A network verification method and system based on fingerprint recognition

Abstract

The present invention relates to the field of fingerprint recognition image processing technology, and in particular to a network verification method and system based on fingerprint recognition. The present invention is provided with a ridge verification unit, which can quickly and accurately determine whether a network verification system meets the standards based on the obtained ridge matching similarity, thereby improving the accuracy of the network verification method of fingerprint recognition. The obtained fingerprint detail point data can accurately determine whether the network verification system meets the standards, further improving the accuracy and reliability of the network verification method of fingerprint recognition. The acquired ridge local feature point data can quickly determine the reason why the network verification system does not meet the standards, thereby improving the accuracy of the operation of the network verification system.

Description

Technical Field

[0001] The present invention relates to the technical field of fingerprint recognition image processing, and in particular to a network verification method and system based on fingerprint recognition. Background Art

[0002] The fingerprint recognition system collects, analyzes and compares live fingerprints through special photoelectric conversion equipment and computer image processing technology, and can quickly and accurately identify personal identities. The system generally includes processes such as fingerprint image collection, fingerprint image processing, feature extraction, feature value comparison and matching. Modern electronic integrated manufacturing technology has miniaturized fingerprint image reading and processing equipment. Fingerprint recognition technology mainly involves four functions: reading fingerprint images, extracting features, saving data and comparing. Fingerprint recognition software establishes a digital representation of fingerprints - feature data, a one-way conversion that can be converted from fingerprints to feature data but not from feature data to fingerprints, and two different fingerprints will not produce the same feature data. The software finds data points called "nodes" on the fingerprint, that is, the coordinate positions of the bifurcation, termination or looping of the fingerprint lines, which have more than seven unique features at the same time. Because there are usually 70 nodes on an average finger, this method will generate about 490 data. Through the method of computer cloud data terminal calculation, the templates of the two fingerprints are compared, their similarity is calculated, and finally the matching result of the two fingerprints is obtained. How to improve the accuracy of network verification methods is becoming increasingly important.

[0003] Chinese patent publication number CN: 103873244B discloses an identity authentication method and system in mobile payment based on fingerprint recognition. The solution integrates mobile payment technology with USB-Key technology, and introduces fingerprint recognition technology in biometric authentication technology, so that users can authenticate their identities by scanning fingerprints in mobile payment. In combination with USB-Key certificate authentication and bank verification of card number and password, the security of users' mobile payment transactions is guaranteed. At the same time, users can use mobile phones to make mobile payments with the same transaction amount authority as using USB-Key for online transactions. However, the invention does not involve the problem of improving the accuracy of the network verification method of fingerprint recognition. Summary of the invention

[0004] To this end, the present invention provides a network authentication method and system based on fingerprint recognition to overcome the problem of low accuracy of the network authentication method based on fingerprint recognition in the prior art.

[0005] To achieve the above object, the present invention provides a network verification method based on fingerprint recognition, comprising:

[0006] The fingerprint collection unit transmits the collected fingerprint image to the fingerprint preprocessing unit;

[0007] The fingerprint preprocessing unit preprocesses the acquired fingerprint image to obtain data information and transmits the preprocessed image information to the ridge feature unit for data extraction; the fingerprint preprocessing unit preprocesses the fingerprint image including image segmentation, image enhancement, binarization and thinning processing for the fingerprint image;

[0008] According to the ridge feature unit, the extracted data information is transmitted to the ridge matching unit so that the ridge matching unit performs image matching based on the data information; the extracted data information includes the total number of fingerprint detail points, ridge endpoint data, ridge bifurcation point data, ridge local feature point data, image segmentation number data and image enhancement contrast data;

[0009] The line matching unit transmits the line matching similarity data obtained based on the matching of the line image with the preset line image reference to the line verification unit so that the line verification unit determines whether the network verification system meets the standards;

[0010] When the network verification system is preliminarily determined to be non-compliant with the standards based on the acquired line matching similarity data according to the line verification unit, whether the network verification system is compliant with the standards is secondarily determined based on the acquired total number of fingerprint detail points data; and, when it is determined that the network verification system is non-compliant with the standards, the reason why the network verification system is non-compliant is determined based on the acquired line local feature point data.

[0011] Furthermore, when the ridge verification unit of the present invention preliminarily determines that the network verification system does not meet the standards based on the difference between the acquired ridge matching similarity and the preset matching similarity benchmark, it secondarily determines whether the network verification system meets the standards based on the acquired total number of fingerprint ridge detail points data, and, when it is determined that the network verification system does not meet the standards, it determines the reason why the network verification system does not meet the standards based on the acquired ridge local feature point data.

[0012] Furthermore, when the line verification unit of the present invention secondarily determines that the network verification system does not meet the standards based on the difference between the acquired total number of fingerprint line detail points data and a preset benchmark and determines that the reason for not meeting the standards is a problem with the line matching similarity benchmark, the line matching similarity benchmark is re-determined based on the acquired line bifurcation point data.

[0013] Furthermore, the ridge verification unit of the present invention is provided with several correction methods for the ridge matching similarity benchmark based on the difference between the acquired ridge bifurcation point data and the preset bifurcation point benchmark, and the correction range of each correction method for the ridge matching similarity benchmark is different.

[0014] Furthermore, the ridge verification unit of the present invention determines the reason why the network verification system does not meet the standard based on the difference between the preset feature point reference and the acquired ridge local feature point data, and selects a corresponding processing method according to the determined reason, including:

[0015] When it is determined that the reason why the network verification system does not meet the standards is a problem with the total number of fingerprint image segmentation benchmarks, re-determine the total number of image segmentation benchmarks based on the acquired ridge bifurcation point data; and,

[0016] When it is determined that the reason why the network verification system does not meet the standard is a problem with the grain line feature point benchmark, the grain line feature point benchmark is re-determined based on the total number of grain line detail point data obtained;

[0017] When it is determined that the reason why the network verification system does not meet the standards is a problem with the fingerprint image enhancement contrast benchmark, the image enhancement contrast benchmark is re-determined based on the acquired ridge endpoint data.

[0018] Furthermore, the ridge verification unit of the present invention is provided with several adjustment methods for the total number of image segmentation benchmarks based on the difference between the acquired ridge bifurcation point data and a preset benchmark, and the adjustment range of each adjustment method for the total number of image segmentation benchmarks is different.

[0019] Furthermore, the ridge verification unit of the present invention is provided with a plurality of adjustment modes for the ridge feature point reference based on the difference between the acquired ridge endpoint data and the preset reference, and the adjustment range of each adjustment mode for the ridge feature point reference is different.

[0020] Furthermore, the ridge verification unit of the present invention is provided with a plurality of adjustment modes for the image enhancement contrast reference based on the difference between the acquired ridge endpoint data and the preset reference, and the adjustment range of each adjustment mode for the image enhancement contrast reference is different.

[0021] Compared with the prior art, the beneficial effect of the present invention is that the present invention can quickly and accurately determine whether the network verification system meets the standards based on the obtained similarity of the line matching by providing a line verification unit, thereby improving the accuracy of the network verification method of fingerprint recognition, and can accurately determine whether the network verification system meets the standards by obtaining fingerprint detail point data, thereby further improving the accuracy and reliability of the network verification method of fingerprint recognition. The reason why the network verification system does not meet the standards can be quickly determined by obtaining the local feature point data of the lines, thereby improving the accuracy of the operation of the network verification system.

[0022] Furthermore, the present invention can accurately and reliably segment the fingerprint image from the background area through image segmentation, effectively shortening the image processing time and improving the accuracy of feature extraction.

[0023] Furthermore, the present invention can effectively reduce noise and enhance the contrast between ridges and valleys through image enhancement, thereby effectively improving accuracy.

[0024] Furthermore, the present invention can effectively use the width of the ridge as the width of a single pixel through refinement, effectively maintaining the continuity of the original ridge, reducing the impact of human factors, and thus improving the accuracy of the network verification system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flowchart of the steps of the network verification method for fingerprint identification according to the present invention;

[0026] Figure 2 A flow chart for determining whether the network verification method of the present invention complies with the standard;

[0027] Figure 3 A secondary determination flow chart of whether the network verification method of the present invention complies with the standard;

[0028] Figure 4 This is a structural block diagram of the fingerprint recognition network verification system described in the present invention. DETAILED DESCRIPTION

[0029] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0030] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0031] It should be noted that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical test data and corresponding historical test results of the system of the present invention in the three months before this test. The system of the present invention comprehensively determines the values ​​of the preset parameter benchmarks for this test based on the results of the cumulative tests in the previous three months before this test. It can be understood by those skilled in the art that the system of the present invention can determine the single parameter mentioned above by selecting the highest proportion of the value as the preset benchmark parameter according to the data distribution, using weighted summation to use the obtained value as the preset benchmark parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset benchmark parameter or other selection methods, as long as the system of the present invention can clearly define the different specific situations in the single determination process through the obtained values.

[0032] See also Figure 1As shown, it is a flow chart of the steps of the network verification method based on fingerprint recognition of the present invention. The steps of the network verification method based on fingerprint recognition of the present invention include:

[0033] Step S1, the fingerprint collection unit transmits the collected fingerprint image to the fingerprint preprocessing unit;

[0034] Step S2, obtaining data information according to the preprocessed fingerprint image, and transmitting the preprocessed image information to the ridge feature unit for data extraction; the fingerprint preprocessing unit performs preprocessing on the fingerprint image, and the preprocessing includes image segmentation, image enhancement and refinement processing on the fingerprint image;

[0035] Step S3, the data information extracted based on the ridge feature unit is transmitted to the ridge matching unit so that the ridge matching unit performs image matching based on the data information; the extracted data information is transmitted to the ridge matching unit for image matching, and the data information includes the total number of fingerprint detail points, ridge endpoint data, ridge bifurcation point data, ridge local feature point data, image segmentation number data and image enhancement contrast data;

[0036] Step S4, determining whether the network verification system meets the standard based on the line matching similarity data obtained after matching the line image extracted by the line matching unit with a preset line image benchmark;

[0037] Step S5, when the line verification unit preliminarily determines that the network verification system does not meet the standards based on the acquired line matching similarity data, it secondarily determines whether the network verification system meets the standards based on the acquired fingerprint detail point data; and, when it is determined that the network verification system does not meet the standards, it determines the reason why the network verification system does not meet the standards based on the acquired line local feature point data.

[0038] Specifically, based on the collection method of the fingerprint collection unit, the fingerprint includes one or more of the following: a fingerprint, a live fingerprint, and a fuzzy fingerprint. A fingerprint refers to the trace of a fingerprint left by pressing a finger stained with ink on something (preferably paper), which is then converted into digital information by a corresponding device to obtain a fingerprint image. The effective area collected by the fingerprint is relatively large, but due to the limitations of the collection method, the collection speed is slow and there are many fingerprint defects. It is currently difficult to strictly control the quality of the collection.

[0039] According to different input principles, live fingerprint collectors are divided into optical, semiconductor and ultrasonic types. According to whether the finger skin is in contact with the fingerprint collector during collection, it can be divided into contact type and non-contact type. The live fingerprint collection device obtains a digitized fingerprint image, preferably a live fingerprint.

[0040] Fuzzy fingerprints generally refer to fingerprint images that require fingerprint traces to be processed through technologies such as development, photography, and scanning.

[0041] Specifically, the fingerprint preprocessing unit is used to highlight the texture and direction information in the fingerprint image, and eliminate or reduce useless information such as noise. Fingerprint image preprocessing includes fingerprint image segmentation, image enhancement, binarization and thinning. Image segmentation is at the forefront of preprocessing, and accurately and reliably separates the fingerprint image from the background area, which is of great significance for shortening image processing time and improving the accuracy of feature extraction. Image enhancement is to restore and enhance the recoverable lines according to the directionality and line distance of the fingerprint image texture, and to shield the irrecoverable areas. Binarization is to set the grayscale of pixels in the image with a grayscale greater than a certain threshold to 1, and the grayscale of pixels less than or equal to the threshold to 0, that is, to convert the image into a binary image. Fingerprint thinning is to extract the ridge skeleton of the fingerprint image.

[0042] Specifically, the ridge feature unit extracts fingerprint minutiae data, ridge endpoint data, ridge bifurcation point data and ridge local feature point data, wherein: the minutiae of the fingerprint uses two minutiae features including ridge endpoints and bifurcation points. The ridge endpoint refers to the position where the ridge suddenly ends, while the ridge bifurcation point is the position where the ridge suddenly splits into two. These two types of minutiae points are used to determine the uniqueness of the description of the fingerprint.

[0043] Specifically, the problem solved by the ridge matching unit is to extract feature information from two given images, match them, and determine whether the two fingerprints come from the same finger. The ridge endpoint is the point where the fingerprint line suddenly ends, while the ridge bifurcation point is the point where the ridge line suddenly splits into two. Fingerprint matching determines the uniqueness of fingerprints by comparing the minutiae features of two fingerprints.

[0044] See also Figure 2 As shown, it is a flow chart for determining whether the network verification method of the present invention meets the standard. The line verification unit of the present invention determines whether the network verification system meets the standard based on the difference between the acquired line matching similarity and the preset matching similarity benchmark, wherein:

[0045] If the difference is less than or equal to a preset first benchmark, the ridge verification unit determines that the network verification system meets the standard and re-tests after a preset time;

[0046] If the difference is greater than a preset first reference and less than or equal to a preset second reference, the ridge verification unit preliminarily determines that the network verification system does not meet the standard, and secondarily determines whether the network verification system meets the standard based on the acquired fingerprint ridge detail point data;

[0047] If the difference is greater than a preset second reference, the grain line verification unit determines that the network verification system does not meet the standard, and determines the reason why the network verification system does not meet the standard based on the acquired grain line local feature point data.

[0048] Preferably, the present invention sets the preset time to 7 days.

[0049] See also Figure 3 As shown, it is a secondary determination flow chart of whether the network verification method of the present invention meets the standard. The ridge verification unit of the present invention secondary determines whether the network verification system meets the standard based on the difference between the acquired fingerprint ridge detail point number data and the preset benchmark, wherein:

[0050] If the difference is less than or equal to a preset difference reference, the ridge verification unit determines that the network verification system meets the standard and re-tests after a preset time;

[0051] If the difference is greater than a preset difference benchmark, the grain verification unit determines that the reason why the network verification system does not meet the standard is a problem with the grain matching similarity benchmark, and redetermines the grain matching similarity benchmark based on the acquired grain bifurcation point data.

[0052] Preferably, the present invention sets the preset time to 7 days.

[0053] Specifically, the ridge verification unit is provided with several correction methods for the ridge matching similarity benchmark based on the difference between the acquired ridge bifurcation point data and the preset bifurcation point benchmark, wherein:

[0054] If the difference is less than or equal to a preset first difference reference, the grain verification unit uses a first correction coefficient α1 to correct the grain matching similarity reference button to a corresponding value;

[0055] If the difference is greater than a preset first difference reference and less than or equal to a preset second difference reference, the grain verification unit uses a second correction coefficient α2 to correct the grain matching similarity reference button to a corresponding value;

[0056] If the difference is greater than a preset second difference reference, the grain verification unit uses a third correction coefficient α3 to correct the grain matching similarity reference button to a corresponding value.

[0057] Among them, the correction formula adopted by the present invention is, K=k×α n , where k is the preset line matching similarity benchmark before correction, K is the corrected line matching similarity benchmark, n is a positive integer, α n As preset correction coefficients, the present invention sets α1=0.98; α2=0.97; α3=0.96.

[0058] The ridge verification unit of the present invention determines the reason why the network verification system does not meet the standard based on the difference between the preset feature point reference and the acquired ridge local feature point data, wherein:

[0059] If the difference is less than or equal to a preset first benchmark, the ridge verification unit determines that the reason why the network verification system does not meet the standard is a problem with the fingerprint image segmentation quantity benchmark, and redetermines the image segmentation quantity benchmark based on the acquired ridge bifurcation point data;

[0060] If the difference is greater than a preset first benchmark and less than or equal to a preset second benchmark, the grain line verification unit determines that the reason why the network verification system does not meet the standard is a problem with the grain line feature point benchmark, and re-determines the grain line feature point benchmark based on the acquired total number of grain line detail point data;

[0061] If the difference is greater than a preset second benchmark, the ridge verification unit determines that the reason why the network verification system does not meet the standard is a problem with the fingerprint image enhancement contrast benchmark, and redetermines the image enhancement contrast benchmark based on the acquired ridge endpoint data.

[0062] Specifically, the ridge verification unit of the present invention is provided with several adjustment methods for the total number of image segmentation benchmarks based on the difference between the acquired ridge bifurcation point data and the preset benchmark, wherein:

[0063] If the difference is less than or equal to a preset first benchmark, the ridge verification unit uses a first adjustment coefficient β1 to adjust the total number of image segmentation benchmark buttons to a corresponding value;

[0064] If the difference is greater than a preset first benchmark and less than or equal to a preset second benchmark, the ridge verification unit uses a second adjustment coefficient β2 to adjust the total number of image segmentation benchmark buttons to a corresponding value;

[0065] If the difference is greater than the preset second reference, the ridge verification unit uses the third adjustment coefficient β3 to adjust the total number of image segmentation reference buttons to a corresponding value;

[0066] Among them, the adjustment formula adopted by the present invention is, Q=q×βn, wherein q is the total number of image segmentation benchmarks preset before adjustment, Q is the total number of image segmentation benchmarks after adjustment, n is a positive integer, βn is a preset adjustment coefficient, and the present invention sets, β1=0.99; β2=0.98; β3=0.97.

[0067] Specifically, the ridge verification unit of the present invention is provided with several adjustment methods for the ridge feature point benchmark based on the difference between the acquired ridge endpoint data and the preset benchmark, wherein:

[0068] If the difference is less than or equal to the preset first reference, the grain line verification unit uses the first adjustment coefficient X1 to adjust the grain line feature point reference button to a corresponding value;

[0069] If the difference is greater than the preset first reference and less than or equal to the preset second reference, the grain line verification unit uses the second adjustment coefficient X2 to adjust the grain line feature point reference button to a corresponding value;

[0070] If the difference is greater than the preset second reference, the grain line verification unit uses the third adjustment coefficient X3 to adjust the grain line feature point reference button to a corresponding value;

[0071] Among them, the adjustment formula adopted by the present invention is, M=m×ηn, wherein, m is the preset grain feature point reference before adjustment, M is the grain feature point reference after adjustment, n is a positive integer, ηn is the preset adjustment coefficient, and the present invention sets, η1=0.98; η2=0.96; η3=0.94.

[0072] Specifically, the ridge verification unit of the present invention is provided with several adjustment methods for the image enhancement contrast benchmark based on the difference between the acquired ridge endpoint data and the preset benchmark, wherein:

[0073] If the difference is less than or equal to the preset first reference, the ridge verification unit uses the first adjustment coefficient γ1 to adjust the image enhancement contrast reference button to a corresponding value;

[0074] If the difference is greater than a preset first reference and less than or equal to a preset second reference, the ridge verification unit uses a second adjustment coefficient γ2 to adjust the image enhancement contrast reference button to a corresponding value;

[0075] If the difference is greater than the preset second reference, the ridge verification unit uses the third adjustment coefficient γ3 to adjust the image enhancement contrast reference button to a corresponding value;

[0076] Among them, the adjustment formula adopted by the present invention is, R=r×βn, wherein r is the total number of image segmentation benchmarks preset before adjustment, R is the total number of image segmentation benchmarks after adjustment, n is a positive integer, γn is a preset adjustment coefficient, and the present invention sets, γ1=0.99; γ2=0.97; γ3=0.95.

[0077] See also Figure 4 As shown, it is a network verification system based on fingerprint recognition using the method described in any one of claims 1 to 8 of the present invention, comprising:

[0078] A fingerprint collection unit, which is used to collect fingerprint images;

[0079] A fingerprint preprocessing unit is connected to the fingerprint acquisition unit and is used to preprocess the fingerprint image to obtain data information and transmit the preprocessed image information to the ridge feature unit for data extraction; the fingerprint preprocessing unit preprocesses the fingerprint image including image segmentation, image enhancement, binarization and thinning of the fingerprint image.

[0080] A ridge feature unit, which is connected to the fingerprint preprocessing unit and is used to transmit the extracted data information to the ridge matching unit so that the ridge matching unit performs image matching based on the data information; the extracted data information includes fingerprint detail point data, ridge endpoint data, ridge bifurcation point data and ridge local feature point data;

[0081] A grain matching unit, connected to the grain feature unit, for matching the acquired grain image with a pre-stored grain image reference to obtain grain matching similarity data;

[0082] A grain checking unit is connected to the grain matching unit and is used to determine whether the network verification system meets the standards based on the acquired grain matching similarity data.

[0083] Specifically, the formula used by the ridge verification unit to calculate the ridge matching similarity is:

[0084] ;

[0085] Among them, θ represents the similarity of grain line matching, f represents the number of grain line endpoint data obtained, f0 represents the preset grain line endpoint data number benchmark, g represents the number of grain line bifurcation point data obtained, and g0 represents the preset grain line bifurcation point data benchmark.

[0086] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0087] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A network verification method based on fingerprint recognition, characterized in that: include: The fingerprint collection unit transmits the collected fingerprint image to the fingerprint preprocessing unit; The fingerprint preprocessing unit preprocesses the acquired fingerprint image to obtain data information and transmits the preprocessed image information to the ridge feature unit for data extraction; the fingerprint preprocessing unit preprocesses the fingerprint image including image segmentation, image enhancement, binarization and thinning processing for the fingerprint image; According to the ridge feature unit, the extracted data information is transmitted to the ridge matching unit so that the ridge matching unit performs image matching based on the data information; the extracted data information includes the total number of fingerprint detail points, ridge endpoint data, ridge bifurcation point data, ridge local feature point data, image segmentation number data and image enhancement contrast data; The line matching unit transmits the line matching similarity data obtained based on the matching of the line image with the preset line image reference to the line verification unit so that the line verification unit determines whether the network verification system meets the standards; When the network verification system is initially determined not to meet the standards by the ridge verification unit based on the acquired ridge matching similarity data, secondarily determining whether the network verification system meets the standards based on the acquired fingerprint detail point total number data, and, when it is determined that the network verification system does not meet the standards, determining the reason why the network verification system does not meet the standards based on the acquired ridge local feature point data; The ridge verification unit determines the reason why the network verification system does not meet the standard based on the difference between the preset feature point reference and the acquired ridge local feature point data, and selects a corresponding processing method according to the determined reason, including: If the difference between the preset feature point benchmark and the acquired ridge line local feature point data is less than or equal to the preset first benchmark, the ridge line verification unit determines that the reason why the network verification system does not meet the standard is a problem with the fingerprint image segmentation quantity benchmark, and redetermines the image segmentation quantity benchmark based on the acquired ridge line bifurcation point data; If the difference between the preset feature point reference and the acquired grain line local feature point data is greater than the preset first reference and less than or equal to the preset second reference, the grain line verification unit determines that the reason why the network verification system does not meet the standard is a problem with the grain line feature point reference, and re-determines the grain line feature point reference based on the acquired grain line detail point total number data; If the difference between the preset feature point benchmark and the acquired ridge local feature point data is greater than a preset second benchmark, the ridge verification unit determines that the reason why the network verification system does not meet the standard is a problem with the fingerprint image enhancement contrast benchmark, and redetermines the image enhancement contrast benchmark based on the acquired ridge endpoint data.

2. The network authentication method based on fingerprint recognition according to claim 1, characterized in that: When the line verification unit determines that the network verification system does not meet the standards based on the difference between the total number of fingerprint line detail points obtained and the preset benchmark, and determines that the reason for not meeting the standards is a problem with the line matching similarity benchmark, the line matching similarity benchmark is re-determined based on the obtained line bifurcation point data.

3. The network authentication method based on fingerprint recognition according to claim 2 is characterized in that: The ridge verification unit is provided with several correction methods for the ridge matching similarity benchmark based on the difference between the acquired ridge bifurcation point data and the preset bifurcation point benchmark, and the correction range of each correction method for the ridge matching similarity benchmark is different.

4. The network authentication method based on fingerprint recognition according to claim 3 is characterized in that: The ridge verification unit is provided with a plurality of adjustment methods for the total number of image segmentation benchmarks based on the difference between the acquired ridge bifurcation point data and the preset benchmark, and the adjustment range of each adjustment method for the total number of image segmentation benchmarks is different.

5. The network authentication method based on fingerprint recognition according to claim 4 is characterized in that: The ridge verification unit is provided with a plurality of adjustment modes for the ridge feature point reference based on the difference between the acquired ridge endpoint data and the preset reference, and the adjustment range of each adjustment mode for the ridge feature point reference is different.

6. The network authentication method based on fingerprint recognition according to claim 5, characterized in that: The ridge verification unit is provided with a plurality of adjustment modes for the image enhancement contrast reference based on the difference between the acquired ridge endpoint data and the preset reference, and the adjustment range of each adjustment mode for the image enhancement contrast reference is different.

7. A network verification system based on fingerprint recognition using the method according to any one of claims 1 to 6, characterized in that: include: A fingerprint collection unit, which is used to collect fingerprint images; A fingerprint preprocessing unit connected to the fingerprint collection unit is used to preprocess the fingerprint image to obtain data information and transmit the preprocessed image information to the ridge feature unit for data extraction; The fingerprint preprocessing unit performs preprocessing on the fingerprint image, including image segmentation, image enhancement, binarization and thinning on the fingerprint image; A ridge feature unit, which is connected to the fingerprint preprocessing unit and is used to transmit the extracted data information to the ridge matching unit so that the ridge matching unit performs image matching based on the data information; the extracted data information includes fingerprint detail point data, ridge endpoint data, ridge bifurcation point data and ridge local feature point data; A grain matching unit, connected to the grain feature unit, for matching the acquired grain image with a pre-stored grain image reference to obtain grain matching similarity data; A grain checking unit is connected to the grain matching unit and is used to determine whether the network verification system meets the standards based on the acquired grain matching similarity data.

8. The network verification system based on fingerprint recognition according to claim 7, characterized in that: The calculation formula for the ridge line matching similarity used by the ridge line verification unit is: ； Among them, θ represents the similarity of grain line matching, f represents the number of grain line endpoint data obtained, f0 represents the preset grain line endpoint data number benchmark, g represents the number of grain line bifurcation point data obtained, and g0 represents the preset grain line bifurcation point data benchmark.

Images