| 基于二维、三维信息融合的人脸识别 |
| |
| 引用本文： | 孙艳丰,张扬,唐恒亮.基于二维、三维信息融合的人脸识别[J].北京工业大学学报,2011,37(6):928-932. |
| |
| 作者姓名： | 孙艳丰 张扬 唐恒亮 |
| |
| 作者单位： | 北京工业大学,计算机学院,北京1000124;北京工业大学,计算机学院,北京1000124;北京工业大学,计算机学院,北京1000124 |
| |
| 基金项目： | 国家自然科学基金资助项目(60533030); 国家科技支撑计划资助项目(2007BAH13) |
| |
| 摘 要： | 为解决光照、姿态等因素发生变化时二维人脸识别算法识别率骤然下降的问题,提出了基于二维、三维信息融合的人脸识别方法.与其他算法不同,该算法输入为一幅二维灰度图像,通过重建相应的三维模型提供三维信息.对于二维图像,选择局部二值模式(LBP)特征进行人脸表示.对于三维模型,定义了54个特征点,将鼻尖点与特征点之间的测地线距离作为三维特征.对2种特征识别结果采用加权融合的方式,权值的确定依据Fisher判别准则.通过CAS-PEAL-R1人脸库对提出的算法进行了测试,并与其他方法进行了比较.
|
| 关 键 词： | 信息融合 局部二值模式 测地线距离 人脸识别 |
Face Recognition Based on Fusing 2D and 3D Information |
| |
| SUN Yan-feng,ZHANG Yang,TANG Heng-liang.Face Recognition Based on Fusing 2D and 3D Information[J].Journal of Beijing Polytechnic University,2011,37(6):928-932. |
| |
| Authors: | SUN Yan-feng ZHANG Yang TANG Heng-liang |
| |
| Affiliation: | SUN Yan-feng,ZHANG Yang,TANG Heng-liang(College of Computer Science,Beijing University of Technology,Beijing 100124,China) |
| |
| Abstract: | Most recognition algorithms are for 2D data with strict restrictions,these algorithms are easily affected by pose,illumination and other factors.The reason is due to the shortage of information.To resolve this problem,we present a face recognition algorithm based on fusing 2D and 3D information.Being different from other algorithms,the input of our algorithm is one single 2D gray-scale image and 3D information is provided by reconstructed the 3D model.For the 2D image,we choose LBP feature as face represent... |
| |
| Keywords: | information fusion local binary pattern(LBP) geodesic distance face recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
