DToLIP: Detection and tracking of lip contours from human facial images using Snake's method

Abstract

Lip detection from human front facial image belongs to image segmentation and an essential in many multimedia systems and real time applications such as videoconferencing, speech reading and understanding, face synthesis and facial animation through pronunciations. An efficient and effective detection of the lip contours from the human front facial image is relatively a difficult job in the field of computer vision and image processing due to the variation amongst human faces, lighting conditions and image acquisition conditions. In this paper, Three Phase Method (3PM) for lip detection and tracking from human front facial images is proposed and implemented. In the first phase of this method, the relevant and useful information is retrieved for mouth region from the given front facial image of human being. The second phase deals with detection and tracking of outer and inner lip contours. And the last phase concerns with combining the results of first and second phase of 3PM and findings of extreme control points of lip contours. The driving force behind this proposed method for lip detection and tracking is Snake's method along with image segmentation using RGB colour model and edge detection as the additional forces. The Proposed 3PM gives promising results but still with little inaccuracy in the results of moustache and with images with colour inequality in mouth region and poor illumination effects.