Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fingerprint comparison method and system based on deep learning, readable medium and equipment

A deep learning and fingerprint technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problems of recognition performance degradation, backlog, bottlenecks, etc.

Pending Publication Date: 2021-09-10
INST OF FORENSIC SCI OF MIN OF PUBLIC SECURITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the continuous increase of the capacity of the fingerprint database, there are many deficiencies in the feature point identification method, mainly: 1. Due to the limitation of the number of features (about 100 complete fingerprints), the fingerprint identification algorithm based on feature points, when the on-site fingerprints are incomplete and In the case of deformation, the recognition performance continues to decline; 2. A large amount of manual intervention is required to mark and calibrate the feature points; 3. After years of continuous improvement, the performance of the algorithm based on feature points has reached the bottleneck, and a large backlog of incomparable in the case

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fingerprint comparison method and system based on deep learning, readable medium and equipment
  • Fingerprint comparison method and system based on deep learning, readable medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] This embodiment discloses a fingerprint comparison method based on deep learning, such as figure 1 shown, including the following steps:

[0023] S1 input the fingerprint image into the deep learning model to extract texture features, and store the extracted texture features in the texture feature database, wherein the texture features in the texture feature database are updated after a predetermined period of time;

[0024] S2 Input the fingerprint image to be compared into the deep learning model for feature extraction, extracting texture features, detail features and dictionary features;

[0025] Dictionary features: Sparse encoding of fingerprint images, done in two steps:

[0026] S2.1 dictionary training, using training samples to obtain a dictionary (also called base) by minimizing the cost function;

[0027] S2.2 Feature coding, using the dictionary learned in step S2.1 to minimize the cost function again to obtain the features (also called coefficients) of ne...

Embodiment 2

[0035] Based on the same inventive concept, this embodiment discloses a fingerprint comparison system based on deep learning, including:

[0036] The first feature extraction module is used to input the fingerprint image into the deep learning model to extract texture features, and store the extracted texture features into the texture feature database;

[0037] The second feature extraction module is used to input the fingerprint image to be compared into the deep learning model for feature extraction, extracting texture features, detail features and dictionary features;

[0038] The candidate list building module is used to input the texture feature obtained by the second feature extraction module into the texture feature database of the first feature extraction module, obtain a fingerprint image matching its feature, and generate a fingerprint image candidate list;

[0039] The result list generation module is used to compare the detailed features of the fingerprint image to b...

Embodiment 3

[0041] Based on the same inventive concept, this embodiment discloses a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to realize any of the above-mentioned fingerprint comparison based on deep learning method.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of fingerprint comparison, and relates to a fingerprint comparison method and system based on deep learning, a readable medium and equipment, and the method comprises the following steps: S1, inputting a fingerprint image into a deep learning model for texture feature extraction, and storing the extracted texture features into a texture feature database; S2, inputting fingerprint images to be compared into the deep learning model for feature extraction, and extracting texture features, detail features and dictionary features; S3, inputting the textural features obtained in the step 2 into the textural feature database in the step S1, obtaining fingerprint images matched with the textural features, and generating a fingerprint image candidate list; and S4, comparing the detail features of the fingerprint images to be compared with the fingerprint images in the fingerprint image candidate list, and generating a fingerprint comparison result list in combination with the dictionary features. According to the invention, fingerprint features can be identified more quickly and accurately.

Description

technical field [0001] The invention relates to a fingerprint comparison method, system, readable medium and equipment based on deep learning, which belongs to the technical field of fingerprint comparison, in particular to the technical field of intelligent fingerprint comparison. Background technique [0002] As an important biological feature of the human body, fingerprints have long been used as a way of identification in various fields of social life. Automatic fingerprint identification technology, as a mature biometric identification technology, is widely used in public security, identity authentication, access control and other fields. With the increasingly widespread application of fingerprint identification, especially the rapid growth of the fingerprint database, new challenges are brought to the automatic fingerprint identification technology. Judging from the tests of major domestic fingerprint technology products carried out in recent years, the traditional au...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06N3/04
CPCG06N3/045
Inventor 李孝君周纯葆张世泽吴春生王彦棡韩柯刘寰冯才刚孙忠吴浩陈子龙吕昱帆
Owner INST OF FORENSIC SCI OF MIN OF PUBLIC SECURITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com