Gender Recognition Based on Facial Features

• Main Authors: Yen-Chun Huang, 黃彥鈞
• Other Authors: Chih-Chin Lai
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/76808899739826120662

碩士 === 國立高雄大學 === 電機工程學系碩士班 === 103 === Determining the gender of a person in a given image or video is an interesting problem. It is an important preprocessing step in many applications such as human-computer interaction, demographic data collection, intelligent surveillance, and customer-oriented advertising. Because human faces contain a variety of useful information, a large number of studies based on facial information have been investigated for gender recognition. In this paper, we present a method which combines a novel texture descriptor called local zigzag pattern and the gradient direction pattern for feature extraction to identify the gender from the facial images. The recognition is performed by using a support vector machine. Experimental results on the FERET, BioID, LFW, and CAS-PEAL-R1 databases are provided to illustrate the proposed approach is an effective method, compared to other similar methods.