CN115731377A - Bidder information verification system, method and device based on picture identification - Google Patents
Bidder information verification system, method and device based on picture identification Download PDFInfo
- Publication number
- CN115731377A CN115731377A CN202211387357.0A CN202211387357A CN115731377A CN 115731377 A CN115731377 A CN 115731377A CN 202211387357 A CN202211387357 A CN 202211387357A CN 115731377 A CN115731377 A CN 115731377A
- Authority
- CN
- China
- Prior art keywords
- picture
- bidder
- information
- identity
- identity card
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012795 verification Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000011835 investigation Methods 0.000 claims abstract description 12
- 238000012937 correction Methods 0.000 claims description 35
- 238000012545 processing Methods 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000012797 qualification Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a system, a method and a device for verifying bidder information based on picture identification, wherein the system, the method and the device comprise the following steps: acquiring an identity information picture of a bidder; preprocessing and identifying to obtain a uniform social credit code of a bidder, a legal representative name and a citizen identity card number thereof, a project principal name and a citizen identity card number thereof; checking by using a third-party credit investigation mechanism, and judging whether integrity bad records and bribery crime records exist or not; when the verification is failed, extracting the identification result and storing the identification result into a manual verification data table; when the verification is passed, storing the legal person certificate and the business license of the bidder into a verification passing data table; the method and the system feed back whether conditions such as bribery crime record, integrity failure record and the like exist in the bidders or not by identifying corporate certificates or business license information provided by the bidders; the technical problems that the bidding system cannot perform verification in real time in the verification process, and a large amount of manpower and time are consumed in verification are solved.
Description
Technical Field
The invention belongs to the technical field of information processing, and particularly relates to a bidder information verification system, method and device based on picture identification.
Background
In the process of identity verification of a bidding enterprise, it is required to determine whether the bidding enterprise has information such as a bribery crime record, an integrity failure record and the like, and the method specifically includes the following steps: 1. inquiring whether the bidders, legal representatives and project responsible persons (such as the person who needs to provide project responsible for the bidding document) exist bribery records within the effective date specified by the bidding document or not in a Chinese referee document network. 2. And inquiring the bad records of the integrity of the bidders, and dividing the records into an enterprise and a non-enterprise according to the properties of the bidders. Aiming at the public institution, inquiring basic information of bidders and whether administrative punishment conditions exist in effective dates specified by bidding documents from 'public institution online'; the enterprises (non-business units) need to inquire whether bidders are listed in a list of seriously illegal and distressed enterprises (blacklist) and whether the bidders are listed in the list of abnormal operation names or not within the effective date specified by the bidding document from the national enterprise credit information public system. 3. And inquiring whether the bidder has a blacklist record in an effective date specified by the bid inviting document or not through 'credit China'.
In the bid evaluation process, whether the bid evaluation is a business unit or an enterprise (non-business unit) is judged, whether a bidder has integrity bad records is inquired in the 'business unit online' and the 'national enterprise credit information public system', whether the bidder name or a uniform social credit code has a bribery criminal record is inquired, whether the legal representative has a bribery criminal record is inquired by associating the bidder name or the uniform social credit code with the name of the legal representative and the national identity number, whether the project responsible has a bribery criminal record is inquired by associating the bidder name or the uniform social credit code with the name of the project responsible and the national identity number, the verification process cannot be carried out in real time, and a large amount of manpower and time are consumed in verification.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the patent refers to the field of 'electric digital data processing'.
The technical scheme of the invention is as follows:
a method for bidder information verification based on picture recognition, the method comprising:
acquiring an identity information picture of a bidder; the identity information pictures comprise legal person certificate pictures, business license pictures, legal representative identity card pictures and project responsible person identity card pictures;
preprocessing the identity information picture of the bidder to obtain an identity information correction picture of the bidder; the preprocessing comprises inclination correction, graying, USM sharpening and binaryzation;
identifying identity information correction pictures of bidders to obtain uniform social credit codes, legal representative names and citizen identity card numbers of the bidders, names of project responsible persons and citizen identity card numbers of the bidders;
acquiring the effective date specified by the bidding document, and checking the bidder by using a third party credit investigation institution when the current date is within the effective date, and judging whether the bidder has integrity bad records and bribery criminal records; the third party credit investigation institution provides a Chinese referee document network, an on-line public institution of public institutions or a credit information public institution of national enterprises;
when the verification fails, extracting the uniform social credit code, the legal representative name and the citizen identity number of the bidder, the project principal name and the citizen identity number of the bidder, and storing the project principal name and the citizen identity number into a manual verification data table for manual verification;
when the verification is passed, storing the legal person certificate and the business license of the bidder into a verification passing data table.
Before the step of obtaining the identity information picture of the bidder, the method further comprises the following steps:
and acquiring corporate certificate pictures or business license pictures of the utilities, the enterprise and the enterprises from the bidding document and storing the corporate certificate pictures or the business license pictures into a bidder qualification certificate picture library, acquiring legal representative identity card pictures from the bidding document and storing the legal representative identity card pictures into a legal representative identity card picture library, and acquiring project principal identity card pictures from the bidding document and storing the project principal identity card pictures into a project principal identity card picture library.
The step of preprocessing the identity information picture of the bidder to obtain the identity information correction picture of the bidder comprises the following steps:
when the identity information picture of the bidder has inclination, performing inclination correction on the identity information picture of the bidder to obtain a first processed picture;
when the identity information picture of the bidder does not have inclination or the first processed picture is obtained, mapping the RGB value of each pixel in the identity information picture or the first processed picture to a gray value of 0-255 to obtain a gray processed picture;
recording segmentation thresholds of the foreground and the background of the gray processing picture as T, calculating a variance value, traversing the segmentation thresholds T by 0-255, calculating the variance value every time, and extracting a T value which enables the variance value to be maximum to serve as a target threshold;
sharpening the gray-scale processing picture by using a target threshold value and adopting a USM sharpening algorithm to obtain a sharpened processing picture;
and carrying out binarization processing on the sharpened picture to obtain an identity information correction picture of the bidder.
And marking the segmentation threshold of the foreground and the background of the gray processing picture as T, and in the step of calculating the variance value, the calculation formula is as follows:
wherein g is a variance value, M × N is a picture size, N 0 The number of pixels, N, with the gray value of the pixel value in the picture smaller than the threshold value T 1 The number of pixels in the picture with the pixel gray scale larger than the threshold value T,
the average gray level is u 0 ；
The number of background pixels is the proportion of the whole picture, and the average gray level is u 1 。
The step of carrying out binarization processing on the sharpening processed picture to obtain the identity information correction picture of the bidder comprises the following steps of:
transversely scanning and sharpening the picture, and accumulating the gray values of all points with light colors at two sides and dark colors in the middle of the sharpened picture and recording the gray values as sum 1 The cumulative point is recorded as p 1 ；
Longitudinally scanning the sharpened picture, and accumulating the gray values of all the points with light color at the upper and lower sides and dark color at the middle of the sharpened picture to be recorded as sum 2 The number of accumulated points is recorded as p 2 ；
Calculating a binary threshold value Y; wherein the calculation formula is as follows: y = (sum) 1 +sum 2 )/(p 1 +p 2 )；
And carrying out binarization on the sharpening processed picture by adopting the threshold value Y to obtain the identity information correction picture of the bidder with the watermark removed.
Identifying the identity information correction picture of the bidder to obtain a unified social credit code, a legal representative name and a citizen identity card number thereof, and a project principal name and a citizen identity card number thereof of the bidder, wherein the steps comprise:
judging the region of the unified social credit code by adopting a character recognition network model for the corporate institution, the enterprise institution and the corporate certificate picture or business license picture of the enterprise, and defining the region as a character region, wherein other regions are defined as text regions;
adopting a character recognition network model to recognize the legal representative identity card picture and the project principal identity card picture, judging the region of the citizen identity number and defining the region as a character region, and defining other regions as text regions;
character recognition is adopted for character areas of corporate certificate pictures or business license pictures of a commercial unit, an enterprise commercial unit and an enterprise, and legal representatives and unified social credit code information of bidders are determined;
character recognition is adopted for character areas of the legal representative identity card picture and the project principal identity card picture, and citizen identity numbers of the legal representative and the project principal are determined;
recognizing texts in text regions of corporate certificate pictures or business license pictures of enterprises, enterprise commercial units and enterprises by adopting an OCR image recognition technology, and determining names, categories and legal representative information of bidders;
and recognizing texts in text areas of the legal representative identity card picture and the project principal identity card picture by adopting an OCR image recognition technology, and determining name information of the legal representative and the project principal of the bidder.
When the verification is passed, after the step of storing the legal certificate and the business license of the bidder into the verification passing data table, the method further comprises the following steps:
and automatically inputting the information of the passed business units, enterprise business units and corporate certificate or business license information of the enterprises in the verification passing data table into the bid evaluation system, and storing the information of the picture of the corporate certificate or business license of the manually failed business units, enterprise business units and enterprises in the abnormal database.
A bidder information verification system based on picture recognition comprises:
the acquiring module is used for acquiring the identity information picture of the bidder; the identity information pictures comprise legal person certificate pictures, business license pictures, legal representative identity card pictures and project responsible person identity card pictures;
the preprocessing module is used for preprocessing the identity information picture of the bidder to obtain an identity information correction picture of the bidder; wherein the preprocessing comprises inclination correction, graying, USM sharpening and binaryzation;
the identification module is used for identifying the identity information correction picture of the bidder to obtain a unified social credit code, a legal representative name and a citizen identity card number of the bidder, and a project responsible person name and a citizen identity card number of the bidder;
the verification module is used for acquiring the effective date specified by the bidding document, verifying the bidder by using a third party credit institution when the current date is within the effective date, and judging whether the bidder has integrity bad records and bribery criminal records; wherein, the third party credit investigation institution provides the China judge document network, the online public system of the public credit information of the enterprise or the state;
the first storage module is used for extracting the unified social credit code, the legal representative name and the citizen identity card number of the bidder, the project principal name and the citizen identity card number of the project principal when the verification fails, and storing the uniform social credit code, the legal representative name and the citizen identity card number of the project principal in the manual verification data table for manual verification;
and the second storage module stores the legal person certificate and the business license of the bidder into the verification passing data table when the verification passes.
A computer arrangement comprising a memory having a computer program stored therein and a processor implementing the steps of the method when the processor executes the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method.
The invention has the beneficial effects that:
the invention identifies the business authority certificate or business license information of the bidder through the system, automatically verifies the bidder by utilizing the data of a Chinese judge document network, a national enterprise credit information public system, an online business authority, credit China and the like provided by a third credit investigation institution, feeds back whether the bidder and legal representatives and project responsible persons have a bribery crime record within the effective date specified by a bidding document, feeds back the bidding evaluation expert whether the bidder has an honest record and the like, saves the time of the bidding evaluation expert, prevents manual operation errors, ensures the fairness and justice in the process of verifying the information of the bidder, and assists the bidding evaluation expert to carry out efficient bidding evaluation.
The technical problems that the bidding system cannot perform verification in real time in the verification process, and a large amount of manpower and time are consumed in verification are solved.
Drawings
Fig. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of an internal structure of a computer device according to an embodiment of the invention.
Detailed Description
As shown in fig. 1, the present invention provides a method for verifying bidder information based on picture recognition, which first determines whether a bidder is a utility or an enterprise (non-utility), and inquires whether there is an integrity failure record within an effective date specified by a bidding document in a national enterprise credit information public system on-line in the utility. Query bribery records are correlated in three modes: name of bidder or uniform social credit code; the name or uniform social credit code of the bidder and the name and national identification number of the legal representative, the name or uniform social credit code of the bidder and the name and national identification number of the project responsible person respectively inquire whether a bribery criminal record exists within an effective date specified by the bidding document.
The method provided by the invention specifically comprises the following steps:
before the step S1, the method further includes:
and S01, acquiring legal certificate pictures or business license pictures of the enterprise/enterprise from the bidding documents and storing the pictures in a bidder qualification certificate picture library, acquiring legal representative identity card pictures from the bidding documents and storing the pictures in the legal representative identity card picture library, and acquiring project responsible person identity card pictures from the bidding documents and storing the pictures in the project responsible person identity card picture library.
S1, acquiring an identity information picture of a bidder; the identity information picture comprises a legal person certificate picture, a business license picture, a legal representative identity card picture and a project responsible person identity card picture;
s2, preprocessing the identity information picture of the bidder to obtain an identity information correction picture of the bidder; wherein the preprocessing comprises inclination correction, graying, USM sharpening and binaryzation; namely, the acquired business entity legal certificate picture or business license picture, legal representative identity card picture and project responsible person identity card picture are preprocessed, and the preprocessing can also comprise image scaling and filtering denoising.
The step S2 specifically includes:
s21, when the identity information picture of the bidder has inclination, performing inclination correction on the identity information picture of the bidder to obtain a first processed picture;
s22, when the identity information picture of the bidder does not have inclination, or after the first processed picture is obtained, mapping the RGB value of each pixel in the identity information picture or the first processed picture to a gray value of 0-255 to obtain a gray processed picture; the gray processing is to map the RGB value of each pixel in the picture to a gray value of 0-255, and the obtained picture is like a black-and-white picture, so that the amount of calculation in the subsequent steps can be reduced, and the picture is easier to recognize.
S23, recording the segmentation threshold values of the foreground and the background of the gray processing picture as T, calculating a variance value, traversing the segmentation threshold values T by 0-255, calculating the variance value every time, and extracting the T value which enables the variance value to be maximum to serve as a target threshold value; the method can identify the characters in the picture with the watermark, and because the watermark is semi-transparent and covers the character data, the edges of the characters under the watermark become fuzzy and difficult to identify, the picture is sharpened, the characters in the picture can be highlighted, and the separation of the characters in the picture and the watermark is favorably realized.
USM sharpening not only enhances the edges of one side of a text, but also significantly weakens the other side of the text edge, so that the text is highlighted, and the image near the text is weakened, thereby reducing the area of the translucent watermark. And white edges may also appear at the edges of the text. A threshold value in the USM sharpening algorithm needs to be set, and if the threshold value is too large, sharpening cannot generate an effect; if the set threshold is too small, the edges of both the text and the watermark will be enhanced. Therefore, setting the threshold includes:
recording segmentation threshold values of the foreground and the background of the gray processing picture as T, calculating a variance value, traversing the segmentation threshold value T by 0-255, calculating the variance value each time, and extracting a T value which enables the variance value to be maximum to serve as a target threshold value; the calculation formula for calculating the variance value is as follows:
wherein g is a variance value, M × N is a picture size, N 0 The number of pixels, N, with the gray value of the pixel value in the picture smaller than the threshold value T 1 The number of pixels in the picture with the pixel gray scale larger than the threshold value T,
the average gray level is u as the ratio of the number of pixels belonging to the foreground to the whole picture 0 ，
The average gray level is u in proportion of the number of background pixels to the whole picture 1 。
S24, sharpening the gray-scale processing picture by using a target threshold value and adopting a USM sharpening algorithm to obtain a sharpened processing picture;
s25, carrying out binarization processing on the sharpened picture to obtain an identity information correction picture of the bidder; the main character picture can be obtained by binarization processing.
Step S25 specifically includes:
s251, transversely scanning the sharpened picture, and accumulating the gray values of all points with light colors at two sides and dark colors in the middle of the sharpened picture to be recorded as sum 1 The cumulative point is recorded as p 1 ；
S252, longitudinally scanning the sharpening processed picture, and accumulating the gray values of all points with light colors at the upper and lower edges and dark colors at the middle of the sharpening processed picture to be sum 2 The cumulative point is recorded as p 2 ；
S253, calculating a binary threshold value Y; wherein the calculation formula is as follows: y = (sum) 1 +sum 2 )/(p 1 +p 2 ) (ii) a That is, the gray values of the black dots subjected to the white edge derivative are accumulated, and the sum is divided by the number of the black dots to obtain the average gray value of the black dots.
And S254, carrying out binarization on the sharpening processed picture by adopting the threshold value Y to obtain the identity information correction picture of the bidder with the watermark removed.
S3, identifying the identity information correction picture of the bidder to obtain a unified social credit code, a legal representative name and a citizen identity card number thereof, and a project principal name and a citizen identity card number thereof of the bidder;
step S3 specifically includes:
s31, judging the region of the unified social credit code for the corporate certificate picture or business license picture of the business unit/enterprise by adopting a character recognition network model, and defining the region as a character region, wherein other regions are defined as text regions;
s32, identifying the legal representative identity card picture and the project principal identity card picture by adopting a character identification network model, judging the region where the citizen identity number is located, defining the region as a character region, and defining other regions as text regions;
s33, character recognition is adopted for the character area of the corporate certificate picture or the business license picture of the enterprise/institution, and the legal representative and the unified social credit code information of the bidder are determined;
s34, character recognition is carried out on character areas of the legal representative identity card pictures and the project responsible person identity card pictures, and citizen identity numbers of the legal representative and the project responsible person are determined;
s35, recognizing texts in text regions of corporate certificate pictures or business license pictures of the enterprises by adopting an OCR image recognition technology, and determining information such as names, categories and legal representatives of bidders;
and S36, recognizing texts in text areas of the legal representative identity card picture and the project principal identity card picture by adopting an OCR image recognition technology, and determining name information of the legal representative and the project principal of the bidder.
S4, obtaining an effective date specified by a bidding document, and when the current date is within the effective date, verifying the bidder by using a third party credit investigation mechanism, and judging whether the bidder has integrity bad records and bribery criminal records; the third-party credit investigation institution provides a Chinese referee document network, an on-line public system of public credit information of public institutions and national enterprises;
s5, when the verification fails, extracting the unified social credit code, the legal representative name and the citizen identity number thereof, the project principal name and the citizen identity number thereof of the bidder, and storing the uniform social credit code, the legal representative name and the citizen identity number thereof into a manual verification data table for manual verification;
and S6, when the verification is passed, storing the legal person certificate and the business license of the bidder into a verification passing data table.
And S7, automatically inputting the information of the legal person certificate or business license of the business unit/enterprise which passes the verification in the verification passing data table into an evaluation system, and storing the information of the legal person certificate picture or business license of the business unit/enterprise which does not pass the manual verification into an abnormal database. The information in the bidding document is judged whether bribery criminal records and honest bad records exist within the effective date specified by the bidding document or not through database data of a Chinese referee document network, an on-line institution unit, a national enterprise credit information public system, a credit China and the like of a third-party credit institution, and if so, the information is stored into a disused bid library.
The invention automatically checks the bidders by identifying the information of the corporate legal certificates or business licenses of the bidders and utilizing the data of a Chinese judge document network, a national enterprise credit information public system, online business, credit China and the like provided by a third credit investigation institution, feeds back whether the bidders and legal representatives and project responsible persons have bribery crime records within the effective date specified by a bidding document, feeds back whether the bidders have integrity bad records and the like to the bidding evaluation experts, can perform label abandoning treatment after the manual review of the bidding evaluation experts, saves the time of the bidding evaluation experts, prevents manual operation errors, ensures fairness and fairness in the process of checking the information of the bidders, and assists the bidding evaluation experts to perform efficient labeling.
As shown in fig. 2, the present invention also provides a system for verifying bidder information based on image recognition, comprising:
the acquiring module 1 is used for acquiring an identity information picture of a bidder; the identity information picture comprises a legal person certificate picture, a business license picture, a legal representative identity card picture and a project responsible person identity card picture;
the preprocessing module 2 is used for preprocessing the identity information picture of the bidder to obtain an identity information correction picture of the bidder; wherein the preprocessing comprises inclination correction, graying, USM sharpening and binaryzation;
the identification module 3 is used for identifying the identity information correction picture of the bidder to obtain a unified social credit code, a legal representative name and a citizen identity card number thereof, a project principal name and a citizen identity card number thereof of the bidder;
the verification module 4 is used for acquiring an effective date specified by the bidding document, verifying the bidder by using a third-party credit institution when the current date is within the effective date, and judging whether integrity failure records and bribery criminal records exist in the bidder; the third-party credit investigation institution provides a Chinese referee document network, an on-line public system of public credit information of public institutions and national enterprises;
the first storage module 5 is used for extracting the unified social credit code, the legal representative name and the citizen identity number thereof, the project responsible person name and the citizen identity number thereof of the bidder when the verification fails, and storing the unified social credit code, the legal representative name and the citizen identity number thereof into the manual verification data table for manual verification;
and the second storage module 6 stores the legal person certificate and the business license of the bidder into a verification passing data table when the verification passes.
In one embodiment, further comprising:
and the storage module is used for acquiring a legal person certificate picture or a business license picture of an enterprise or a business from the bidding document and storing the legal person certificate picture or the business license picture into the bidder certificate picture library, acquiring a legal representative identity card picture from the bidding document and storing the legal representative identity card picture into the legal representative identity card picture library, and acquiring a project principal identity card picture from the bidding document and storing the project principal identity card picture into the project principal identity card picture library.
In one embodiment, the pre-processing module 2 includes:
the correcting unit is used for carrying out inclination correction on the identity information picture of the bidder when the identity information picture of the bidder has inclination to obtain a first processed picture;
the gray processing unit is used for mapping the RGB value of each pixel in the identity information picture or the first processed picture to a gray value of 0-255 to obtain a gray processed picture when the identity information picture of the bidder does not have inclination or the first processed picture is obtained;
the calculation unit is used for recording the segmentation threshold values of the foreground and the background of the gray processing picture as T, calculating a variance value, enabling the segmentation threshold value T to traverse 0-255, calculating the variance value every time, and extracting a T value enabling the variance value to be maximum to serve as a target threshold value;
the sharpening unit is used for sharpening the gray-scale processing picture by using a target threshold value and adopting a USM sharpening algorithm to obtain a sharpened processing picture;
and the binarization unit is used for carrying out binarization processing on the sharpened processed picture to obtain the identity information correction picture of the bidder.
In one embodiment, in the calculation unit, the calculation formula is:
wherein g is a variance value, M × N is a picture size, N 0 The number of pixels, N, with the gray value of the pixel value in the picture smaller than the threshold value T 1 The number of pixels in the picture with the pixel gray scale larger than the threshold value T,
the average gray level is u as the ratio of the number of pixels belonging to the foreground to the whole picture 0 ，
The average gray level is u in proportion of the number of background pixels to the whole picture 1 。
In one embodiment, the binarization unit includes:
a horizontal scanning subunit, configured to scan the sharpened image horizontally, and record the gray value of all the points with light color at both sides and dark color in the middle of the sharpened image as sum 1 The number of accumulated points is recorded as p 1 ；
A longitudinal scanning subunit, configured to longitudinally scan the sharpened picture, and record the gray value of all the points where the upper and lower edges of the sharpened picture are light and the middle of the sharpened picture is dark as sum 2 The cumulative point is recorded as p 2 ；
A calculating subunit for calculating a binarized threshold value Y; wherein the calculation formula is as follows: y = (sum) 1 +sum 2 )/(p 1 +p 2 )；
And the binarization subunit is used for binarizing the sharpening processed picture by adopting the threshold value Y to obtain the identity information correction picture of the bidder with the watermark removed.
In one embodiment, the identification module 3 includes:
the first definition unit is used for judging the region of the unified social credit code for the corporate certificate picture or the business license picture of the enterprise/institution by adopting a character recognition network model and defining the region as a character region, and defining other regions as text regions;
the second definition unit is used for identifying the legal representative identity card picture and the project principal identity card picture by adopting a character identification network model, judging the region where the citizen identity number is located and defining the region as a character region, and defining other regions as text regions;
the first character recognition unit is used for adopting character recognition to the character area of the legal certificate picture or the business license picture of the enterprise/institution and determining the legal representative and the unified social credit code information of the bidder;
the second character recognition unit is used for performing character recognition on character areas of the legal representative identity card picture and the project responsible person identity card picture and determining the citizen identity numbers of the legal representative and the project responsible person of the bidder;
the first text recognition unit is used for recognizing texts in text regions of corporate certificate pictures or business license pictures of the enterprises and enterprises by adopting an OCR image recognition technology, and determining information such as names, categories and legal representatives of bidders;
and the second text recognition unit is used for recognizing the text of the text regions of the legal representative identity card picture and the project principal identity card picture by adopting an OCR image recognition technology and determining the name information of the legal representative and the project principal of the bidder.
In one embodiment, further comprising:
and the input module is used for automatically inputting the information of the legal person certificate or the business license of the business unit/enterprise which passes the verification in the verification passing data table into the evaluation system, and storing the information of the legal person certificate picture or the business license of the business unit/enterprise which does not pass the manual verification into the abnormal database.
The modules, units and sub-units are all used for correspondingly executing each step in the method for verifying the bidder information based on the image recognition, and specific implementation manners thereof are described with reference to the method embodiments and are not described herein again.
As shown in fig. 3, the present invention also provides a computer device, which may be a server, and the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operating system and the computer programs to run in the non-volatile storage medium. The database of the computer device is used for storing all data required by the process of the method for verifying the bidder information based on the picture recognition. The network interface of the computer device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a method for bidder information verification based on picture recognition.
Those skilled in the art will appreciate that the structure shown in fig. 3 is a block diagram of only a portion of the structure associated with the present application, and does not constitute a limitation on the computer apparatus to which the present application is applied.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements any one of the above methods for verifying bidder information based on picture recognition.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware associated with instructions of a computer program, which may be stored on a non-volatile computer-readable storage medium, and when executed, may include processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).
Claims (10)
1. A method for verifying bidder information based on picture identification is characterized by comprising the following steps:
acquiring an identity information picture of a bidder; the identity information picture comprises a legal person certificate picture, a business license picture, a legal representative identity card picture and a project responsible person identity card picture;
preprocessing the identity information picture of the bidder to obtain an identity information correction picture of the bidder; the preprocessing comprises inclination correction, graying, USM sharpening and binaryzation;
identifying identity information correction pictures of bidders to obtain uniform social credit codes, legal representative names and citizen identity card numbers, project principal names and citizen identity card numbers of the bidders;
acquiring the effective date specified by the bidding document, and checking the bidder by using a third party credit investigation institution when the current date is within the effective date, and judging whether the bidder has integrity bad records and bribery criminal records; the third party credit investigation institution provides a Chinese referee document network, an on-line public institution of public institutions or a credit information public institution of national enterprises;
when the verification fails, extracting the uniform social credit code, the legal representative name and the citizen identity number of the bidder, the project principal name and the citizen identity number of the bidder, and storing the project principal name and the citizen identity number into a manual verification data table for manual verification;
when the verification is passed, storing the legal person certificate and the business license of the bidder into a verification passing data table.
2. The method for verifying the bidder information based on the image recognition as claimed in claim 1, wherein the step of obtaining the identity information image of the bidder is preceded by the step of:
and acquiring corporate certificate pictures or business license pictures of the utilities, the enterprise and the enterprises from the bidding document and storing the corporate certificate pictures or the business license pictures into a bidder qualification certificate picture library, acquiring legal representative identity card pictures from the bidding document and storing the legal representative identity card pictures into a legal representative identity card picture library, and acquiring project principal identity card pictures from the bidding document and storing the project principal identity card pictures into a project principal identity card picture library.
3. The method for verifying the bidder information based on the picture identification as claimed in claim 1, wherein the step of preprocessing the picture of the identity information of the bidder to obtain the corrected picture of the identity information of the bidder comprises:
when the identity information picture of the bidder has inclination, performing inclination correction on the identity information picture of the bidder to obtain a first processed picture;
when the identity information picture of the bidder does not have inclination or the first processed picture is obtained, mapping the RGB value of each pixel in the identity information picture or the first processed picture to a gray value of 0-255 to obtain a gray processed picture;
recording segmentation thresholds of the foreground and the background of the gray processing picture as T, calculating a variance value, traversing the segmentation thresholds T by 0-255, calculating the variance value every time, and extracting a T value which enables the variance value to be maximum to serve as a target threshold;
sharpening the gray-scale processing picture by using a target threshold value and adopting a USM sharpening algorithm to obtain a sharpened processing picture;
and carrying out binarization processing on the sharpened picture to obtain an identity information correction picture of the bidder.
4. The method for verifying bidder information based on image recognition according to claim 3, wherein a segmentation threshold of a foreground and a background of the gray-scale processed image is denoted as T, and in the step of calculating a variance value, a calculation formula is as follows:
wherein g is a variance value, M × N is a picture size, N 0 The number of pixels, N, with the gray value of the pixel value in the picture smaller than the threshold value T 1 The number of pixels in the picture with the pixel gray scale larger than the threshold value T,
the average gray level is u 0 ；
The number of background pixels is the proportion of the whole picture, and the average gray level is u 1 。
5. The method for verifying the bidder information based on the picture identification as claimed in claim 3, wherein the step of binarizing the sharpened picture to obtain the identity information correction picture of the bidder comprises:
transversely scanning and sharpening the picture, and accumulating the gray values of all the points with light color at two sides and dark color in the middle of the sharpened picture to be recorded as sum 1 The cumulative point is recorded as p 1 ；
Longitudinally scanning the sharpening processing picture and enabling the sharpening processing picture to be onThe gray values of all the points with the lower two sides being light color and the middle being dark color are accumulated and recorded as sum 2 The number of accumulated points is recorded as p 2 ；
Calculating a binary threshold value Y; wherein the calculation formula is as follows: y = (sum) 1 +sum 2 )/(p 1 +p 2 )；
And carrying out binarization on the sharpening processed picture by adopting the threshold value Y to obtain the identity information correction picture of the bidder with the watermark removed.
6. The method for verifying the information of the bidder based on the picture recognition according to claim 1, wherein the step of recognizing the identification information correction picture of the bidder to obtain the unified social credit code, the legal representative name and the citizen identity number thereof, and the project responsible name and the citizen identity number thereof of the bidder comprises:
judging the region of the unified social credit code by adopting a character recognition network model for the corporate institution, the enterprise institution and the corporate certificate picture or business license picture of the enterprise, and defining the region as a character region, wherein other regions are defined as text regions;
adopting a character recognition network model to recognize the legal representative identity card picture and the project principal identity card picture, judging the region of the citizen identity number and defining the region as a character region, and defining other regions as text regions;
character recognition is adopted for character areas of corporate certificate pictures or business license pictures of a commercial unit, an enterprise commercial unit and an enterprise, and legal representatives and unified social credit code information of bidders are determined;
character recognition is adopted for character areas of the legal representative identity card picture and the project principal identity card picture, and citizen identity numbers of the legal representative and the project principal are determined;
recognizing texts in text regions of corporate certificate pictures or business license pictures of a business unit, an enterprise business unit and an enterprise by adopting an OCR image recognition technology, and determining names, categories and legal representative information of bidders;
and recognizing texts in text areas of the legal representative identity card picture and the project principal identity card picture by adopting an OCR image recognition technology, and determining name information of the legal representative and the project principal of the bidder.
7. The method for verifying the bidder information based on the picture recognition as claimed in claim 1, wherein after the step of storing the legal certificate and the business license of the bidder in the verification passing data table when the verification passes, further comprising:
and automatically inputting the information of the passed business units, enterprise business units and corporate certificate or business license information of the enterprises in the verification passing data table into the bid evaluation system, and storing the information of the picture of the corporate certificate or business license of the manually failed business units, enterprise business units and enterprises in the abnormal database.
8. A bidder information verification system based on picture recognition is characterized by comprising:
the acquiring module is used for acquiring the identity information picture of the bidder; the identity information pictures comprise legal person certificate pictures, business license pictures, legal representative identity card pictures and project responsible person identity card pictures;
the preprocessing module is used for preprocessing the identity information picture of the bidder to obtain an identity information correction picture of the bidder; wherein the preprocessing comprises inclination correction, graying, USM sharpening and binaryzation;
the identification module is used for identifying the identity information correction picture of the bidder to obtain a unified social credit code, a legal representative name and a citizen identity card number of the bidder, a project principal name and a citizen identity card number of the bidder;
the verification module is used for acquiring the effective date specified by the bidding document, verifying the bidder by using a third party credit institution when the current date is within the effective date, and judging whether the bidder has integrity bad records and bribery criminal records; wherein, the third party credit investigation institution provides a Chinese referee document network, an on-line public system of public credit information of public institutions or national enterprises;
the first storage module is used for extracting the unified social credit code, the legal representative name and the citizen identity card number of the bidder, the project principal name and the citizen identity card number of the project principal when the verification fails, and storing the uniform social credit code, the legal representative name and the citizen identity card number of the project principal in the manual verification data table for manual verification;
and the second storage module stores the legal person certificate and the business license of the bidder into the verification passing data table when the verification passes.
9. A computer arrangement comprising a memory and a processor, the memory storing a computer program, wherein the processor, when executing the computer program, performs the steps of the method according to any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211387357.0A CN115731377A (en) | 2022-11-07 | 2022-11-07 | Bidder information verification system, method and device based on picture identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211387357.0A CN115731377A (en) | 2022-11-07 | 2022-11-07 | Bidder information verification system, method and device based on picture identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115731377A true CN115731377A (en) | 2023-03-03 |
Family
ID=85294760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211387357.0A Withdrawn CN115731377A (en) | 2022-11-07 | 2022-11-07 | Bidder information verification system, method and device based on picture identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115731377A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391068A (en) * | 2023-10-27 | 2024-01-12 | 中国人寿保险股份有限公司山东省分公司 | Method and system for checking life insurance security business information based on RPA |
-
2022
- 2022-11-07 CN CN202211387357.0A patent/CN115731377A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391068A (en) * | 2023-10-27 | 2024-01-12 | 中国人寿保险股份有限公司山东省分公司 | Method and system for checking life insurance security business information based on RPA |
| CN117391068B (en) * | 2023-10-27 | 2024-04-05 | 中国人寿保险股份有限公司山东省分公司 | Method and system for checking life insurance security business information based on RPA |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12008827B2 (en) | Systems and methods for developing and verifying image processing standards for mobile deposit | |
| US10303937B2 (en) | Systems and methods for mobile image capture and content processing of driver's licenses | |
| US11544945B2 (en) | Systems and methods for mobile image capture and content processing of driver's licenses | |
| CN110569341B (en) | Method and device for configuring chat robot, computer equipment and storage medium | |
| CN110287971B (en) | Data verification method, device, computer equipment and storage medium | |
| US8577118B2 (en) | Systems for mobile image capture and remittance processing | |
| US20160078632A1 (en) | Document image compression method and its application in document authentication | |
| CN112507782A (en) | Text image recognition method and device | |
| CN111445058A (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN115731377A (en) | Bidder information verification system, method and device based on picture identification | |
| CN114241463A (en) | Signature verification method and device, computer equipment and storage medium | |
| US7522760B1 (en) | Method for inspecting document images | |
| CN111582115A (en) | Financial bill processing method, device and equipment and readable storage medium | |
| CN116168407A (en) | Identity card image quality inspection method and system | |
| CN111860314B (en) | Electronic license verification method, device and system based on image recognition | |
| CN112380957A (en) | Method and device for identifying other item ticket information, computer equipment and storage medium | |
| CN115205882A (en) | Intelligent identification and processing method for expense voucher in medical industry | |
| CN110232322B (en) | Authentication method and device for identity card, computer equipment and storage medium | |
| CN117095446B (en) | Cloud database-based instant license generation and verification method, system and medium | |
| CN117894033B (en) | Method and system for checking consistency of answer sheets based on OCR (optical character recognition) | |
| CN116704246A (en) | Image identification method and device, electronic equipment and storage medium | |
| US7570835B2 (en) | Edge smoothing filter for character recognition | |
| WO2005114548A1 (en) | A method for the assessment of the quality and usability of digital cheque images | |
| CN118675189A (en) | Automatic correction method and system for certificate of image scanning equipment | |
| CN116151993A (en) | Integrated general insurance flow system and method based on double-check insurance mechanism |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230303 |