Face Recognition Based on AAM Attitude Alignment
In the unconstrained environment, face recognition results can be seriously affected by the inner and outer factors such as expression, attitude, light conditions and background. Active Appearance Model (AAM) can build the priori model with shape and texture information to synthesize new face images. In this paper, the shape model of AAM, which can expresses the variation of face attitude, is removed so that the face images are aligned to new synthesized images without the attitude influence. By improving AAM, we reduce some inner and outer effects on recognition process, and the attitude changes especially can be removed. Face recognitions based on Standard Model Features (SMFs) with SVM is carried on IMM database. Experiment results indicate that the recognition for face images aligned by AAM gets a better recognition rate.
face recognition active appearance model attitude alignment feature extraction
Yan Bian Heng Zhao Peng Yu
School of Electronic Engineering, Xidian University, Xian, Shaanxi, China School of Life Sciences and Technology, Xidian University, Xian, Shaanxi, China
国际会议
哈尔滨
英文
312-316
2012-05-19（万方平台首次上网日期，不代表论文的发表时间）