Multi-stage Combination of Geometric and Colorimetric Detectors for Eyes Localization

We present in this paper a method for the localization of the eyes in a facial image. This method works on color images, applying the so called Chinese Transformation (CT) on edge pixels to detect local symmetry. The CT is combined with a skin color model based on a modified Gaussian Mixture Model (GMM). The CT and the modified GMM give us a small rectangular area containing one eye with a very high probability. This rectangle is then processed to find the precise position of the eye, using four sources of information: a darkness measure, a circle finder, a “not skin” finder and a position information. Experimental results on a large database are presented on nearly 1000 faces from the ECU database.

[1]  Dante Augusto Couto Barone,et al.  A probabilistic model for the human skin color , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[2]  Abdesselam Bouzerdoum,et al.  Skin segmentation using color pixel classification: analysis and comparison , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Yehezkel Yeshurun,et al.  Robust detection of facial features by generalized symmetry , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[4]  Georgios Tziritas,et al.  Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis , 1999, IEEE Trans. Multim..

[5]  Lionel Prevost,et al.  Combining model-based classifiers for face localization , 2005, MVA.

[6]  Anil K. Jain,et al.  Face Detection in Color Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Kin-Man Lam,et al.  Locating the eye in human face images using fractal dimensions , 2001 .

[8]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..