Presentation 2004/3/10
Development of Noncontacting Real-time Blink Detection System by Measuring the Area of Iris
Tomofumi MIYAKAWA, Hironobu TAKANO, Toshihiro NOJIRI, Kiyomi NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Doze is the state in which the consciousness level falls owing to lack of sleep, fatigue, illness, etc. If drivers are in a doze state during driving, it leads to the serious accident. Therefore, in order to prevent the accident caused by the doze operation, it is needed to detect the doze state at an early stage and to warn drivers. When the consciousness level falls, several changes appear, i.e., the number of blinks increases and the closed eye time becomes long. In this study, we developed a real-time blink detection system aiming for application to the noncontacting doze detection system from the change of blinks. Further, we developed an electroencephalogram-eye blink correlation analysis system in order to investigate the relation between the consciousness level and blinks. The grayscale picture was converted into the binary image. The area of the iris was measured using the eye positional information obtained by the partial eye template matching method. The eye blink was judged when the area of the iris became below threshold. The present system detected blinks noncontacting and real-time, and measured the number of blinks and closed eye time.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Blink / Closed eye time / Real-time detection / Non-contact type
Paper # MBE2003-138
Date of Issue

Conference Information
Committee MBE
Conference Date 2004/3/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To ME and Bio Cybernetics (MBE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development of Noncontacting Real-time Blink Detection System by Measuring the Area of Iris
Sub Title (in English)
Keyword(1) Blink
Keyword(2) Closed eye time
Keyword(3) Real-time detection
Keyword(4) Non-contact type
1st Author's Name Tomofumi MIYAKAWA
1st Author's Affiliation Graduate School of Engineering, Toyama Prefectural University()
2nd Author's Name Hironobu TAKANO
2nd Author's Affiliation Graduate School of Engineering, Toyama Prefectural University
3rd Author's Name Toshihiro NOJIRI
3rd Author's Affiliation Toyama Industrial Technology Center
4th Author's Name Kiyomi NAKAMURA
4th Author's Affiliation Graduate School of Engineering, Toyama Prefectural University
Date 2004/3/10
Paper # MBE2003-138
Volume (vol) vol.103
Number (no) 730
Page pp.pp.-
#Pages 6
Date of Issue