A secure management system for storing data of face images

Abstract

The present invention discloses a security management system for storing face image data, belonging to the technical field of face image data security management, which includes a stored data processing module, a user terminal, and a data verification and scheduling module; the stored data processing module is used to process the face image data stored in the access control database; the user terminal is for user use and includes a face data management module and a face verification module; the face data management module is used for the user to manage the corresponding face information; the data verification and scheduling module is used for data verification and scheduling during access control face recognition; the face verification module is used for face verification; through the mutual cooperation among the stored data processing module, the user terminal, and the data verification and scheduling module, the secure processing of the user face data stored in the community access control is realized, avoiding the leakage of the user face data stored in the existing access control system; and enhancing the confidence of users in using face recognition.

Description

Technical Field

[0001] The present invention belongs to the technical field of face image data security management, and specifically relates to a security management system for storing face image data. Background Art

[0002] Traditional access control systems require the use of keys or passwords for authentication, which is cumbersome and easy to forget. Facial recognition technology can achieve non-contact authentication and provide a more convenient and efficient access management method. Therefore, facial recognition is currently used for access control management in many communities. However, in recent years, data leakage and abuse incidents have been frequent, posing a serious threat to personal privacy and social security. In order to prevent the leakage and abuse of face image data, many current residents are reluctant to use the facial recognition systems in communities for fear of face information leakage, which has led to significant obstacles in the application of facial recognition systems. Especially when a large amount of residents' face information is stored in the access control system, the stored face data is also vulnerable to the coveting of malicious individuals, and the property management staff lack the corresponding professional capabilities. Therefore, a secure management system needs to be established to strengthen the protection of face image data, protect residents' privacy, and enhance people's confidence in using it. Based on this, the present invention provides a security management system for storing face image data. Summary of the Invention

[0003] In order to solve the problems existing in the above solutions, the present invention provides a security management system for storing face image data.

[0004] The object of the present invention can be achieved through the following technical solutions:

[0005] A security management system for storing face image data includes a stored data processing module, a user terminal, and a data verification and scheduling module;

[0006] The stored data processing module is used to process the face image data stored in the access control database, identify in real time the users corresponding to each of the face image data stored in the access control database, and send the face image data to the user terminal of the corresponding user;

[0007] When a user matching feature corresponding to a user is identified in the access control database, the face image data of the user corresponding to the user matching feature is deleted from the access control database.

[0008] The user terminal is for user use and includes a face data management module and a face verification module;

[0009] The face data management module is used for a user to manage corresponding face information, determine the target face image of the user, generate a corresponding user matching feature based on the target face image, and send the user matching feature to the access control database.

[0010] Further, the method for determining the target face image includes:

[0011] Receiving in real time the face image data sent by the storage data processing module, and determining the user face image according to the received face image data; marking the determined user face image as the target face image;

[0012] When the face image data sent by the storage data processing module is not received, the user inputs the user face image by himself / herself. After the input of the user face image is successful, the input user face image is marked as the target face image.

[0013] Further, the method for setting the user matching feature includes:

[0014] Identifying the target face image of the user; determining a plurality of feature regions according to the target face image; processing each of the feature regions to form feature units, and combining the feature units into a user matching feature.

[0015] Further, the method for setting the feature region includes:

[0016] Marking each candidate area in the target face image, and determining corresponding initial combinations based on the user matching features already stored in the access control database;

[0017] Performing feature processing on each of the initial combinations to obtain corresponding simulated user matching features;

[0018] Calculating the difference value between the simulated user matching feature and each user matching feature already stored in the access control database;

[0019] Marking the initial combinations with each difference value greater than threshold X1 as intermediate combinations;

[0020] Identifying the number of candidate areas in each of the intermediate combinations, and selecting the intermediate combination with the least number of candidate areas as the target candidate combination;

[0021] If there are multiple intermediate combinations with the least number of candidate areas, selecting the intermediate combination with the largest difference value as the target candidate combination.

[0022] Further, the method for calculating the difference value includes:

[0023] Determine the corresponding feature units and verification units according to the simulated user matching features and the stored user matching features for which the difference values are calculated as needed;

[0024] Calculate the corresponding element differences according to the feature units and verification units, and mark the element differences as Kt, where t = 1, 2,..., c, and c is a positive integer;

[0025] According to the formula DC = ∑K t Calculate the corresponding unit difference, where DC in the formula is the unit difference;

[0026] Accumulate the unit differences of each one to obtain the corresponding difference value.

[0027] Furthermore, the method for processing the feature region includes:

[0028] Obtain the feature region image, perform grayscale processing on the feature region image to form the corresponding feature region grayscale image, and divide the feature region grayscale image into several element blocks;

[0029] Identify the grayscale values of each pixel in each of the element blocks, and form the initial matrix of the element block according to the positions of the grayscale values where, r ij represents the element value of the i-th column and the j-th row; i = 1, 2,..., n, n is a positive integer; j = 1, 2,..., m, m is a positive integer;

[0030] Adjust the initial matrix so that Then mark the adjusted initial matrix as the intermediate matrix, and the intermediate matrix is

[0031] Merge the intermediate matrices corresponding to each of the element blocks to form the feature units corresponding to the feature region image.

[0032] The data verification scheduling module is used to perform data verification scheduling during access control face recognition, obtain the face matching image, match the user terminal corresponding to the face matching image, send the face matching image to the matched user terminal, and receive in real time the face verification results sent by the face verification modules in each matched user terminal, and send the face verification results to the access control system.

[0033] Furthermore, the method for matching the user terminal according to the face matching image includes:

[0034] Perform feature processing on the face matching image to obtain the face matching image features;

[0035] Determine the matching units corresponding to the user matching features in the access control database according to the face matching image features;

[0036] Calculate the similarity value between the matching unit and the corresponding feature unit, and mark the user matching features with the similarity values all greater than the threshold X2 as matching verification features;

[0037] Identify the user terminals corresponding to each of the matching verification features, and mark them as the user terminals for face matching image matching.

[0038] Furthermore, the calculation method of the similarity value includes:

[0039] Identify each matching intermediate matrix formed in the matching unit and the corresponding feature unit and the feature intermediate matrix

[0040] According to the formula and the formula Calculate the representative values A and Q corresponding to the matching intermediate matrix and the feature intermediate matrix respectively;

[0041] Perform replacement of the corresponding matching intermediate matrix and feature intermediate matrix according to the representative values A and Q; obtain the corresponding matching similarity data and feature similarity data;

[0042] Mark the representative values in the matching similarity data and the feature similarity data as A s and Q s ; s = 1, 2,..., v, where v is a positive integer;

[0043] According to the similarity value formula Calculate the corresponding similarity value; in the formula: XS is the similarity value.

[0044] The face verification module is used to perform face verification, obtain the face matching image received by the user terminal, identify the target face image of the user, verify the face matching image according to the target face image, and obtain the corresponding face verification result; send the face verification result to the data verification scheduling module;

[0045] After obtaining the corresponding face verification result, delete the face matching image, and the user cannot view the face matching image through the user terminal.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] Through the mutual cooperation among the storage data processing module, the user terminal, and the data verification scheduling module, the secure processing of the user face data stored in the community access control is realized, avoiding the leakage of the user face data stored in the existing access control system; moreover, after the secure processing, the user face images are no longer stored in the access control system, and at the same time, the leakage of the user face images from the property side is avoided; the verification process is migrated to the user side, improving the user's confidence in using face recognition; and after obtaining the face verification result, the face matching images are deleted, and the user cannot view the face matching images through the user terminal, protecting the personal privacy of the verification personnel; at the same time, because of the user terminal matching process, it will effectively prevent some people from cracking and accumulating the face information of the verification personnel after registering as users. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings according to these drawings without creative efforts.

[0049] Figure 1 It is a block diagram of the principle of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0051] As Figure 1 shown, a secure management system for storing face image data includes a storage data processing module, a user terminal, and a data verification scheduling module;

[0052] The user terminal is used by users, generally set in the form of a small program or APP, and the users refer to the residents in the community; it includes a face data management module and a face verification module;

[0053] The face data management module is used for users to manage the corresponding face information, determine the user's face image, form the user's target face image, and generate the corresponding user matching feature based on the target face image, and send the obtained user matching feature to the access control database; the access control database is a database for storing face image data in the access control system.

[0054] Among them, the method for determining the user's face image includes:

[0055] Receive the face image data sent by the real-time receiving and storing data processing module in real time, and determine the user's face image according to the received face image data; this situation is for residents who have previously applied the face recognition function in the access control system. According to the previously recorded face image data, the user's face image is intelligently determined without the user having to record again; mark the determined user face image as the target face image;

[0056] When no face image data sent by the storage data processing module is received, it means that the user has not previously entered face information in the access control system; the user enters the face image by himself / herself. After the entry is successful, determine the user's face image and mark it as the target face image.

[0057] The method for setting user matching features includes:

[0058] Identify the target face image of the user;

[0059] Determine several feature regions according to the target face image. The feature region refers to the facial region that can represent the user; determine each face recognition region according to the existing face recognition principle and mark it as the candidate area. Determine the target candidate combination according to the combination difference of each candidate area, and mark the candidate areas in the target candidate combination as feature regions;

[0060] The combination difference means that after each candidate area is combined, analyze whether the combination of candidate areas can be different from other face information. The benchmark is the user matching features already stored in the access control database, that is, whether the user matching features corresponding to its combination are different from the user matching features already stored in the access control database. When it is judged that it is different from other user matching features, mark the corresponding combination as the initial combination, and estimate the difference value from the already stored user matching features according to the positions of each candidate area corresponding to the initial combination, that is, estimate according to the positions and quantities of the corresponding candidate areas, because some of the already stored user matching features may correspond to different numbers and positions of candidate areas, and corresponding factors will be considered during subsequent matching verification. Therefore, in order to reduce the amount of subsequent data analysis and further refine, mark all initial combinations with difference values greater than the threshold X1 as intermediate combinations, identify the number of candidate areas in each intermediate combination, and select the intermediate combination with the fewest candidate areas as the target candidate combination; if there are multiple intermediate combinations with the fewest candidate areas, select the intermediate combination with the largest difference value as the target candidate combination;

[0061] Process each feature region to form feature units, and combine the feature units into user matching features.

[0062] The calculation method of the difference value is as follows:

[0063] Process according to the initial combination to form its corresponding simulated user matching features, that is, process according to the acquisition method of user matching features; identify the facial positions corresponding to each feature unit in the user matching features;

[0064] Identify the stored user matching features for which the difference value needs to be calculated, and mark them as verified user matching features;

[0065] Determine the verification units corresponding to each feature unit in the verified user matching features according to the identified positions, that is, the feature units at the same positions as the feature units in the verified user matching features; if there is no feature unit at this position in the verified user matching features, this position can be any preset feature unit at the corresponding position, such as the feature units at each position preset according to various existing face data, the feature units at the corresponding positions in the stored other user matching features, that is, there are multiple possibilities for the verification units at this position, but the feature unit corresponding to the smallest difference value finally obtained;

[0066] Calculate the unit difference between each feature unit and the corresponding verification unit, use the element differences for accumulation to form a unit difference, and then accumulate according to each unit difference to form the corresponding difference value.

[0067] That is, identify the matrix corresponding to the feature unit and the matrix corresponding to the verification unit, calculate the difference between each corresponding element, take the absolute value, and mark it as the element difference K t , where t = 1, 2,..., c, c is a positive integer, the number of elements in the matrix; then calculate the corresponding unit difference according to the formula DC = ∑K t Calculate the corresponding unit difference, where DC is the unit difference in the formula, accumulate the unit differences available, and obtain the corresponding difference value; for the verification units with multiple possibilities, take the one with the smallest difference value as the standard.

[0068] The methods for processing each feature region include:

[0069] Obtain the feature region image, perform grayscale processing on the feature region image to form the corresponding feature region grayscale image, divide the feature region grayscale image into several element blocks of the same size, that is, the number of elements in each element block is the same and the size is the same; calculate according to the actual size, the number of elements of the feature region grayscale image and the preset element block size range, if there are multiple size options, select the largest size as the corresponding size of the element block, where the preset element block size range is set by the corresponding professional personnel;

[0070] Identify the grayscale values of each pixel in each element block, and form the initial matrix of the element block according to the positions of the grayscale values where, r ijRepresents the element value at the i-th column and j-th row, that is, the grayscale value at the corresponding position; i = 1, 2, ……, n, where n is a positive integer; j = 1, 2, ……, m, where m is a positive integer;

[0071] Adjust the initial matrix so that Then mark the adjusted initial matrix as the intermediate matrix ∑r ij Is the sum of the element values corresponding to each element in the initial matrix;

[0072] Merge the intermediate matrices corresponding to each element block to form the feature units corresponding to the feature region image. The feature units are formed by combining the intermediate matrices according to their corresponding positions in the corresponding element library to form a large matrix including all elements, that is, the feature units.

[0073] The stored data processing module is used to process the face image data stored in the access control system, identify the users corresponding to the stored face image data, send the corresponding face image data to the face data management module of the corresponding user, and when it is recognized that the stored face image data has the user matching characteristics corresponding to the user, delete the corresponding face image data stored in the access control database.

[0074] The data verification scheduling module is used to perform data verification scheduling during access control face recognition, obtain the face image of the access control recognition, mark it as the face matching image, and process the face matching image according to the setting method of the feature region, that is, process all the candidate areas in the face matching image in the corresponding manner to obtain the face matching image features;

[0075] Perform location matching between the user matching characteristics stored in the access control database and the face matching image features, that is, determine the feature units in the face matching image features that need to be matched and analyzed according to the candidate areas corresponding to the user matching characteristics, mark them as matching units, and form each matching unit;

[0076] Calculate the similarity values between each matching unit and the corresponding feature units in the user matching characteristics, and mark the user matching characteristics with similarity values all greater than the threshold X2 as the matching verification characteristics;

[0077] Identify the user terminals corresponding to each matching verification characteristic, send the face matching image to the corresponding user terminals, and receive in real time the face verification results sent by the face verification modules in each corresponding user terminal. According to the obtained face verification results, the specific verification object can be determined. If all are unqualified, the door cannot be opened; send the obtained face verification results to the access control system, and the access control system will perform access control according to the face verification results subsequently.

[0078] The calculation of the similarity value can be carried out in the following way:

[0079] One is: based on existing neural networks such as CNN networks or DNN networks, a corresponding similarity analysis model is established, and a corresponding training set is established and trained manually. The training set includes input data and output data. The input data is a combination of two matrices with equal rows and columns set by simulation, and the output data is a similarity value. The matching unit and the feature unit are analyzed by the similarity analysis model after successful training to obtain the corresponding similarity value; since the neural network is an existing technology in this field, therefore, the specific establishment and training processes are not described in detail in the present invention.

[0080] Another is: identify each intermediate matrix in the matching unit and the corresponding feature unit, and mark them as the matching intermediate matrix and the feature intermediate matrix According to the formula and the formula calculate the representative values A and Q corresponding to the matching intermediate matrix and the feature intermediate matrix respectively;

[0081] Use the corresponding representative values A and Q to replace the corresponding matching intermediate matrix and feature intermediate matrix in the matching unit and the corresponding feature unit;

[0082] Mark the replaced matching unit and feature unit as the matching similarity data and the feature similarity data respectively;

[0083] Mark the corresponding representative values in the matching similarity data and the feature similarity data as A s and Q s ; s = 1, 2,..., v, where v is a positive integer;

[0084] According to the similarity value formula calculate the corresponding similarity value; in the formula: XS is the similarity value.

[0085] The face verification module is used to perform face verification, obtain the face matching image received by the user terminal, identify the target face image of the user, verify the face matching image according to the obtained target face image, and obtain the corresponding face verification result; and when the corresponding face verification result is obtained, the obtained face matching image is deleted, and the user cannot view the face matching image through the user terminal; send the obtained face verification result to the data verification scheduling module.

[0086] Verify the face matching image according to the target face image, and implement it using the existing face recognition technology.

[0087] The above formulas are all calculated by removing the dimension and taking their numerical values. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulating a large amount of data.

[0088] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A security management system for storing data of face images, characterized in that, It includes a storage data processing module, a user terminal, and a data verification scheduling module; The storage data processing module is used to process the face image data stored in the access control database, identify the users corresponding to each of the face image data stored in the access control database in real time, and send the face image data to the user terminal of the corresponding user; When a user matching feature corresponding to a user is identified in the access control database, the face image data of the user corresponding to the user matching feature is deleted from the access control database; The user terminal is for user use, and is set in the form of an APP, and includes a face data management module and a face verification module; The face data management module is used for the user to manage the corresponding face information, receive the face image data sent by the storage data processing module in real time, determine the user's face image according to the received face image data; mark the determined user's face image as the target face image; When the face image data sent by the storage data processing module is not received, the user inputs the user's face image by himself / herself. After the user's face image is successfully input, the input user's face image is marked as the target face image; Generate a corresponding user matching feature based on the target face image, and send the user matching feature to the access control database; The data verification scheduling module is used to perform data verification scheduling during access control face recognition, obtain the face image of access control recognition, mark it as the face matching image, match the user terminal of the corresponding user according to the face matching image, send the face matching image to the matching user terminal, and receive the face verification results sent by the face verification modules in each matching user terminal in real time, and send the face verification results to the access control system; The face verification module is used to perform face verification, obtain the face matching image received by the user terminal, identify the target face image of the user, verify the face matching image according to the target face image, and obtain the corresponding face verification result; send the face verification result to the data verification scheduling module; And after obtaining the face verification result, delete the face matching image, and the user cannot view the face matching image through the user terminal.

2. The security management system for storing face image data according to claim 1, wherein The setting method of the user matching feature includes: Identify the target face image of the user; determine a number of feature regions according to the target face image; process each of the feature regions to form feature units, and combine the feature units into a user matching feature.

3. A security management system for storing face image data according to claim 2, characterized in that, The setting method of the feature region includes: Mark each candidate area in the target face image, and determine the corresponding initial combinations based on the user matching features already stored in the access control database; Perform feature processing on each of the initial combinations to obtain the corresponding simulated user matching features; Calculate the difference values between the simulated user matching features and each of the user matching features already stored in the access control database; Mark the initial combinations with each of the difference values greater than the threshold X1 as intermediate combinations; Identify the number of candidate areas in each of the intermediate combinations, and select the intermediate combination with the least number of candidate areas as the target candidate combination; When there are multiple such intermediate combinations with the least number of candidate areas, select the intermediate combination with the largest difference value as the target candidate combination.

4. A security management system for storing data of a face image according to claim 3, characterized in that, The calculation method of the difference value includes: Determine the corresponding respective feature units and verification units according to the simulated user matching features for which the difference value needs to be calculated and the stored user matching features; Calculate the corresponding element differences according to the feature units and verification units, and mark the element differences as Kt, where t = 1, 2,..., c, and c is a positive integer; Calculate the corresponding unit difference according to the formula DC = ∑K t where DC is the unit difference Accumulate the respective unit differences available to obtain the corresponding difference value.

5. The security management system for storing data of a face image according to claim 4, characterized in that, The method for processing the feature area includes: Obtain the feature area image, perform gray-scale processing on the feature area image to form the corresponding feature area gray-scale image, and divide the feature area gray-scale image into several element blocks; Identify the grayscale values of each pixel in each of the said element blocks, and form an initial matrix of the element block according to the positions of the said grayscale values ; where r ij represents the element value at the i-th column and the j-th row; i = 1, 2, ……, n, n is a positive integer; j = 1, 2, ……, m, m is a positive integer; Adjust the initial matrix such that ; then mark the adjusted initial matrix as the intermediate matrix, and the intermediate matrix is ; Merge the intermediate matrices corresponding to the respective element blocks to form the feature units corresponding to the feature area image.

6. The security management system for storing face image data according to claim 5, characterized in that, In the data verification scheduling module, the method for matching the corresponding client according to the face matching image includes: Perform feature processing on the face matching image to obtain the face matching image features; Determine the respective matching units corresponding to the respective user matching features in the access control database according to the face matching image features; Calculate the similarity values between the matching units and the corresponding feature units, and mark the user matching features for which the similarity values are all greater than the threshold X2 as the matching verification features; Identify the clients corresponding to the respective matching verification features and mark them as the clients matched by the face matching image.

7. A security management system for storing face image data according to claim 6, characterized in that, The calculation method of the similarity value includes: Identify each matching intermediate matrix formed in the matching unit and the corresponding feature unit and the feature intermediate matrix ; According to the formula and the formula calculate the representative values A and Q corresponding to the matching intermediate matrix and the feature intermediate matrix respectively; Perform replacement of the corresponding matching intermediate matrix and the feature intermediate matrix according to the representative value A and the representative value Q; obtain the corresponding matching similarity data and feature similarity data; Mark the corresponding representative values in the matching similar data and the feature-similar data as A s and Q s ; s = 1, 2, ……, v, where v is a positive integer; According to the similarity value formula calculate the corresponding similarity value; where: XS is the similarity value.

Images