Face Recognition Technology based on Kalman Filter
Download as PDF
In this paper, a combination of basic Haarlike features proposed by Viola-Jones an extended set of Haarlike features proposed by Lienhart et al will be researched and implemented in the face detection phase using matlab and a set of proposed rules for Adaptive Boosting(Adaboost). Followed by a method of Lip Localization using YCbCr colourspace, lip contour estimation with the Van-Chese method of active contours without edges and tracking using kalman filter algorithm. The significance of the item is that it can be applied to human-computer interaction, security and surveillance, video communication and compression, medical imaging, video editing and robot vision applications. This paper can also serve as groundwork for future research into automatic lip reading systems which may allow it possible for an application to know what one is saying in a video simply by reading their lips.
Lip movement, Face recognition, Pattern recognition, Computer vision, Human computer interaction