Face detection using neural networks with skin segmentation

Detecting faces in images remains a challenge in image processing and is currently an active area of research. A frontal face detection algorithm is presented in this paper. Skin colors were used to initially detect possible faces in the image. Using a search window, possible faces are processed using edge detection. These are then classified as faces or non faces using an artificial neural network classifier. The algorithm was tested in images with varying sizes and number of faces. Results from experiments demonstrate successful face detections. Ideas for future work are also included to close the paper. © 2011 IEEE