期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2014
卷号：3
期号：4
页码：1345-1352
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Naturally before recognizing a face, it m ust be located in the im age. In some cooperative systems, face detection is obviated by constraining the user. Most systems use a combination of skin-tone and face texture to determ ine the location of a face and use an im age pyramid to allow faces of varying sizes to be detected. Increasingly, system s are being developed to detect faces that are not full frontal. This paper proposes a design to detect faces in real tim e using hog descriptor. Taking HOG of the image and calculate the weights which contributes for the facial features. Positive weights with facial features like eyes, nose, and mouth are m arked com pletely to visualize a face. This algorithm continuously detects the face from +90 0 to -90 0 rotations even for occluded faces with high detection rate.
关键词：Face detection; Face recognition; Facial ; feature; HOG descriptor; Face visualization
