feature map. Specifically, in an embodiment of the present application, the face detection feature extraction module is used to: input the face detection image into the face feature extractor based on the dilated convolutional neural network model to obtain the face detection feature map. Accordingly, considering that the face detection image reflects the key feature information of face detection, therefore, in the technical solution of the present application, the face detection image is input into the face feature extractor based on the dilated convolutional neural network model to capture and extract richer and more critical face feature information to obtain a face detection feature map. It should be understood that the dilated convolutional neural network model processes the input face detection image by using a special dilated convolution kernel, thereby achieving the extraction of facial features. That is, the atrous convolution expands the receptive field by inserting "holes" in the convolution kernel, which enables the model to capture a wider range of contextual information with fewer parameters. As a result, the atrous convolutional neural network can still provide excellent performance when processing complex scenes, such as subtle changes in user expressions or in unfavorable lighting conditions, and can more accurately recognize and understand the user's facial features.

[0067] In an embodiment of the present application, the facial feature differential calculation module 170 is used to calculate the differential feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map as a face comparison high-dimensional feature. It should be understood that in order to more carefully and accurately display the difference between the face detection feature map and the age-assisted face reference correction feature map, so as to show the subtle changes in the face, in the technical solution of the present application, calculating the differential feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map helps to identify whether the identity matches. That is, by focusing on the differential features between the two, the system can more sensitively identify the unique and subtle differences between different individuals, thereby improving the accuracy of recognition.

[0068] In the embodiment of the present application, the identity verification result generation module 180 is used to obtain the identity verification result based on the face comparison high-dimensional feature, and determine whether to generate a gate opening instruction based on the identity verification result. Specifically, Figure 4FIG. 1 is a block diagram of an identity authentication result generation module in an intelligent gate system based on image recognition technology according to an embodiment of the present application. Figure 4 As shown, the identity authentication result generation module 180 includes: a face feature parsing unit 181, which is used to input the face comparison high-dimensional feature map into the classifier-based identity authentication device to obtain the identity authentication result, and the identity authentication result is used to indicate whether the identity matches; a gate opening instruction generation unit 182, which is used to generate a gate opening instruction in response to the identity authentication result being an identity match. That is, the face comparison high-dimensional feature obtained by performing a differential calculation between the face detection feature map and the age-assisted face reference correction feature map is used for classification processing, so as to intelligently determine whether the identity matches and control the gate opening instruction. In this way, by using the age information on the ID card, the system can predict and adapt to the facial features of the face that change over time, such as wrinkles and facial contour changes, thereby improving the recognition accuracy across ages. At the same time, an efficient deep learning model and an optimized algorithm are used to accurately compare the face reference features and the detection features, thereby improving the processing speed and accuracy of face recognition, thereby ensuring efficient passage in crowded places such as public transportation.

[0069] In particular, in a preferred example, when the face reference feature map and the face detection feature map express the face image semantic features of the face reference image and the face detection image respectively, after the modality-assisted heterogeneous Transformer cross-domain joint encoder performs channel constraints on the face reference feature map based on the age information encoding features, the face contrast high-dimensional feature map, which is the differential feature map between the face detection feature map and the age-assisted face reference correction feature map, has a distribution regression mode shift caused by the channel dimension semantic association alignment shift, that is, it causes the face contrast high-dimensional feature map to be input into the classifier-based authenticator. The identity authentication result obtained overflows, affecting its accuracy.

[0070] Based on this, inputting the face comparison high-dimensional feature map into the classifier-based identity authentication device to obtain the identity authentication result specifically includes: determining the matching probability value corresponding to the identity match obtained by inputting the face comparison high-dimensional feature map into the classifier-based identity authentication device, and passing the face comparison high-dimensional feature map through a probabilistic activation function to obtain a probabilistic face comparison high-dimensional feature map; subtracting the probabilistic face comparison high-dimensional feature map from the unit feature map, and using the point subtraction result feature map as the base to calculate a power function with the matching probability value as the exponent; comparing the power function feature map with the probabilistic Performing dot multiplication on the face comparison high-dimensional feature map to obtain a face comparison high-dimensional intermediate feature map; taking the absolute value of each eigenvalue of the probabilistic face comparison high-dimensional feature map as the base, calculating a power function with the inverse of the matching probability value as the exponent, and summing all eigenvalues ​​to obtain a face comparison high-dimensional bias eigenvalue; multiplying the face comparison high-dimensional bias eigenvalue by a weight serving as a hyperparameter, and performing dot multiplication with the face comparison high-dimensional intermediate feature map to obtain an optimized face comparison high-dimensional feature map; inputting the optimized face comparison high-dimensional feature map into the classifier-based identity verification device to obtain an identity verification result.

[0071] Wherein, let the probabilistic face contrast high-dimensional feature map be denoted as F, then the optimized face contrast high-dimensional feature map F' is expressed as:

[0072]

[0073] Wherein, F is the probabilistic face contrast high-dimensional feature map, F I is a unit feature map with all eigenvalues ​​being one, and f i ∈F, is the feature value of each position of the probabilistic face comparison high-dimensional feature map F, ⊙ is the point multiplication by position, is the point-by-point subtraction, p is the matching probability value, (·) ⊙p is a power function with the matching probability value as an exponent to calculate the feature values ​​of each position in the feature map, It is added by position point, α is the weight as a hyperparameter, and F' is the optimized face contrast high-dimensional feature map.

[0074] That is, for the face contrast high-dimensional feature map, based on the convergence limit of the probability distribution of the Cauchy-Hadamard form power series, the feature set of the face contrast high-dimensional feature map is represented by a power series based on the convergence probability, and a set convergence bounded bias based on each eigenvalue of the face contrast high-dimensional feature map as a convergence radius is added, so as to avoid the invalid overflow of the classification result caused by the deviation of the distribution mode of the face contrast high-dimensional feature map caused by the gradient propagation of the model parameters based on the convergence probability in the regression process of the classifier-based identity verification device under the unified probability convergence limit standard, thereby improving the accuracy of the identity verification result obtained by the classifier-based identity verification device. In this way, by using the age information on the ID card, the system can predict and adapt to the facial features of the face that change over time, such as wrinkles and facial contour changes, thereby improving the recognition accuracy across ages. At the same time, an efficient deep learning model and an optimized algorithm are used to accurately compare the reference features and detection features of the face, which improves the processing speed and accuracy of face recognition, thereby ensuring efficient passage in crowded places such as public transportation.

[0075] In summary, the intelligent gate system 100 based on the image recognition technology according to the embodiment of the present application is explained, which obtains the face reference image and age information from the ID card recognition image, and collects the face detection image by the camera, and uses the data processing algorithm based on deep learning to perform face feature analysis on the face reference image and the face detection image, and encodes the age information, so as to intelligently judge whether the identity matches according to the face comparison features obtained by calculating the difference between the face reference correction features obtained with the assistance of age information and the face detection features, and control the gate opening command. In this way, the accuracy of cross-age identity recognition can be significantly improved, and at the same time, thanks to the efficient algorithm for data processing, the processing speed of face recognition is also improved, thereby ensuring efficient passage in crowded places such as public transportation.

[0076] As described above, the smart gate system 100 based on the image recognition technology according to the embodiment of the present application can be implemented in various terminal devices, such as a server for a smart gate based on the image recognition technology. In one example, the smart gate system 100 based on the image recognition technology according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the smart gate system 100 based on the image recognition technology can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the smart gate system 100 based on the image recognition technology can also be one of the many hardware modules of the terminal device.

[0077] Alternatively, in another example, the smart gate system 100 based on image recognition technology and the terminal device may also be separate devices, and the smart gate system 100 based on image recognition technology may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0078] Figure 5 Flow chart of the intelligent gate method based on image recognition technology according to the embodiment of the present application. Figure 5 As shown, in the intelligent gate method based on image recognition technology, it includes: S110, obtaining a face reference image and age information from an ID card recognition image; S120, inputting the face reference image into a face feature extractor to obtain a face reference feature map; S130, performing one-hot encoding on the age information to obtain an age information one-hot encoding vector; S140, inputting the age information one-hot encoding vector and the face reference feature map into a modality-assisted heterogeneous Transformer cross-domain joint encoder to obtain an age-assisted face reference correction feature map; S150, obtaining a face detection image collected by a camera; S160, inputting the face detection image into the face feature extractor to obtain a face detection feature map; S170, calculating a differential feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map as a face comparison high-dimensional feature; S180, obtaining an identity authentication result based on the face comparison high-dimensional feature, and judging whether to generate a gate opening instruction based on the identity authentication result.

[0079] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned intelligent gate method based on image recognition technology have been referred to above. Figures 1 to 4 The invention has been introduced in detail in the description of the intelligent gate system based on image recognition technology, and therefore, its repeated description will be omitted.

[0080] In summary, the method of intelligent gate machine based on image recognition technology based on the embodiment of the present application is explained, which obtains the face reference image and age information from the ID card recognition image, and collects the face detection image by the camera, and uses the data processing algorithm based on deep learning to perform face feature analysis on the face reference image and the face detection image, and encodes the age information, so as to intelligently judge whether the identity matches according to the face comparison feature obtained by calculating the difference between the face reference correction feature obtained with the assistance of age information and the face detection feature, and control the gate opening instruction. In this way, the accuracy of cross-age identity recognition can be significantly improved, and at the same time, thanks to the efficient algorithm for data processing, the processing speed of face recognition is also improved, thereby ensuring efficient passage in crowded places such as public transportation.

[0081] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details of the above application are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present application to the use of the above specific details to be implemented.

Claims

1. An intelligent gate system based on image recognition technology, characterized in that: include: A face reference image age information acquisition module is used to obtain a face reference image and age information from an ID card recognition image; A face reference feature extraction module, used for inputting the face reference image into a face feature extractor to obtain a face reference feature map; An age information one-hot encoding module, used for performing one-hot encoding on the age information to obtain an age information one-hot encoding vector; An age information-face reference feature joint encoding module, used for inputting the age information one-hot encoding vector and the face reference feature map into a modality-assisted heterogeneous Transformer cross-domain joint encoder to obtain an age-assisted face reference corrected feature map; A face detection image acquisition module is used to obtain a face detection image acquired by a camera; A face detection feature extraction module, used for inputting the face detection image into the face feature extractor to obtain a face detection feature map; A face feature difference calculation module, used for calculating a difference feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map as a face comparison high-dimensional feature; The identity authentication result generation module is used to obtain the identity authentication result based on the face comparison high-dimensional features, and based on the identity authentication result, determine whether to generate a gate opening instruction.

2. The intelligent gate system based on image recognition technology according to claim 1 is characterized in that: The face reference feature extraction module is used to: input the face reference image into a face feature extractor based on a hole convolutional neural network model to obtain the face reference feature map.

3. The intelligent gate system based on image recognition technology according to claim 2 is characterized in that: The age information-face reference feature joint encoding module includes: An age information feature linear transformation and reshaping unit is used to perform linear transformation and feature reshaping on the age information one-hot encoding vector to obtain an age information one-hot encoding modulation matrix; A facial reference feature linear transformation unit, configured to perform a first linear transformation and a second linear transformation on the facial reference feature map to obtain a first linear transformation facial reference feature map and a second linear transformation facial reference feature map; A face reference feature linear transformation reshaping unit, used for reshaping the first linear transformation face reference feature map and the second linear transformation face reference feature map to obtain a first linear transformation face reference feature matrix and a second linear transformation face reference feature matrix; an age information one-hot encoding attention calculation unit, configured to use the first linear transformation face reference feature matrix and the second linear transformation face reference feature matrix as a key matrix and a value matrix and use the age information one-hot encoding modulation matrix as a query matrix, input the query matrix, the key matrix and the value matrix into a Transformer structure to obtain an age information one-hot encoding attention query face reference matrix; An age information feature encoding and reshaping unit is used to reshape and perform point convolution encoding on the age information one-hot encoding attention query face reference matrix to obtain an age information one-hot encoding attention query face reference feature map; The age-assisted facial feature correction unit is used to perform position point multiplication on the age information one-hot encoding attention query face reference feature map and the face reference feature map to obtain the age-assisted face reference correction feature map.

4. The intelligent gate system based on image recognition technology according to claim 3 is characterized in that: The age information feature linear transformation shape reshaping unit is used to: After performing matrix multiplication of the age information one-hot encoding vector and the age information modulation matrix to obtain the age information modulation vector, the age information modulation vector and the age information bias vector are added according to position to obtain the age information one-hot encoding modulation bias vector; Inputting the age information one-hot coded modulation bias vector into a Sigmoid function for activation processing to obtain an age information one-hot coded modulation activation vector; The age information one-hot coded modulation activation vector is reshaped to obtain the age information one-hot coded modulation matrix.

5. The intelligent gate system based on image recognition technology according to claim 4 is characterized in that: The face reference feature linear transformation unit is used to: Each feature matrix along the channel dimension in the face reference feature map is multiplied by position with the first face reference modulation matrix, and then added by position with the first face reference bias matrix to obtain a first face reference bias feature map; Inputting the first face reference bias feature map into the Sigmoid function for activation processing to obtain the first linear transformation face reference feature map; Multiplying each feature matrix along the channel dimension in the face reference feature map by position with the second face reference modulation matrix, and then adding the matrix by position with the second face reference bias matrix to obtain a second face reference bias feature map; The second face reference offset feature map is input into the Sigmoid function for activation processing to obtain the second linear transformation face reference feature map.

6. The intelligent gate system based on image recognition technology according to claim 5 is characterized in that: The age information one-hot encoding attention calculation unit is used to: Calculating the matrix product between the transposed matrix of the age information one-hot encoding modulation matrix and the first linear transformation face reference feature matrix and inputting the matrix product into a softmax function to obtain an age information-face reference feature association matrix; The age information-face reference feature association matrix is ​​used as a weight matrix, and the matrix product between the weight matrix and the second linear transformation face reference feature matrix is ​​calculated to obtain the age information one-hot encoding attention query face reference matrix.

7. The intelligent gate system based on image recognition technology according to claim 6 is characterized in that: The face detection feature extraction module is used to: input the face detection image into the face feature extractor based on the hole convolutional neural network model to obtain the face detection feature map.

8. The intelligent gate system based on image recognition technology according to claim 7 is characterized in that: The identity authentication result generating module includes: A face feature analysis unit, used for inputting the face comparison high-dimensional feature map into a classifier-based identity verification device to obtain the identity verification result, wherein the identity verification result is used to indicate whether the identity matches; The gate opening instruction generating unit is used to generate a gate opening instruction in response to the identity authentication result being an identity match.

9. A smart gate method based on image recognition technology, characterized in that: include: Obtain a face reference image and age information from the ID card recognition image; Inputting the face reference image into a face feature extractor to obtain a face reference feature map; One-hot encoding the age information to obtain a one-hot encoding vector of the age information; Inputting the age information one-hot encoding vector and the face reference feature map into a modality-assisted heterogeneous Transformer cross-domain joint encoder to obtain an age-assisted face reference corrected feature map; Obtaining a face detection image captured by a camera; Inputting the face detection image into the face feature extractor to obtain a face detection feature map; Calculating a differential feature map between the face detection feature map and the age-assisted face reference correction feature map to obtain a face comparison high-dimensional feature map as a face comparison high-dimensional feature; Based on the face comparison high-dimensional features, an identity authentication result is obtained, and based on the identity authentication result, it is determined whether to generate a gate opening instruction.

10. The intelligent gate method based on image recognition technology according to claim 9, characterized in that: Inputting the face reference image into a face feature extractor to obtain a face reference feature map, including: inputting the face reference image into a face feature extractor based on a hole convolutional neural network model to obtain the face reference feature map.

Images