Skin Color-Based Frontal Face Detection and Gender Classification

Face detection is necessary for many different applications: face recognition, image database management, etc. In this study, a face detection algorithm is performed on images based on human skin color, and the detected face image is classified based on gender. In this algorithm, three color spaces (RGB, HSV, YCbCr) are used and face detection is performed by combining different thresholds in these three spaces. Outputs of the algorithm are used as feature vectors for the gender classification. The genders in the images are classified with 100% accuracy using the different classification methods.