Robust and Real Time Human Face Detection and Tracking Using Skin Segmentation, Template Matching and Kalman Filter

Face detection and tracking find applications in areas like video structuring, indexing, and visual surveillance and form active areas of research. This paper presents a robust algorithm for human face detection and tracking against picture and other objects. It is based on motion information, skin color detection, morphological operation and template matching. In the first step, foreground detection is performed using background subtraction algorithm and applying Kalman filter for motion segmentation. Then skin color segmentation is performed on the foreground segmented regions using statistical models. It results in a mask marking the skin color regions in the real frame which is further used to compute the position and size of the dominant facial region. To speed up the tracking process, system does not search the entire frame for the potential face regions. This means that we can quickly determine a good approximation of the search region corresponding to face location. Finally, the current template can dynamically be updated in size and content to adapt to temporal changes of the tracked face’s scale and orientation. Moreover, a confidence measure representing the template’s reliability is presented to guide possible template re-initialization for continuous face tracking. The proposed face detection and tracking method achieves high performance, robustness to illumination variations and geometric changes (such as viewpoint and scale changes) and at the same time entails a significantly reduced computational complexity.

Robust and Real Time Human Face Detection and Tracking Using Skin Segmentation, Template Matching and Kalman Filter Keywords:

Face detection , Foreground segmentation , Skin segmentation , Template matching , Kalman Filter , Tracking