3D face registration based on principal axis analysis and labeled regions orientation

作     者：Guo Zhe Zhang Yanning Lin Zenggang Liu Yantong 

作者机构：Shaanxi Key Lab. of Speech & Image Information Processing School of Computer Science Chang'an Campus of Northwestern Polytechnical Univ. Xi'an 710129 P. R. China 

出 版 物：《Journal of Systems Engineering and Electronics》 (系统工程与电子技术（英文版）)

年 卷 期：2009年第20卷第6期

页      面：1324-1331页

核心收录：

学科分类：080503[工学-材料加工工程] 08[工学] 080203[工学-机械设计及理论] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 080201[工学-机械制造及其自动化] 

基　　金：supported by the New Century Excellent Talents of China (NCET-05-0866) 

主　　题：local orientation registration principal axis analysis label regions orientation iterative closest point. 

摘      要：A novel multi-view 3D face registration method based on principal axis analysis and labeled regions orientation called local orientation registration is *** pre-registration is achieved by transforming the multi-pose models to the standard frontal model＇s reference frame using the principal axis analysis *** significant feature regions, such as inner and outer canthus, nose tip vertices, are then located by using geometrical distribution *** regions are subsequently employed to compute the conversion parameters using the improved iterative closest point algorithm, and the optimal parameters are applied to complete the final *** results implemented on the proper database demonstrate that the proposed method significantly outperforms others by achieving 1.249 and 1.910 mean root-mean-square measure with slight and large view variation models, respectively.