期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于球面调和函数的3-D人脸识别方法

3-D Face Recognition Method Based on Spherical Harmonics
下载PDF
导出
摘要 根据3-D数据的优势,利用图像成像原理和球面调和函数理论,结合3-D投影原理和PCA技术建立了一个3-D人脸模型。该模型用不受光线影响的低维线性子空间的基向量来表示,将结构和纹理两个3-D信息作为整体进行考虑,使得模型只需要通过一组参数简单描述。由于本文构建的3-D模型只与人脸的内在属性有关,与光线无关,因此能够排除光线对人脸识别率的影响,本文在AR人脸数据库上的识别实验证明了本文方法的有效性。 The accuracy of 2-D face recognition methods is affected by lighting. A novel method is proposed according to the ascendancy of 3-D face data. A 3-D face model is constructed by the imaging theory and spherical harmonics, combining with the principle of 3-D projection and PCA. The model combines two 3-D parameters of the shape and the texture as a whole. And the model is represented by harmonic vectors in low-dimensional linear subspaces. In this way, the model can be simply described by one set of parameters. The 3-D model is invariant with the illumination because it is only determined by physical characteristics of human faces. The experiment on AR face database shows that the method is effective.
作者 丁晓宇 邓娜 马争鸣
机构地区 华南农业大学工程学院 中山大学电子与通信工程系
出处 《数据采集与处理》 CSCD 北大核心 2009年第5期632-637,共6页 Journal of Data Acquisition and Processing
基金 广东省科技计划基金(2004B10101031)资助项目 珠海市科技计划基金(PC20051017)资助项目
关键词 人脸识别 球面谐波 3-D人脸模型 PCA face recognition spherical harmonics 3-D face model PCA
分类号 TP391.41 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献13

  • 1Zhao W, Chellappa R, Phillips P J, et al. Face recognition: a literature survey[J]. ACM Computing Surveys, 2003,35 (4) : 399-458.
  • 2Donikian M, Walter B, Bala K, et al. Accurate direct illumination using iterative adaptive sampling [J]. IEEE Trans on Visualization and Computer Graphics, 2006,12 (3): 353-364.
  • 3Diplaros A, Gevers T, Patras I. Combining color and shape information for illumination-viewpoint invariant object recognition[J]. IEEE Trans on Image Processing, 2006,15(1) : 1-11.
  • 4Chen W, Er M J, Wu S. Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain[J]. IEEE Trans on Systems, Man and Cybernetics, Part B, 2006,36(2):458-466.
  • 5Ishiyama R, Hamanaka M, Sakamoto S. An appearance model constructed on 3-D surface for robust face recognition against pose and illumination variations [J]. IEEE Trans on Systems, Man and Cyhernetics, Part C, 2005,35 (3):326-334.
  • 6Charalampidis D. Texture synthesis: textons revisited[J]. IEEE Trans on Image Processing, 2006, 15 (3) :777-787.
  • 7Zhao W, Chellappa R. Illumination-insensitive face recognition using symmetric shape-from-shading [C]//Proc of IEEE International Conf on Computer Vision. USA: IEEE, 2000:286-293.
  • 8Hsu R L. Face detection and modeling for recognition[D]. Michigan, USA: Department of Computer Science & Engineering, Michigan State University, 2002.
  • 9Blanz V, Vetter T. Face recognition based on fitting a 3-D morphable model[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25 (9) : 1063-1074.
  • 10Basri R, Jacobs D W. Lambertian reflectance and linear subspaces[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003,25 (2) : 218-233.
数据采集与处理
2009年 第5期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部