论文信息 - Robust facial profile recognition

Robust facial profile recognition

In this paper we present a robust approach to facial profile recognition. The high robustness results from a localization method that automatically locates the facial profile from the full contour of a person's head, and a facial profile matching method that is upgraded by a procedure for tuning facial profile normalization parameters. A model preselection method is introduced to exclude a large part of the model database from the actual matching. The facial profile recognition system has been implemented and achieved good results.

[1] Masahide Kaneko,et al. Design and implementation of SPIDER - A transportable image processing software package , 1983, Comput. Vis. Graph. Image Process..

[2] Horst Bunke,et al. Combination of face classifiers for person identification , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[3] Horst Bunke,et al. Applications of approximate string matching to 2D shape recognition , 1993, Pattern Recognit..

[4] Horst Bunke,et al. Kombination von Frontal- und Profilanalyse menschlicher Gesichter , 1995, DAGM-Symposium.

[5] Rama Chellappa,et al. Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[6] M. K. Khan,et al. Machine identification of human faces , 1981, Pattern Recognition.

[7] Jun S. Huang,et al. Human face profile recognition by computer , 1990, Pattern Recognit..

[8] Ashok Samal,et al. Automatic recognition and analysis of human faces and facial expressions: a survey , 1992, Pattern Recognit..