Stereo Vision을 이용한 얼굴 인식 및 추적 시스템 알고리즘

Abstract

In this paper, a method for face detection and tracking system using stereo vision is described. For the extraction of the object from the background of the acquired image, haar-like feature algorithm is used. This system is based on the use of stereo vision digital camera named as "Bumblebee". Two different methods for the vision systems are discussed in this paper. The first system is human face detection and tracking system for the stereo camera using haar-like feature algorithm. The second system is a calculation of the object distance from the stereo camera using the disparity planes. Finally., we evaluate our method by experimental studies of the pictures acquired from a real stereo camera.