Sept. 27, 1999 to Sept. 29, 1999
In this paper, a new fast method for detecting human faces in color images using wavelet transform is proposed. The face detection algorithm has three stages, where chrominance, shape and frequency information are used respectively. The algorithm starts at the lower resolution version of the image obtained from the wavelet transform, so that the amount of data to be processed is greatly reduced. Experimental results show that the human face in color images can be detected regardless of orientation.
Jayashree Karlekar, U.B. Desai, "Finding Faces in Color Images Using Wavelet Transform", ICIAP, 1999, Image Analysis and Processing, International Conference on, Image Analysis and Processing, International Conference on 1999, pp. 1085, doi:10.1109/ICIAP.1999.797744