Face Detection Using Rotated Asymmetric Haar Features
Mohamed Oualla, Abdelalim Sadiq · 2017
We have obtained encouraging results in our previous work which consists in feeding the group of Haar-like features created by Viola and Jones by others rotated by any angle. This motivated us to re-feed this group of features by others which are asymmetric. To test the performance of this method, we used the two UMIST and CMU-PIE bases of images, which are among the most widely used in the field of face detection and recognition.