Method for converting infrared face image into visible light face image

A face image and conversion method technology, which is applied in the directions of graphic image conversion, image data processing, instruments, etc., can solve the problems of difficult large-scale acquisition of face images, difficulties, and large differences in imaging domains, and achieves reasonable design and improved accuracy. rate, the effect of reducing dependence

Inactive Publication Date: 2020-11-20
TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are two problems. On the one hand, it is difficult to obtain such face image pairs of infrared and visible light on a large scale; Requires substantial prior knowledge for accurate conversion
There is enormous difficulty in artificially designing to extract prior knowledge to help achieve this transformation

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
  • Method for converting infrared face image into visible light face image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0020] A method for converting an infrared human face image to a visible light human face image, comprising the following steps:

[0021] Step 1. On the one hand, use the images in the existing infrared face database and visible light face database; on the other hand, use surveillance cameras to collect infrared images of people's faces and visible light face images; construct infrared and visible light face data sets;

[0022] Step 2. Align the images in the face database according to the relative positions of the eyes, and transform them to the same size.

[0023] Step 3, the entire data set is randomly selected and a training data set, a verification data set, and a test data set are in accordance with the relationship of 7:2:1.

[0024] In this embodiment, the size of the face image is 48*64 pixels.

[0025] Step 4. Construct the confront...

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 a method for converting an infrared face image into a visible light face image. The method comprises the following steps: constructing an infrared and visible light face dataset; aligning the images in the face data set according to the relative positions of the eyes, and converting the images into the same size; constructing a training data set, a verification data set and a test data set; constructing an adversarial generative network, and performing network training by adopting a cyclic adversarial generative mode; and generating a transformation network from the infrared face image to the visible light face image. The method is reasonable in design, reduces dependence on supervision data, well solves the problem of conversion from the infrared face image to the visible light face image, can improve the accuracy of infrared face recognition by means of a visible light face recognition method, and can be widely applied to night infrared camera shooting occasions.

Description

technical field [0001] The invention belongs to the technical field of infrared image processing, in particular to a conversion method from an infrared face image to a visible light face image. Background technique [0002] In the existing video surveillance network, it is often required to realize the 24-hour all-weather monitoring function. When the lighting is not good at night, infrared camera becomes a must. Improving the recognition rate of infrared face images has important practical significance for improving the effect of night monitoring. [0003] In order to improve the recognition rate of infrared face images, on the one hand, it is possible to start from infrared face images and conduct in-depth research on recognition methods based on infrared face images; At the middle level, there is still a huge gap compared with the recognition rate of visible light face images. On the other hand, the research on visible light face recognition technology has made the grea...

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): G06K9/00G06T3/00
CPCG06T3/0012G06V40/161G06V40/172
Inventor 任德华赵婷婷柳映辉陈亚瑞吴超何畅
Owner TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
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