Unlock instant, AI-driven research and patent intelligence for your innovation.

Low-exposure vein image enhancement method based on actor-critic model

A vein image, low-exposure technology, applied in the field of identity recognition, can solve problems such as loss of vein details, avoid cumbersomeness, improve robustness and generalization ability, and enhance the effect of low-exposure vein images

Active Publication Date: 2022-01-04
CHINA UNIV OF MINING & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a low-exposure vein image enhancement method based on the Actor-Critic model, which solves the problem of vein detail loss caused by global image processing, and achieves the effect of low-exposure vein image enhancement

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
  • Low-exposure vein image enhancement method based on actor-critic model
  • Low-exposure vein image enhancement method based on actor-critic model
  • Low-exposure vein image enhancement method based on actor-critic model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0100] The low-exposure vein image enhancement method based on the Actor-Critic model of the present invention, the steps are as follows:

[0101] Step S1. In order to verify the effectiveness of this method, the self-made vein dataset (Data-1) and the public dataset PTUPalmvein (Data-2) are used, and the ROI extraction method is used to extract the effective area of ​​the vein image in the dataset, and the pixel size is obtained as 512*800 vein image. When using the processed Data-1 dataset, 2000 normal-exposure dorsal vein images and 2000 low-exposure hand dorsal vein images synthesized by gamma change and Gaussian noise were used as the training set. When using the processed Data-2 data set, since this data set is a public data set, it cannot be collected by itself, so a total of 800 normal-exposed palm vein images and 800 synthetic low-exposure palm vein images were used in the first two parts of the data set Vein images are used as training set. Part of the vein image a...

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 discloses a low-exposure vein image enhancement method based on the Actor-Critic model, designing contrast, saturation, white balance, exposure and tone curve function filters, and selecting an optimal group of image filters through the Actor-Critic model Order and parameters, and use it to filter the low-exposure vein image, output the image corresponding to each filter operation and extract the detail information, superimpose it on the image processed by the last layer of filters, and finally output the enhanced vein image. The low-exposure vein image enhancement model based on Actor-Critic disclosed in the present invention can automatically select the image editing filter order and parameters, realize the restoration of the light information of the low-exposure vein image and the enhancement of contrast, and extract each filter in the filtering process The complementary vein detail information of the output image solves the problem of vein detail loss caused by global image processing, and achieves the effect of low-exposure vein image enhancement.

Description

technical field [0001] The invention belongs to identification technology, in particular to a low-exposure vein image enhancement method based on an Actor-Critic model. Background technique [0002] Under the irradiation of near-infrared light, hemoglobin in veins will absorb a large amount of near-infrared light, while other biological tissues mainly composed of bone and fat cannot absorb it, thus forming a vein image with dark veins and bright background. Under the influence of some external factors, in addition to the darker shadows formed by the absorption of near-infrared light by veins, other background areas also appear dark, so that there is no obvious distinction between vein patterns and background areas, and the contrast of vein images is low. Therefore, a low-exposure vein image enhancement method based on the Actor-Critic model is proposed for the first time. The low-exposure vein image is enhanced through image processing, the illumination information of the im...

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 Patents(China)
IPC IPC(8): G06T5/20G06T5/50
CPCG06T5/20G06T5/50G06T2207/10024G06T2207/30168G06T2207/30101G06T2207/20221G06T2207/20024G06T2207/20081
Inventor 王军袁静波李玉莲潘在宇申政文陈晓玲
Owner CHINA UNIV OF MINING & TECH