Aging simulation using facial muscle and bimode model

• Main Authors: Chien-Hsun Tu, 杜建勳
• Other Authors: Shin-Feng Lin
• Format: Others
• Language: en_US
• Published: 2011
• Online Access: http://ndltd.ncl.edu.tw/handle/88200136852522726119

碩士 === 國立東華大學 === 資訊工程學系 === 99 === Recently, the techniques of face recognition have been widely used in security application such as security monitoring, and access control. However, there are still some problems in face recognition system which the light changes, expression changes, head movements, accessory occlusion and aging effect are the main issues. For the aging effect, the shape and texture change degrades the performance of face recognition system. Our goal is to come up with a representation that is robust to changes due to facial aging. Therefore, there are many algorithms focusing on how to simulate face image. In this thesis, the modeling of face image is an important procedure for aging simulation. We propose an aging simulation scheme. Based on the facial muscle model, our scheme also applies bimode model which can estimate the geometric and texture variation of a target age from subspace of age groups. Finally, the PCA is applied to face recognition system. The simulating results presented in the thesis are compared with the ground truth image of the same person. Experimental results show that the proposed aging simulation scheme is able to improve performance of face recognition system.