|
概要（日本語）
|
Even in noisy environments such as in machinery factories or in crushes, it is hard to communicate with machinery equipments such as industrial robots. In such cases, lip shape movements are expected as excellent information to improve the performance of word recognitions. In this paper, a method to extract lip shapes from face images by using Active Contour Models is proposed. Normalization to reduce the effect of the lip size change depending on the distance from a camera to human faces is mentioned. A three-hierarchy Neural Network is used for the recognition method. The proposed method is implemented as hardware circuits in a FPGA chip. Experimental results of vowel recognition are shown to confirm effectiveness of the proposed method.
|