An Efficient Algorithm for Face Detection Using Color Segmentation & Energy Thresholding

In this paper we presented a simple and effective method to detect faces in such a situation that the images to be tested are very similar to the images in a training set, by using color-based segmentation. Color segmentation is an effective process to separate skin from its background. The color segmentation process will be followed by energy thresholding. Face detection has been a fascinating problem for image processing researchers during the last decade because of many important applications such as video face recognition at airports and security check-points, digital image archiving, etc. In this paper we attempt to detect faces in a digital image using various techniques such as skin color segmentation, morphological processing, template matching, We determined that the more complex classifiers did not work as well as expected due to the lack of large databases for training. Reasonable results were obtained with color segmentation, template matching at multiple scales, and clustering of correlation peaks.