Local Binary Pattern Histogram-Based Gender Classification Using Real AdaBoost

• Main Authors: Yu-KaiTseng, 曾郁凱
• Other Authors: Jenn-Jier Lien
• Format: Others
• Language: en_US
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/63733223508488000465

碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 101 === Gender classification is a hot research topic in recent years, which could be applied to many categories, e.g. electronic advertising, surveillance systems, etc. In this thesis, we present a gender classification system using local binary pattern histogram and Real AdaBoost learning method to create a strong classifier. The strong classifier outputs confidence value which presents the judgments with trust degrees. According to the error between manually labeled inner eye corner points and the eye corner points calculated by Shape Optimized Search algorithm, we present a statistical method to get the reference points which are close to the manually label inner eye corner points. In addition, in order to reduce the noise caused by facial expression changes and face’s small amplitude movements, the output of gender classification is determined by accumulating previous judgment results. The experimental results demonstrate that the system we purposed not only works effectively on single frame but could also applied in real-time systems.