Hand Region Extraction by Background Subtraction with Renewable Background for Hand Gesture Recognition

In order to realize high-precision hand gesture recognition, it is necessary that hand region is extracted correctly from moving image. In this paper, we propose a new hand region extraction method by using background subtraction algorithm. In the proposed method, we introduce the renewal of background image according to the situation of input image. In comparison with thc conventional method, our method is able to extract hand region more accurately and more efficiently. Moreover, the proposed method has been applied to hand region extraction for Japanese sign language, and its validity has been confirmed.