论文信息 - Face Recognition Using Ordinal Features

Face Recognition Using Ordinal Features

In this paper, we present an ordinal feature based method for face recognition. Ordinal features are used to represent faces. Hamming distance of many local sub-windows is computed to evaluate differences of two ordinal faces. AdaBoost learning is finally applied to select most effective hamming distance based weak classifiers and build a powerful classifier. Experiments demonstrate good results for face recognition on the FERET database, and the power of learning ordinal features for face recognition.

[1] Shimon Ullman,et al. Object recognition with informative features and linear classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[2] Henry Schneiderman,et al. Feature-centric evaluation for efficient cascaded object detection , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[3] Heinrich H. Bülthoff,et al. Biologically motivated computer vision : Second International Workshop, BMCV 2002, Tübingen, Germany, November 22-24, 2002 : proceedings , 2002 .

[4] Javid Sadr,et al. The Fidelity of Local Ordinal Encoding , 2001, NIPS.

[5] Henry Schneiderman,et al. Feature-centric evaluation for efficient cascaded object detection , 2004, CVPR 2004.

[6] Pawan Sinha,et al. Qualitative Representations for Recognition , 2002, Biologically Motivated Computer Vision.

[7] Yoav Freund,et al. A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[8] Michel Vidal-Naquet,et al. Visual features of intermediate complexity and their use in classification , 2002, Nature Neuroscience.

[9] P. Sinha,et al. Dissociated Dipoles: Image Representation via Non-local Comparisons , 2003 .