一种基于相关反馈的视频人脸算法

doi:10.3969/j.issn.1001-2400.2012.03.025

Abstract

Abstract:

How to fully utilize both spatial and temporal information in video to overcome the difficulties existing in the video-based face recognition, such as the low resolution of face images in video, large variations of face scale, radical changes of illumination and pose as well as occasional occlusion of different parts of faces, is the key problem. In this paper, on the basis of Locality Preserving Projections (LPP), we propose a novel relevance feedback video face recognition method (RFVLPP), which can preserve more spatial and temporal information hidden in the video face sequence using clustering, and make full use of the intrinsic nonlinear structure information to extract discriminative manifold features. The experiment compares RFVLPP with other algorithms on UCSD/Honda Video Database and our own Video Database. Experimental results show that the proposed approach can outperform state-of-the-art solutions for video-based face recognition.

Key words: video-based face recognition, locality preserving projection, relevance feedback

LU Ke;DING Zhengming;ZHAO Jidong;WU Yue. Novel face recognition relevance feedback algorithm for video[J].J4, 2012, 39(3): 154-160.

References

［1］ Chellappa R, Wilson C, Sirohey S. Human and Machine Recognition of Faces: a Survey［J］. Proceedings of the IEEE, 1995, 83(5): 705-740.
［2］ Turk M, Pentland A. Face Recognition Using Eigenfaces［C］//Proc IEEE Conf on Computer Vision and Pattern Recognition. Washington: IEEE Press, 1991: 586-591.
［3］ Belhumeur P N, Hespanha J P, Kriegman D J. Eigenfaces vs Fisherfaces: Recognition Using Class Specific Linear Projection［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720.
［4］ Guo Guodong. Li S Z, Chan K. Face Recognition by Support Vector Machines［C］//Fourth IEEE International Conference on Automatic Face and Gesture Recognition (FG'00). Washington: IEEE Press, 2000: 196-201.
［5］ He Xiaofei, Niyogi P. Locality Preserving Projections［C］//Advances in Neural Information Processing Systems 16 (NIPS). Vancouver: MIT Press, 2003: 153-162.
［6］ He Xiaofei. Face Recognition Using Laplacianfaces［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340.
［7］田玉敏, 云艳娥, 马天骏. 判别近邻保持嵌入人脸识别［J］. 西安电子科技大学学报, 2011, 38(3): 24-28.
Tian Yumin, Yun Yan'e, Ma Tianjun. Discriminant Neighborhood Preserving Embedding Algorithm for Face Recognition［J］. Journal of Xidian University, 2011, 38(3): 24-28.
［8］ Lu K, Zhao J. Hessian Optimal Design for Image Retrieval［J］. Pattern Recognition, 2011, 44(6): 1155-1161.
［9］ Belkin M, Niyogi P. Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering［C］//Proceedings of advance in Neural Information Processing Systems 14. Cambridge: MIT Press, 2002: 585-591.
［10］严严, 章毓晋. 基于视频的人脸识别研究进展［J］. 计算机学报, 2009, 32(5): 878-886.
Yan Yan, Zhang Yujin. State of the Art on Video-Based Face Recognition［J］. Chinese Journal of Compu Ters, 2009, 32(5): 878-886.
［11］ Wang Huafeng, Wang Yunhong, Cao Yuancao. Video-based Face Recognition: a Survey［DB/OL］. ［2010-12-05］. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.193.639.
［12］ Liu X M, Chen T. Video-based Face Recognition Using Adaptive Hidden Markov Models［C］//Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. Madison: IEEE, 2003: 340-345.
［13］ Cipolla A R. Face Recognition from Face Motion Manifolds Using Robust Kernel Resistor-average Distance［C］//Proceedings of the IEEE Conference on Compute Vision and Patter Recognition Workshop. Washington: IEEE, 2004: 88-93.
［14］ Rui Y, Huang T S, Ortega M, et al. Relevance Feedback: a Power Tool for Interative Content-Based Image Retrieval［J］. IEEE Trans on Circuits Syst Video Technol, 1998, 8(5): 644-655.
［15］ Kanungo T, Mount D M, Netanyahu N S, et al. An Efficient k-means Clustering Algorithm: Analysis and Implementation［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002(24): 881-892.
［16］ Cvetkovic D M, Doob M, Gutman I, et al. Recent Results in the Theory of Graph Spectra［M］. Amsterdam: North-Holland, 1988.
［17］鲁珂, 赵继东, 吴跃, 等. 基于保局投影的相关反馈算法［J］. 计算机辅助设计与图形学学报, 2007, 19(1): 20-24.
Lu Ke, Zhao Jidong, Wu Yue, et al. Relevance Feedbacks Algorithm Based on Locality Preserving Projections ［J］. Journal of Computer-Aided Design & Computer Graphics, 2007, 19(1): 20-24.

[1]	WANG Ying;GAO Xin-bo. A mass detection algorithm based on SVM and relevance feedback [J]. J4, 2007, 34(2): 239-245.
[2]	CUI Jiang-tao(1);SUN Jun-ding(1;2);ZHOU Li-hua(1). An efficient high-dimensional image indexing method for relevance feedback [J]. J4, 2006, 33(1): 62-65.

Novel face recognition relevance feedback algorithm for video

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 2

Metrics

Comments

Recommended 5