Face Detection Using Fuzzy Logic and Skin Color Segmentation in Images

Abstract

Face detection is one of the challenging problems in image processing. A novel face detection system is presented in this paper and we propose a new approach using Takagi-Sugeno (T-S) fuzzy model and Hue Saturation and Value (HSV) color model. The algorithm uses fuzzy classifier in conjunction with HSV color model to quickly locate faces in the image. The fuzzy classifier basically examines small windows of an image to detect presence of faces in that window and the HSV color model detects the skin in the image. The algorithm is characterized by its simplicity and inexpensive computational requirements. The method shows that our system has comparable performance in terms of detection rates and false positive rates.