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

Robust infrared face recognition technology

An infrared human and face recognition technology, applied in the field of robust infrared face recognition, can solve problems that do not conform to the heat transfer principle of biological tissues, achieve high theoretical research significance and practical application value, improve accuracy, and stabilize blood flow biological characteristics Effect

Inactive Publication Date: 2010-07-28
JIANGXI UNIVERSITY OF FINANCE AND ECONOMICS
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this model is based on several ideal assumptions, and it is believed that there is no correlation between the temperature points of the human face, which does not conform to the heat transfer principle of biological tissues

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
  • Robust infrared face recognition technology
  • Robust infrared face recognition technology
  • Robust infrared face recognition technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as Figure 5 Shown, the technology of the present invention comprises the following steps:

[0048] 1. Collect images, perform face detection, geometric normalization, and face direction detection on the images.

[0049] Firstly, the database is collected, and what is used is the ThermoVisionA40 infrared camera produced by FLIR. The camera uses an uncooled microbolometer sensor with a pixel resolution of 320 x 240 and a spectral response band of 7.5 to 13 microns. In order to accurately measure the surface temperature of the measured object, the device has a temperature self-calibration function to eliminate temperature drift. Its temperature sensitivity is as high as 0.08°C. The original infrared face image such as figure 1 shown.

[0050] Assuming that the skin temperature of the human face is higher than the temperature of the environment, the human face can be easily detected from the infrared image. Assuming that f(x, y) is the original face image, and a...

Embodiment 3

[0111] like Image 6 As shown, after preprocessing and geometric normalization of the infrared face image, the image is first normalized by 0-1. The value obtained by 0-1 normalization is used as the weight of the point on the face that changes with temperature. Then extract the state parameters in the image, and use the lowest value in the image as the ambient temperature value when the image is collected. Finally, the temperature difference between the image and the image in the standard environment and the obtained weight are used to normalize the temperature of the image. The normalized image can better reduce the influence of the ambient temperature on the image. Embodiment 3: as Figure 7 and 8 As shown, after temperature normalization of the image, based on the classic Pennes biological heat transfer equation in the biological heat transfer model, we converted the infrared face image into a discrete blood flow map through discretization modeling. The discrete blood ...

Embodiment 4

[0113] like Figure 10 As shown, first, the first PCA+FLD feature extraction is performed on the total training samples (assuming there are M samples). Then, the first PCA+FLD feature extraction is performed on the test samples. Recognition is performed based on the extracted features, sorted according to the size of the Euclidean distance, and the first N (where N<M) samples are taken out to obtain secondary samples. Finally, PCA+FLD feature extraction is performed on the secondary sample, and the test sample is recognized in the new feature space, and the class with the closest distance is the final recognition result.

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 robust infrared face recognition technology. The technology comprises the following main links: first, detecting a face in an image, estimating the direction of the face, and geometrically normalizing the face; then, calculating the weight along with temperature changes of each point in the face image, and converting images at the different temperatures into an image at the reference temperature by using a linear normalization method; and finally, solving the temperature normalized image to acquire a corresponding discrete rheography by using a Pennes biological heat transmission equation so as to acquire a more robust biological characteristic, and recognizing the face by adopting a secondary characteristic extraction method. Experiments prove that the technology can greatly improve the recognition rate of delay data, can be used in a real-time infrared face recognition system, and has high theoretical studying significance and practical application value.

Description

technical field [0001] The invention relates to a robust infrared face recognition technology, in particular to a temperature normalization method and a blood flow diagram-based recognition method. Background technique [0002] The idea of ​​using infrared for face recognition was first proposed in 1992 by Dr. Prokoski of Mikos Corporation in the United States. In addition to the above-mentioned characteristics of infrared face images, Dr. Prokoski further pointed out that the human face thermogram is determined by the infrared thermal radiation of the tissue and structure of the face, such as the size and distribution of blood vessels, and the distribution of blood vessels of each person is Unique, non-replicable, and this characteristic does not change with age, so they are related to human physiological structure like fingerprints and are unique. [0003] In recent years, a few countries such as the United States, Japan, Israel, Singapore and my country have successively...

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): G06K9/00
Inventor 伍世虔谢志华卢宇方志军
Owner JIANGXI UNIVERSITY OF FINANCE AND ECONOMICS
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