Hand shape recognition

Automated hand shape recognition has been studied over the past decade and some commercial systems have been developed. Despite these advances, there is not much open public literature discussing the hand shape verification r esearch. This study proposes a method by using quadtree techniques, which a re able to recognize the hand shape image within an extremely short time. T he geometrical shape of a hand is a biometric characteristic of human bring s, although it is different even for :a twin sibling, This study uses paral lel grating to project onto the backside of a hand. The parallel grating wi ll be distorted by the curvature shape of the hand and processed by image p rocessing techniques for recognition. This study also presents our recognit ion results of 100 students captured over a period of time. (C) 2000 Elsevi er Science Ltd. All rights reserved.