Fingerprint image enhancement method based on Retinex-ResNet network model

A fingerprint image and network model technology, applied in the field of image processing, can solve the problems of fingerprint image geometric deformation edge, blur, etc., achieve strong modeling ability, reduce the loss of fingerprint detail information, and solve the effect of gradient dispersion problem

Pending Publication Date: 2022-07-12
中电万维信息技术有限责任公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a fingerprint image enhancement method based on the Retinex-ResNet network model, which adopts methods of deformable convolution, parallel channel attention and serial spatial attention to solve the problem that fingerprint images are prone to geometric deformation on soft materials such as clothing and blurred edges

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 image enhancement method based on Retinex-ResNet network model
  • Fingerprint image enhancement method based on Retinex-ResNet network model
  • Fingerprint image enhancement method based on Retinex-ResNet network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention and its effects will be further described below in conjunction with the accompanying drawings.

[0024] The fingerprint image enhancement method based on the Retinex-ResNet network model, the fingerprint image is processed through three network modules, namely the decomposition network module, the adjustment network module and the fusion network module. The decomposition network module is based on the Retinex-Net network architecture and introduces the ResNet network model And the deformable convolutional network model, in which the ResNet network model solves the gradient dispersion problem and reduces the loss of fingerprint details, the deformable convolutional network model expands the network receptive field, and enhances the modeling ability of the geometric deformation of the fingerprint image; adjust the network module in the ResNet network On the basis of the model, the parallel channel attention and serial spatial attention mechanisms are ...

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 relates to the technical field of image processing, in particular to a fingerprint image enhancement method based on a Retinex-ResNet network model. The invention provides a fingerprint image enhancement method based on a Retinex-ResNet network model, which aims to solve the problems that fingerprint images obtained by different acquisition devices contain noise, texture has defects and edge blurring phenomena, and recognition of the fingerprint images is seriously interfered, and can effectively enhance the fingerprint images under low illumination, and improve the recognition accuracy of the fingerprint images. And meanwhile, texture defects and edge blurring phenomena can be effectively improved. According to the method, defects and edge blurring phenomena of fingerprint images on different media are solved, and a foundation is laid for accurate fingerprint identification.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fingerprint image enhancement method based on a Retinex-ResNet network model. Background technique [0002] Fingerprint image recognition is one of the biometric identification methods. It is widely used in the fields of public security, finance, medicine, public management and other fields because of its uniqueness, stability and identification. However, the quality of fingerprint images varies widely due to different collection devices. At the same time, fingerprint images on different media also have texture defects and blurred edges. For example, fingerprints on clothing pose a serious challenge to accurately extract fingerprint images. [0003] The invention patent with publication number CN113569715A discloses a fingerprint image enhancement method and device. First, calculate the grayscale distribution data of the acquired fingerprint image; then according to t...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06V40/12G06V10/30G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/251
Inventor 张峻崎焦勇杨祺秦涛
Owner 中电万维信息技术有限责任公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap