Low Resource Lip Finding and Tracking Al

One of the best challenges in Lip Reading is to apply this technology to an embedded device. In the current solutions the high use of resources, especially in reference to visual processing, makes the imple-mentation in a small device very difficult. In this article a new, efficient and straightfor-ward algorithm for detection and tracking of lips is presented. Lip Finding and Tracking is the first step in visual processing for Lip Reading. In our ap-proach the Lip Finding is performed between a small amount of blobs, which should fulfill a geometric restriction. In terms of computational power and memory the proposed algorithm meets the require-ments of an embedded device; on average less than 4 MHz1 of CPU is required. This algorithm shows promising results in a realistic environment accom-plishing successful lip finding and tracking in 94.2% of more than 4900 image frames. 1