Fast image classification using a sequence of visual fixations

Based on human retinal sampling distributions and eye movements, a sequential resolution image preprocessor is developed. Combined with a nearest neighbor classifier, this preprocessor provides an efficient image classification method, the sequential resolution nearest neighbor (SRNN) classifier. The human eye has a typical fixation sequence that exploits the nonuniform sampling distribution of its retina. If the retinal resolution is not sufficient to identify an object, the eye moves in such a way that the projection of the object falls onto a retinal region with a higher sampling density. Similarly, the SRNN classifier uses a sequence of increasing resolutions until a final class decision is made. Experimental results on texture segmentation show that the preprocessor used in the SRNN classifier is considerably faster than traditional multiresolution algorithms which use all the available resolution levels to analyze the input data.

[1]  C. Curcio,et al.  Topography of ganglion cells in human retina , 1990, The Journal of comparative neurology.

[2]  Ivan Tomek,et al.  A Generalization of the k-NN Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Sahibsingh A. Dudani.  The Distance-Weighted k-Nearest-Neighbor Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  G. McLachlan,et al.  Pattern Classification: A Unified View of Statistical and Neural Approaches. , 1998 .

[5]  A. Hendrickson,et al.  Human photoreceptor topography , 1990, The Journal of comparative neurology.

[6]  Wilson S. Geisler,et al.  A nonparametric statistical analysis of texture segmentation performance using a foveated image preprocessing similar to the human retina , 1996, Proceeding of Southwest Symposium on Image Analysis and Interpretation.

[7]  Michael Unser,et al.  Multiresolution Feature Extraction and Selection for Texture Segmentation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Jürgen Schürmann,et al.  Pattern classification , 2008 .

[9]  L. Croner,et al.  Receptive fields of P and M ganglion cells across the primate retina , 1995, Vision Research.

[10]  Andrew Luk,et al.  A Re-Examination of the Distance-Weighted k-Nearest Neighbor Classification Rule , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[11]  T. Kuyel.  Foveated models for compression, texture discrimination and classification , 1998 .

[12]  Amanda J. C. Sharkey,et al.  On Combining Artificial Neural Nets , 1996, Connect. Sci..

[13]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.

[14]  C.-C. Jay Kuo,et al.  Texture analysis and classification with tree-structured wavelet transform , 1993, IEEE Trans. Image Process..

[15]  Jake K. Aggarwal,et al.  Multiple resolution imagery and texture analysis , 1987, Pattern Recognit..