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

Full-automatic fingerprint detail feature extraction method and system

A technology of detail features and extraction methods, applied in neural learning methods, acquisition/organization of fingerprints/palmprints, instruments, etc., can solve problems such as increased recognition complexity, fingerprint image degradation, etc., to reduce optimization complexity and delete redundancy point, easy-to-deploy effect

Pending Publication Date: 2022-04-12
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, usually when collecting fingerprints, the fingerprint image is degraded due to the noise of the collection equipment and the uneven force of the collector. These factors increase the complexity of identification. Therefore, effective modeling of degraded fingerprint images is a problem that has not yet been effectively solved. The problem

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
  • Full-automatic fingerprint detail feature extraction method and system
  • Full-automatic fingerprint detail feature extraction method and system
  • Full-automatic fingerprint detail feature extraction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] According to a kind of automatic fingerprint minutiae feature extraction method provided by the present invention, comprising:

[0072] Step S1: Preliminary prediction network based on fingerprint prior knowledge and fingerprint minutiae points forms fingerprint minutiae extraction network D;

[0073] Step S2: Preprocessing the fingerprint image to obtain a preprocessed fingerprint image;

[0074] Step S3: using the preprocessed fingerprint image to train the fingerprint minutiae extraction network D to obtain the trained fingerprint minutiae extraction network D;

[0075] Wherein, for each unit F=(I) in the training image set, the minutiae point extraction network D of the fingerprint is generated to predict the minutiae sequence P=(M p ), and with the original marked truth-value detail point G=(M g ) Calculate the attribute information difference loss function L and backpropagation for optimization iterations to obtain the optimal fingerprint minutiae point extracti...

Embodiment 2

[0126] Embodiment 2 is a preferred example of embodiment 1

[0127] The present invention provides a fingerprint minutiae point extraction method based on ResNet feature extraction and generalized intersection-over-union ratio (GIoU) ​​non-maximum suppression of redundant deletion. The method is based on existing prior knowledge and neural network fingerprint minutiae feature extraction architecture, A more effective fingerprint minutiae feature extraction algorithm is proposed. Since the neural network fingerprint minutiae feature extraction method based on the general CNN or VGG structure can not meet the actual needs in terms of recognition accuracy, a fingerprint based on ResNet is developed. The feature extraction algorithm realizes the detection of fingerprint minutiae, and then combines the non-maximum suppression method of the generalized intersection ratio metric to delete redundant minutiae, further improving the accuracy of fingerprint minutiae detection.

[0128] T...

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 provides a full-automatic fingerprint detail feature extraction method and system. The method comprises the following steps: S1, forming a fingerprint detail extraction network D based on fingerprint priori knowledge and a fingerprint detail point prediction network; s2, preprocessing the fingerprint image to obtain a preprocessed fingerprint image; s3, training a fingerprint detail extraction network D by using the preprocessed fingerprint image to obtain a trained fingerprint detail extraction network D; s4, utilizing the trained fingerprint detail extraction network D to preliminarily predict a fingerprint detail point set; and S5, the fingerprint minutiae set is preliminarily predicted, fingerprint redundant points are eliminated by applying non-maximum suppression based on a pervasive intersection-to-parallel ratio, and a final accurate fingerprint minutiae set is obtained.

Description

technical field [0001] The invention relates to the technical field of image processing and pattern recognition, in particular to a fully automatic fingerprint detail feature point extraction method. Background technique [0002] In recent years, with the great progress of network computing and services, GPU resource virtualization, and system integration technology, it is possible for online automatic fingerprint identification technology to be widely used in the real world. Fingerprint identification technology is especially used in criminal investigation, judicial identification, finance and Social security and other areas play an important role. Typically, fingerprint identification technology includes two stages of registration and identification authentication. The fingerprint registration stage mainly involves fingerprint image acquisition, foreground image segmentation, normalization, direction field / frequency field estimation, enhancement, binarization, thinning, e...

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): G06V40/12G06V10/34G06V10/80G06V10/774G06V10/82G06N3/04G06N3/08
Inventor 赵洪田郑世宝王玉
Owner SHANGHAI JIAO TONG UNIV
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