Face Tracking Search And Implementation Based On Embedded Mobile Platform

With the development of the smart phones, PDA, and all kinds of mobile terminals carrying embedded operating system, the face tracking technology in the mobile platform become a hotspot once again. This paper proposes a fast face detection method based on skin detection, morphological operation and contour extraction to overcome the disadvantage of the traditional Adaboost face detection way. The experimental results prove that the method has quicker speed in keeping high detection rate. Not only focusing on theory but also in Practical application, this face detection method has applied to Android mobile platform. The face tracking Program which is designed based on this method is running well in numbers of Android smart phones. The detection frame number is up to21frames per second. We completed the real-time tracking face requirements. Test results show that, this program has good detection effect in the images which contain more faces. In addition, this article describes the design and implementation of the face tracking system in the Android platform in detail, also introduced simply in Windows mobile and MTK platform of transplant process.