Gender Recognition Based on Edge Histogram
Abbas Roayaie Ardakany, Ai La · International Journal of Computer Theory and Engineering · 2012
In this paper, we present a novel method to gender classification using a new simple feature extraction which extracts geometric and appearance features at the same time.This feature extraction is performed by computing the derivative in all pixels of face images and then constructing a histogram based on edges magnitudes and directions.The experiments clearly show that the presented method is quite competitive with 95.67% accuracy on FERET database.In addition, the efficiency of the proposed method makes it a good choice for real-time systems which combine face detection and gender classification.