Intelligent music player based on human motion recognition

Abstract

In this paper, an intelligent music player system based on computer vision is proposed. We present an improved method for skin color area detection and segmentation based on YCbCr and HSI mixed skin color space. Then we use the Adaboost learning algorithm to obtain the face detector based on the Haar wavelet transform with in skin color region and receive the location of eyes and mouth. The frame subtraction algorithm is used to achieve position of hand motion, we used CAMSHIFT algorithm to track the motion trajectory and estimate the center of hand, which used for controlling the Music Player. Afterwards, the system will recognize the hand motion by calculating the relationship between the mouth location and the position of hand area in real time. Therefore, experimental results illustrate this intelligent music controlling system has satisfying interactive input functions in real time, and it can be applied in different illumination condition and complex background well. © 2011 Springer-Verlag.