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

Near infrared eye positioning and eye state identification method

An eye state and eye positioning technology, applied in character and pattern recognition, image data processing, instruments, etc., can solve problems such as inability to guarantee robustness, performance degradation, image noise increase, etc., to meet real-time requirements, hardware The effect of low cost and improved robustness

Inactive Publication Date: 2014-10-08
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the iris disappears in the near-infrared eye image, and the image noise increases, which is quite different from the image under the natural spectrum. In the actual application environment, the reflection of the glasses, opening and closing of the eyes, and head rotation make the existing eye positioning and eye status The performance of recognition algorithms has dropped significantly, and the use of a single feature or positioning method cannot guarantee robustness in all application environments

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
  • Near infrared eye positioning and eye state identification method
  • Near infrared eye positioning and eye state identification method
  • Near infrared eye positioning and eye state identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The specific implementation of the present invention will be further described below in conjunction with the accompanying drawings. The following is only one implementation of the present invention, and its specific step sequence and content are not intended to limit all feasible implementations of the present invention.

[0041] combine figure 1 , a near-infrared eye positioning and eye state recognition method of the present invention, the specific implementation is as follows:

[0042] Step 1: Train an eye cascade classification detector based on Haar features, and collect an appropriate amount of near-infrared eye images through an image acquisition system combined with an 850nm active near-infrared light source and a narrow-band filter, including eyes open and closed, including eyebrows And eye images are used as positive samples, non-eye images are used as negative samples, and the eye cascade classification detector based on Haar features is trained by Adaboost 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 near infrared eye positioning and eye state identification method, belongs to the field of image processing and mode identification, and is applied to driver fatigue detection and visual line tracking. The method involves, first of all, performing face positioning on an input near infrared image, then positioning an eye area by use of an near infrared eye positioning algorithm based on a cascade structure, and finally determining an eye state by use of an eye state identification algorithm based on HOG-LBP characteristic fusion. The method can robustly position two situations, i.e., eye opening and eye closing under an infrared condition and accurately identify the eye state. At the same time, the calculation complexity is not high, and the real-time performance is satisfied.

Description

technical field [0001] The invention belongs to the field of image processing and pattern recognition, and in particular relates to a method for near-infrared eye positioning and eye state recognition. Background technique [0002] Eyes are an important part of facial biometric recognition, so the precise location information and eye status of eyes are widely used in intelligent systems such as driver fatigue detection and eye tracking. [0003] According to the features and models adopted by the eye localization method, it can be divided into the following three categories: [0004] The first category is the positioning method based on the appearance features of the eye, such as the inherent shape of the eye, the gray distribution of the pupil, iris and white of the eye, and the bright pupil effect. This type of positioning method relies on good imaging conditions. In the driving environment, it is necessary to overcome many uncontrollable conditions such as illumination, ...

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): G06K9/00G06K9/62G06T7/00
Inventor 秦华标刘军仝锡民
Owner SOUTH CHINA UNIV OF TECH
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