Blink duration measurement system for drowsiness detection using image processing

ABSTRACT Support systems for automobile drivers have been recently developed. One support system prevents drivers from sleeping at the wheel, but an adequate system has not yet been commercialized. Many reports say that when a driver is drowsy, the blinking duration tends to be long. So, we propose a method to prevent drivers from sleeping by detecting the blinking duration. Because this method only uses simple image processing, the algorithm is not complex. The algorithm involves face localization, then eye localization, followed by measurement of the blinking duration. We tested our system on a number of frames, and the correct blinking duration was usually detected. Keywords: eye detection, blink, drowsiness detection 1. INTRODUCTION According to the Japan Automobile Manufacturers Association, about 95,000 car accidents occurred in 2003 in Japan, and about 56% of these accidents were due to the driver’s low level of attention. Therefore, it is important to detect a driver’s attention level and to warn any driver with a low attention level in order to prevent car accidents. To detect a driver’s attention level, we must monitor both visual attention and drowsiness