Abstract:
Face detection is concerned with determining whether or not face(s) is present in an image or image sequences. In this work a face detection algorithm capable of detecting face(s) without prior training as a face classifier was developed. The procedure is based on skin segmentation and facial feature extraction of the two eyes and mouth. Skin segmentation was done in the red, green, blue (RGB) colour space. White balance correction was adopted to correct the change in image temperature that occurs due to change in lighting conditions at the point of acquiring image. Morphological operations and bounding box was adopted to search and extract face region from the segmented skin region. Facial feature, eyes and mouth, were extracted for final verification of
the found face using the Laplacian of Gaussian (LoG) filter and the isosceles triangle matching rules. The extracted features were used to develop the face detection algorithm. The developed algorithm was tested using random images taken under different lighting conditions. The efficiency of the algorithm was evaluated using a standard face detection image database. The result obtained shows that the developed algorithm performed satisfactorily well with 81.37% detection accuracy. Furthermore, the computational time of the developed algorithm was compared with other algorithms in literature. The result showed that it had a lesser computational time of 2.46sec. The developed algorithm is capable of detecting face(s) without prior need of training with less computational complexity
