Abstract: Human face detection plays a very important role in various biometric applications like crowd surveillance, photography, human-computer interaction, tracking, automatic target recognition, artificial intelligence and many other security applications. Varying illumination conditions, color variance, brightness, pose variations affect face detection. So, automatic face detection and recognition is a challenging concept which has attracted much attention due to its many applications in different fields. Face detection still poses a problem and up to now, there is no technique that provides a robust solution to face detection in all situations. There are many techniques for face detection, but skin color based technique is most popular as it is simple, robust and processing color information is much faster than processing any other facial features. So this paper proposes a novel algorithm foe face detection using multi-color space based skin segmentation and region properties. First, skin regions are segmented from an image using a combination of RGB, HSV and YCgCr color models using thresholding concept. Then facial features are used to locate the human face based on knowledge of geometrical properties of human face by testing each segmented skin region. Experimental results are used to show that, our proposed algorithm is robust enough to achieve approximately 96% accuracy and can locate a face in both single and multiple face images. The proposed method has also a good performance on images with complex background and can detect faces of different sizes, poses and expressions under different environmental conditions.
Keywords: face detection, skin color segmentation, RGB, HSV, YCgCr, Sobel edge detector.