CN118196856B - Social security identification method and device based on public service convenience registration - Google Patents

Abstract

The present invention relates to a social security identity recognition method based on public service convenience registration, including the following: obtaining a user's reservation request and its associated identity verification content; obtaining the user's identity recognition information corresponding to the identity verification content; when the identity recognition information matches the identity verification content, obtaining the user's social security card license information through preset rules; obtaining a typical image of the social security card license based on the social security card license information; recognizing the typical image of the social security card license to obtain the user's social security identity information; entering the user's social security identity information and generating a handling voucher; and feeding back the handling voucher to the user. The present invention establishes an entire automated process from reservation to completion of handling, which can bring users a comfortable and convenient handling experience, and also improves the license recognition accuracy, thereby improving the user's handling experience and ensuring the promotion and popularization of this product.

Description

A social security identity recognition method and device based on public service convenience registration

Technical Field

The present invention relates to the technical field related to certificate recognition, and in particular to a social security identity recognition method and device based on public service convenience registration.

Background Art

There are usually two ways to register for public services: on-site registration and online registration. Both methods require obtaining the user's social security identity information.

When obtaining a user's social security identity information, the most primitive method is to manually read and fill it out. This method is very cumbersome, time-consuming and laborious, especially during peak registration periods, and is often complained by users. Later, with the rise of artificial intelligence, a method of using a camera to obtain social security card images and then identify and automatically obtain the user's social security identity information has emerged. This method can well solve the drawbacks of manual reading and filling out, but in the process of obtaining the social security card image, the quality of the obtained social security card image is often poor due to interference from environmental factors or damage to the social security card itself, which leads to subsequent recognition failure. In addition, the existing recognition and registration process is not perfect enough. It only focuses on the recognition process and cannot provide users with a high-quality user experience.

Summary of the invention

The purpose of the present invention is to solve at least one of the deficiencies of the prior art and to provide a social security identity recognition method based on public service convenience registration.

In order to achieve the above object, the present invention adopts the following technical solutions:

Specifically, a social security identity recognition method based on public service convenience registration is proposed, including the following:

Get the user's reservation request and its associated authentication content;

Obtaining the identity information of the user corresponding to the identity verification content;

When the identity recognition information matches the identity verification content, the user's social security card information is obtained according to preset rules;

Obtaining a typical image of the social security card based on the social security card information;

Recognize the typical image of the social security card to obtain the user's social security identity information;

Enter the user's social security identity information and generate a processing voucher;

Feedback the handling certificate to the user.

Further, specifically, the identity verification content is a pre-stored facial image of the user, and the corresponding identity recognition information is a real-time facial image of the user. If the real-time facial image of the user and the pre-stored facial image of the user are recognized through facial recognition, they are judged to be a match at this time.

Further, specifically, the user's social security card information is obtained through preset rules, including:

Within a preset time range, continuous frames of social security card images of the user are obtained to obtain the social security card information of the user.

Further, specifically, obtaining a typical image of a social security card based on the social security card information includes:

For consecutive frames of social security card images, similarity calculation is performed between the current frame social security card image and the previous frame social security card image, and the current frame social security card image with a similarity lower than a first threshold is eliminated, and finally a sequence of remaining social security card images is obtained;

In addition, it is agreed that when the previous social security card image of the current social security card image is removed, the previous social security card image of the removed social security card image is used as the previous social security card image of the current social security card image for similarity calculation;

Assume that the remaining social security card image sequence includes m social security card images, the image matrix of the j-th social security card image is Bj(j), and its serial number is j. Define the pixel value of the pixel point in the wj-th row and the dj-th column in the image matrix Bj(j) as Bj(j, wj, dj);

Calculate the clear trend of any pixel point Bj(j, wj, dj) based on its neighborhood pixels, clear(j, wj, dj), the relevant calculation formula is as follows:

Where max(j, wj, dj) is the maximum value of the pixels in the neighborhood of Bj(j, wj, dj), avg(j, wj, dj) and min(j, wj, dj) are the average value and minimum value of the pixels in the neighborhood of Bj(j, wj, dj) respectively;

Based on the clarity trend, find the clear representation area of all images in the remaining social security card image sequence;

By calculating the average pixel value of the pixels at the same position of m social security card images, and constructing the initial image with the average pixel value of each different position;

The pixel positions corresponding to the clear representation areas of all images in the remaining social security card image sequence are replaced with the same pixel positions in the initial image to obtain a typical social security card image.

Further, specifically, based on the clarity trend, the clear representation areas of all images in the remaining social security card image sequence are found, including:

When the sequence number of the image is 1, the image matrix B1(1) is traversed to select the two pixels with the largest and second largest clarity trend values, and the two pixels are connected to obtain the line segment zx(1). Then, the pixel with the largest clarity trend other than the line segment zx(1) is selected in B1(1), and the two end points of the line segment zx(1) are respectively connected to the pixel with the largest clarity trend other than the line segment lin(1) selected in B1(1) to obtain the clear representation area of B1(1);

When the sequence number of the image is not 1, assume that its image matrix is Bj(j), calculate the pixel average value avg(j-1) of the pixel points in the clear representation area of Bj-1(j-1), traverse the image matrix Bj(j), select the pixel points with a clarity trend greater than avg(j-1), and then select two random pixel points from them, connect the two random pixel points to obtain a line segment zx(j), then select the pixel point with the largest clarity trend other than the line segment zx(j) in Bj(j), and connect the two endpoints of the line segment zx(j) to the pixel point with the largest clarity trend other than the line segment zx(j) selected in Bj(j) to obtain the clear representation area of Bj(j).

Furthermore, specifically, the processing voucher includes information on the processing number, appointment time, and processing time.

Further, specifically, the similarity between the current frame social security card image and the previous frame social security card image is calculated by calculating the Bhattacharyya distance in a histogram-based manner.

Furthermore, the typical image of the social security card is identified to obtain the user's social security identity information, including:

The built-in OCR recognition algorithm and portrait recognition algorithm are used to recognize typical images of social security cards to obtain OCR recognition content and portrait recognition content, namely the user's social security identity information.

The present invention also proposes a social security identity recognition device based on public service convenience registration, comprising:

The reservation request acquisition module is used to obtain the user's reservation request and its associated identity authentication content;

An identity information acquisition module, used to acquire the identity information of the user corresponding to the identity authentication content;

A first judgment module is used to obtain the user's social security card information according to a preset rule when the identity recognition information matches the identity authentication content;

An image acquisition module to be identified, used to obtain a typical image of a social security card based on the social security card information;

An image recognition module is used to recognize the typical image of the social security card to obtain the user's social security identity information;

An information entry and voucher generation module, used to enter the user's social security identity information and generate a processing voucher;

The information feedback module is used to feed back the processing certificate to the user.

The beneficial effects of the present invention are:

The present invention proposes a social security identity recognition method based on public service convenience registration, establishes the entire automated process from appointment to completion, and can bring users a comfortable and convenient processing experience. In addition, when performing social security identity information recognition, a method for constructing typical images of social security card certificates is designed, which can ensure high image quality at the source, and then use mature OCR and portrait recognition algorithms to recognize the user's social security identity information, improve recognition accuracy, and then improve the user's processing experience, thereby ensuring the promotion and popularization of this product.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and other features of the present disclosure will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present disclosure represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings:

FIG1 is a flow chart of a social security identity recognition method based on public service convenience registration according to the present invention.

DETAILED DESCRIPTION

The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other without conflict. The same reference numerals used throughout the drawings indicate the same or similar parts.

Embodiment 1, referring to FIG. 1 , the present invention proposes a social security identity recognition method based on public service convenience registration, comprising the following:

Step 110: Obtain the user's reservation request and its associated identity verification content;

Step 120: Obtain the user identity information corresponding to the identity verification content;

Step 130: When the identity recognition information matches the identity verification content, the user's social security card information is obtained according to a preset rule;

Step 140: obtaining a typical image of a social security card based on the social security card information;

Step 150: Recognize the typical image of the social security card to obtain the user's social security identity information;

Step 160: Enter the user's social security identity information and generate a processing certificate;

Step 170: Feedback the processing certificate to the user.

In this embodiment 1, the entire automated process from appointment to completion is established, which can bring users a comfortable and convenient processing experience. In addition, when performing social security identity information recognition, a method for constructing typical images of social security card certificates is designed, which can ensure high image quality at the source, and then use mature OCR and portrait recognition algorithms to recognize the user's social security identity information, improve recognition accuracy, and then improve the user's processing experience, thereby ensuring the promotion and popularization of this product.

As a preferred embodiment of the present invention, specifically, the identity authentication content is a pre-stored facial image of the user, and the corresponding identity recognition information is a real-time facial image of the user. If the real-time facial image of the user and the pre-stored facial image of the user pass facial recognition, they are judged to be a match at this time.

In this preferred embodiment, considering that face recognition is currently a mature and reliable verification method, face images are selected to determine the user's identity information. Of course, identity determination through voiceprints, fingerprints, etc. is also possible.

As a preferred embodiment of the present invention, specifically, obtaining the user's social security card information through preset rules includes:

Within a preset time range, continuous frames of social security card images of the user are obtained to obtain the social security card information of the user.

Specifically, obtaining a typical image of a social security card based on the social security card information includes:

For consecutive frames of social security card images, similarity calculation is performed between the current frame social security card image and the previous frame social security card image, and the current frame social security card image with a similarity lower than a first threshold is eliminated, and finally a sequence of remaining social security card images is obtained;

In addition, it is agreed that when the social security card image of the previous frame is removed, the social security card image of the previous frame of the removed social security card image is used as the social security card image of the previous frame of the current social security card image for similarity calculation, and so on;

Assume that the remaining social security card image sequence includes m social security card images, the image matrix of the j-th social security card image is Bj(j), and its serial number is j. Define the pixel value of the pixel point in the wj-th row and the dj-th column in the image matrix Bj(j) as Bj(j, wj, dj);

Calculate the clear trend of any pixel point Bj(j, wj, dj) based on its neighborhood pixels, clear(j, wj, dj), the relevant calculation formula is as follows:

Where max(j, wj, dj) is the maximum value of the pixel in the neighborhood of Bj(j, wj, dj), avg(j, wj, dj) and min(j, wj, dj) are the average and minimum values of the pixel in the neighborhood of Bj(j, wj, dj), respectively. The neighborhood refers to the 8-neighborhood of the pixel.

Based on the clarity trend, find the clear representation area of all images in the remaining social security card image sequence;

By calculating the average pixel value of the pixels at the same position of m social security card images, and constructing the initial image with the average pixel value of each different position;

The pixel positions corresponding to the clear representation areas of all images in the remaining social security card image sequence are replaced with the same pixel positions in the initial image to obtain a typical social security card image.

In this preferred embodiment, the clear representation area in each social security card certificate image is found by calculating the clarity trend, which is equivalent to replacing the corresponding position of the initial image composed of the average pixel value with the clear representation area in each image. The recognition success rate of the remaining social security card certificate image sequence obtained in this way will be very high. In addition, considering that the user may have hand shaking and other erroneous operations when taking the social security card certificate image, which may cause excessive differences in some frame images, these images are eliminated through similarity recognition for subsequent processing.

As a preferred embodiment of the present invention, specifically, based on the clarity trend, the clear representation area of all images in the remaining social security card image sequence is found, including:

When the sequence number of the image is 1, the image matrix B1(1) is traversed to select the two pixels with the largest and second largest clarity trend values, and the two pixels are connected to obtain the line segment zx(1). Then, the pixel with the largest clarity trend other than the line segment zx(1) is selected in B1(1), and the two end points of the line segment zx(1) are respectively connected to the pixel with the largest clarity trend other than the line segment lin(1) selected in B1(1) to obtain the clear representation area of B1(1);

When the sequence number of the image is not 1, assume that its image matrix is Bj(j), calculate the pixel average value avg(j-1) of the pixel points in the clear representation area of Bj-1(j-1), traverse the image matrix Bj(j), select the pixel points with a clarity trend greater than avg(j-1), and then select two random pixel points from them, connect the two random pixel points to obtain a line segment zx(j), then select the pixel point with the largest clarity trend other than the line segment zx(j) in Bj(j), and connect the two endpoints of the line segment zx(j) to the pixel point with the largest clarity trend other than the line segment zx(j) selected in Bj(j) to obtain the clear representation area of Bj(j).

As a preferred implementation manner of the present invention, specifically, the handling voucher includes information on the handling number, appointment time and processing time.

As a preferred embodiment of the present invention, specifically, the similarity between the social security card photo image of the current frame and the social security card photo image of the previous frame is calculated by calculating the Bhattacharyya distance in a histogram-based manner.

As a preferred embodiment of the present invention, the social security card typical image is identified to obtain the user's social security identity information, including:

The built-in OCR recognition algorithm and portrait recognition algorithm are used to recognize typical images of social security cards to obtain OCR recognition content and portrait recognition content, namely the user's social security identity information.

The OCR recognition algorithm and portrait recognition algorithm are both popular and stable algorithms on the market.

The present invention also proposes a social security identity recognition device based on public service convenience registration, comprising:

The reservation request acquisition module is used to obtain the user's reservation request and its associated identity authentication content;

An identity information acquisition module, used to acquire the identity information of the user corresponding to the identity authentication content;

A first judgment module is used to obtain the user's social security card information according to a preset rule when the identity recognition information matches the identity authentication content;

An image acquisition module to be identified, used to obtain a typical image of a social security card based on the social security card information;

An image recognition module is used to recognize the typical image of the social security card to obtain the user's social security identity information;

An information entry and voucher generation module, used to enter the user's social security identity information and generate a processing voucher;

The information feedback module is used to feed back the processing certificate to the user.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

Although the description of the present invention has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims in view of the prior art by reference to the appended claims, thereby effectively covering the intended scope of the present invention. In addition, the above description of the present invention is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that have not yet been foreseen may still represent equivalent changes to the present invention.

The above is only a preferred embodiment of the present invention. The present invention is not limited to the above implementation. As long as the technical effect of the present invention is achieved by the same means, it should belong to the protection scope of the present invention. Within the protection scope of the present invention, its technical scheme and/or implementation method can have various modifications and changes.

Claims (6)

1. A social security identification method based on public service convenience registration, characterized by comprising the following steps:

acquiring a reservation request of a user and associated identity verification content thereof;

acquiring the identity information of the user corresponding to the identity verification content;

When the identity identification information is matched with the identity verification content, obtaining social security card license information of the user through a preset rule;

Obtaining a typical image of the social security card license based on the social security card license information;

Identifying the representative image of the social security card license to obtain social security information of the user;

Inputting the social security information of the user and generating a handling certificate;

feeding back the handling certificate to the user;

specifically, the social security card license information of the user is obtained through a preset rule, which comprises,

Obtaining continuous frame social security card license images of a user within a preset time range to obtain social security card license information of the user;

Specifically, a typical image of the social security card license is obtained based on the social security card license information, which comprises,

For continuous frame social security license images, similarity calculation is carried out on the current frame social security license image and the previous frame social security license image, the current frame social security license image with the similarity lower than a first threshold value is removed, and finally a residual social security license image sequence is obtained;

When the condition that the previous-frame social security card license image of the current-frame social security card license image is removed exists, the previous-frame social security card license image of the removed social security card license image is used as the previous-frame social security card license image of the current-frame social security card license image to perform similarity calculation;

Assuming that the remaining social security license image sequences comprise m Zhang Shebao card license images in total, wherein an image matrix of a j Zhang Shebao th card license image is Bj (j), a serial number of the image matrix is marked as j, and pixel values of pixel points of a wj row and a dj column in the image matrix Bj (j) are defined as Bj, wj and dj;

Any pixel point Bj (j, wj, dj) is calculated based on the clear trend clear (j, wj, dj) of the neighborhood pixel point, the correlation calculation formula is as follows,

Wherein max (j, wj, dj) is the maximum value of the adjacent pixel points of Bj (j, wj, dj), avg (j, wj, dj) and min (j, wj, dj) are the average value and the minimum value of the adjacent pixel points of Bj (j, wj, dj) respectively;

searching out clear representation areas of all images in the remaining social security card license image sequence based on the clear trend;

Calculating the average pixel value of the pixel points of the m Zhang Shebao card license image at the same position, and constructing a built image together by using the average pixel value of each different position;

replacing the same pixel point positions in the initial image with the pixel point positions corresponding to the clear representation areas of all images in the rest social security license image sequence to obtain a representative social security license image;

Specifically, the clear representation area of all images in the remaining social security license image sequence is found based on the clear trend, including,

When the sequence number of the image is 1, traversing an image matrix B1 (1), selecting two pixels with the largest clear trend degree value and the second largest value from the two pixels, connecting the two pixels to obtain a line segment zx (1), selecting the pixel with the largest clear trend degree except the line segment zx (1) from the B1 (1), and connecting two end points of the line segment zx (1) with the pixel with the largest clear trend degree except the line segment lin (1) selected from the B1 (1) to obtain a clear representation area of the B1 (1);

When the serial number of the image is not 1, assuming that an image matrix of the image is Bj (j), calculating a pixel average value avg (j-1) of pixel points in a clear representation area of Bj-1 (j-1), traversing the image matrix Bj (j), selecting pixel points with clear trend degree larger than avg (j-1), selecting two random pixel points, connecting the two random pixel points to obtain a line segment zx (j), selecting a pixel point with the largest clear trend degree except the line segment zx (j) in the Bj (j), and connecting two end points of the line segment zx (j) with the pixel point with the largest clear trend degree except the line segment zx (j) in the Bj to obtain the clear representation area of the Bj (j).

2. The social security identity recognition method based on public service convenience registration according to claim 1, wherein the identity verification content is a pre-stored face image of a user, the corresponding identity recognition information is a real-time face image of the user, and the identity verification content is judged to be matched at the moment if the real-time face image of the user and the pre-stored face image of the user pass through face recognition.

3. The social security identification method based on public service convenience registration according to claim 1, wherein the transaction certificate includes information of a transaction number, a reservation time, and a processing time.

4. The social security identification method based on public service convenience registration according to claim 1, wherein the similarity calculation is performed between the current frame social security license image and the previous frame social security license image in a histogram-based manner by calculating the pasteurization distance.

5. The social security identification method based on public service convenience registration according to claim 1, wherein the social security identification information of the user is obtained by identifying the representative image of the social security card license,

And the built-in OCR recognition algorithm and the human image recognition algorithm are used for recognizing the typical image of the social security card license to obtain OCR recognition content and human image recognition content, namely social security identity information of the user.

6. A social security identification device based on public service registration is characterized by comprising,

The reservation request acquisition module is used for acquiring a reservation request of a user and associated identity verification content;

The identity information acquisition module is used for acquiring the identity information of the user corresponding to the identity verification content;

The first judging module is used for acquiring social security card license information of the user through a preset rule when the identity identification information is matched with the identity verification content;

the image acquisition module to be identified is used for acquiring a typical image of the social security card license based on the social security card license information;

the image identification module is used for identifying the typical image of the social security card license to obtain the social security information of the user;

the information input and credential generation module is used for inputting the social security information of the user and generating a transacting credential;

The information feedback module is used for feeding the handling certificate back to the user;

specifically, the social security card license information of the user is obtained through a preset rule, which comprises,

Obtaining continuous frame social security card license images of a user within a preset time range to obtain social security card license information of the user;

Specifically, a typical image of the social security card license is obtained based on the social security card license information, which comprises,

For continuous frame social security license images, similarity calculation is carried out on the current frame social security license image and the previous frame social security license image, the current frame social security license image with the similarity lower than a first threshold value is removed, and finally a residual social security license image sequence is obtained;

When the condition that the previous-frame social security card license image of the current-frame social security card license image is removed exists, the previous-frame social security card license image of the removed social security card license image is used as the previous-frame social security card license image of the current-frame social security card license image to perform similarity calculation;

Assuming that the remaining social security license image sequences comprise m Zhang Shebao card license images in total, wherein an image matrix of a j Zhang Shebao th card license image is Bj (j), a serial number of the image matrix is marked as j, and pixel values of pixel points of a wj row and a dj column in the image matrix Bj (j) are defined as Bj, wj and dj;

Any pixel point Bj (j, wj, dj) is calculated based on the clear trend clear (j, wj, dj) of the neighborhood pixel point, the correlation calculation formula is as follows,

Wherein max (j, wj, dj) is the maximum value of the adjacent pixel points of Bj (j, wj, dj), avg (j, wj, dj) and min (j, wj, dj) are the average value and the minimum value of the adjacent pixel points of Bj (j, wj, dj) respectively;

searching out clear representation areas of all images in the remaining social security card license image sequence based on the clear trend;

Calculating the average pixel value of the pixel points of the m Zhang Shebao card license image at the same position, and constructing a built image together by using the average pixel value of each different position;

replacing the same pixel point positions in the initial image with the pixel point positions corresponding to the clear representation areas of all images in the rest social security license image sequence to obtain a representative social security license image;

Specifically, the clear representation area of all images in the remaining social security license image sequence is found based on the clear trend, including,

When the sequence number of the image is 1, traversing an image matrix B1 (1), selecting two pixels with the largest clear trend degree value and the second largest value from the two pixels, connecting the two pixels to obtain a line segment zx (1), selecting the pixel with the largest clear trend degree except the line segment zx (1) from the B1 (1), and connecting two end points of the line segment zx (1) with the pixel with the largest clear trend degree except the line segment lin (1) selected from the B1 (1) to obtain a clear representation area of the B1 (1);

When the serial number of the image is not 1, assuming that an image matrix of the image is Bj (j), calculating a pixel average value avg (j-1) of pixel points in a clear representation area of Bj-1 (j-1), traversing the image matrix Bj (j), selecting pixel points with clear trend degree larger than avg (j-1), selecting two random pixel points, connecting the two random pixel points to obtain a line segment zx (j), selecting a pixel point with the largest clear trend degree except the line segment zx (j) in the Bj (j), and connecting two end points of the line segment zx (j) with the pixel point with the largest clear trend degree except the line segment zx (j) in the Bj to obtain the clear representation area of the Bj (j).