Abstract—In this paper, an improved algorithm to detect faces in images with skin tone regions is proposed. Among the segmented candidate regions, facial edges detected using Canny and Sobel operators on wavelet approximation are suggested as feature set. These features are further classified using a neural-net proposed. Results of the test using the proposed algorithm are compared with those of the previous ones.

Index Terms—Face detection, localization, edge, segment, approximation.

H. C. Vijaylakshmi is with Sri Jayachamaranendra College of Engineering, Mysore. Karnataka, India (e-mail vijisjce@yahoo.co.in)
Sudarshan PatilKulkarni, Scientist, is with JSS Research Foundation, SJCE, Mysore, and Karnataka, India (e-mail pk.sudarshan@gmail.com)

Cite: H. C. Vijay Lakshmi and Sudarshan PatilKulkarni, "Face Detection in Skin-Toned Images Through Wavelet Edges and Neural Network," International Journal of Computer and Electrical Engineering vol. 4, no. 5, pp. 697-700, 2012.