Hand Mouse: Real Time Hand Motion Detection System Based on Analysis of Finger Blobs
İbrahim Furkan İnce, Manuel SocarrasGarzon -, TaeCheon Yang - · International Journal of Digital Content Technology and its Applications · 2010
Hand detection is a fundamental step in many practical applications as gesture recognition, video surveillance, and multimodal machine interface and so on. The aim of this paper is to present the methodology for hand detection and propose the hand motion detection method. Skin color is used to segment the hand region from background and hand blob is extracted from the segmented finger blobs. Analysis of finger blobs gives us the location of hand even when hand and head blobs are visible in the same image. In this paper, we propose a fast, computationally inexpensive solution which uses any type of computer video camera to control a cursor through hand movements and gesticulations. The design and evaluation phases are presented in detail. We have performed extensive experiments and achieve very encouraging results. Finally, we discuss the effectiveness of the proposed method through several experimental results.