Face Recognition Using Facial Feature Based on Decision Method

• Main Authors: Pei-Yuan Chu, 朱培源
• Other Authors: Jyi-Chang Tasi
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/56388276463917342120

碩士 === 義守大學 === 資訊管理學系 === 101 === Face recognition application has penetrated all levels, such as access control systems, smart appliances and robot recognition. Commonly used face recognition method includes principal component analysis, linear discriminant analysis and facial features analysis method. Facial features to recognize faces mainly uses relative size of facial shape and location characteristics to identify whether their identification is a critical success factor lies in the accuracy of facial shapes made, how to choose a good number of features and how to combine the characteristics of the last and with the appropriate decision rule. Basically, there are many facial features can be selected, so how to assemble features and establish decision rules becomes very important. The thesis proposes a new set of decision rules used in facial feature. In the thesis, the characteristics of the initial selection are 32 features, and this similarity lowest images are eliminated by taking advantage of the 32 features, the images with different expressions or other images from different angles with the same person are also eliminated by using the images mentioned above. Finally, it selects a valid combination among the 32 characteristic features and decides the higher probability candidate images through the statistics method and calculation of deviation. Experimental results showed that if we only select one candidate image, correct judgment of the proposed method is about 90% in this thesis. If the candidate selected four images, the correct judgment was 100%.