Theory of evidence for face detection and tracking
International Journal of Approximate Reasoning
| Hi-index | 0.00 |
In this paper an improvement of the performance for detecting faces in color images is proposed. This improvement is achieved by integrating the AdaBoost learning algorithm with skin color information. Firstly, the system searches the entire image for face candidates by skin color segmentation and morphological operations, then a powerful feature selection algorithm, AdaBoost is performed to automatically select a small set of features in order to achieve robust detection results, the final face regions are obtained via scanning these face candidates using the cascaded classifier, which is constructed by AdaBoost algorithm.The complete system is tested on a variety of color images and compared with other relevant methods. Experimental results show the proposed system obtains competitive results and improves detection performance substantially.