Finger extraction from scene with grayscale morphology and BLOB analysis

Abstract

In this paper, we describe a method to detect human fingers from images captured by a stereo camera. The images captured by the stereo camera are preprocessed by a skin detection module. Two hands are extracted from the skin regions using disparity information. We then apply grayscale morphology and use BLOB analysis to detect fingers and their directions. The method is simple yet powerful for finger detection. This extraction result can be used for posture and gesture recognition tasks in computer vision.