Comparison of two different approaches for multiple face detection in color images

Abstract: Human face detection has become a major field of interest in current research because there is no deterministic algorithm to find multiple faces in a given image. In this paper, the performance comparison has been made of two different algorithms for multiple face detection in color images. First algorithm combines HSI and YCbCr color models along with morphological operations. In the second algorithm, RGB color model with Viola-Jones algorithm is used. After making comparison, it is found that; first algorithm gives better detection accuracy (91%) as compared to the second method (88%). But, first algorithm requires more processing time which is matter of concerned in real-time face detection. The average processing time required for first algorithm is about 6.3sec, whereas for second algorithm it is 5.1sec.

Keywords: Color models, Multiple Face Detection, Morphological Operations, Viola Jones