The Fast Integration of a Rotated Haar-Like Feature for Face Detection
Mohamed Oualla · International Journal of Advanced Trends in Computer Science and Engineering · 2020
This paper addresses the problem of detecting rotated human faces in images.We propose a new face detection approach based on a novel extension of rotated Haar-like features, and a method to calculate their values based on the Bresenham algorithm of drawing a segment.The extension of the basic set of features, proposed by Viola and Jones, is done by the generation of a set of rotated Haar-likefeatures, by any angle, in an image.For the feature's integration process, we calculate the value of a rotated feature using the integral image technique, proposed by viola and jones.The main objective of this article is to propose a method to calculate the integral image of a rotated feature; we introduce the concept of key points that forms the four segments of a rotated rectangle.Our method focuses on three essential tasks; the first is to determine the rule for drawing a segment (SDR), the second is to identify all the key points of the rectangle r, and the third is to calculate the integral image.The speed of this method depends on the size and angle of rotation of the rectangle.Experimental results obtained using images from the MIT-CMU dataset are promising in terms of detection rate and the false alarm rate in comparison with other competing algorithms.