使用GLBP-TOP方法从多视角进行动态生物特征识别。
Dynamic biometric identification from multiple views using the GLBP-TOP method.
作者信息
Wang Yu, Shen Xuanjing, Chen Haipeng, Zhai Yujie
机构信息
College of Computer Science and Technology, Jilin University, Changchun 130012, China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin 130012, China Applied Technology College Jilin University, Changchun 130012, China.
College of Computer Science and Technology, Jilin University, Changchun 130012, China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin 130012, China.
出版信息
Biomed Mater Eng. 2014;24(6):2715-24. doi: 10.3233/BME-141089.
To realize effective and rapid dynamic biometric identification with low computational complexity, a video-based facial texture program that extracts local binary patterns from three orthogonal planes in the frequency domain of the Gabor transform (GLBP-TOP) was proposed. Firstly, each normalized face was transformed by Gabor wavelet to get the enhanced Gabor magnitude map, and then the LBP-TOP operator was applied to the maps to extract video texture. Finally, weighted Chi square statistics based on the Fisher Criterion were used to realize the identification. The proposed algorithm was proved effective through the biometric experiments using the Honda/UCSD database, and was robust against changes of illumination and expressions.
为了实现具有低计算复杂度的有效且快速的动态生物特征识别，提出了一种基于视频的面部纹理程序，该程序从伽柏变换（GLBP-TOP）频域中的三个正交平面提取局部二值模式。首先，通过伽柏小波对每个归一化面部进行变换以获得增强的伽柏幅度图，然后将LBP-TOP算子应用于这些图以提取视频纹理。最后，基于Fisher准则的加权卡方统计用于实现识别。通过使用本田/加州大学圣地亚哥分校数据库进行的生物特征实验证明了所提出的算法是有效的，并且对光照和表情的变化具有鲁棒性。
Zotero 插件