Anti-Counterfeiting System of Drunk Driving Using Driver's Facial image Identification

Abstract

This study proposes an anti-counterfeiting system of drunk driving, which prevents drivers from drunken driving and cheat of driver's alcohol detection. The study develops the technology of driver's facial image match by a serial image processes. The methodology of facial image match uses the Adaboost algorithm, Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) to extract the facial features of drivers, is suitable to be applied under the internal environments of cabin. By analyzing the facial features of drivers, the time of driver's exchange is detected, and the driver's identity is indentified. When the cheat act of driver's alcohol detection occurred, the system will generate warning signals through a buzzer to notice the driver to take alcohol detection. The system detected the time of driver's exchange effectively, and indentified different driver's identity successfully, the accuracy rate of ORL face database is 96.25 %, the accuracy rate of ARTC driver's face database is 100.00 %. This system has been implemented on low-cost DSP platform and it can be installed efficiently on varied kind of vehicles. The study will be implemented on the vehicle to verify the reliability of the technology in the future.

Driver Voice Identification System Using Auto-Correlation Function and Average Magnitude Difference Function

“…Currently, biometric technology is developing rapidly and the physiological characteristics used for this include: fingerprints [1], the face [2], iris, retina, hand-geometry, palm, finger-vein, ear-shape, voiceprint, and DNA. In addition, the behavioral characteristics used include: signatures, keyboard typing, and others.…”