期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2016
卷号：88
期号：3
出版社：Journal of Theoretical and Applied
摘要：The face is one part of the human body that has special characteristics, which is often used to distinguish the identity of one individual and another. Facial recognition is very important to be developed since this application is applied in the security system. The recognition of sex is one part of the face recognition. Gender plays an important role in our interactions in the community and with the computer. Classification gender of the face image can be applied in the field of demographic data collection, human-computer interface (customize the behavior of software in connection with the sex of the user) and others. The purpose of this study is to make implementation of the system in recognizing the gender on facial image or filling the form with the Gender Recognition face image that is able to recognize a person s sex quickly and accurately, and run well. This study used methods of Two Dimensional Linear Discriminant Analysis (TDLDA) for feature extraction, which directly assess within-class scatter matrix of the transformation matrix without any image into a vector image, and this resolves the singular problem within-class scatter matrix. To obtain optimal recognition results of the classification method, it used the classification Support Vector Machine. This study integrates TDLDA and SVM methods for the introduction of gender based on facial image. The combination of both methods proves the optimal results with an accuracy of 74% to 92% with a test that uses a database of faces taken from http://www.advancedsourcecode.com.
关键词：Support Vector Machine; Two Dimensional Linear Discriminant Analysis; Gender
