A Feature-Based Gender Recognition Method Based on Color Information

Abstract

In the paper, we proposed a gender recognition scheme based on color information. The proposed gender recognition scheme is comprised of four parts: face detection, eye detection, feature extraction, and gender classifier. To evaluate the proposed scheme, a large number of images containing different-size faces are captured by using low-cost web cam. Experimental results show that our proposed scheme can detect facial regions as well as eyes well. In addition, the classification rate of our gender recognition scheme is more than 80%. These results demonstrate that our proposed scheme can achieve not only face and eye detection but also gender recognition.