Fast image classification using a sequence of visual fixations

Based on human retinal sampling distributions and eye movements, a sequenti al resolution image preprocessor is developed. Combined with a nearest neig hbor classifier, this preprocessor provides an efficient image classificati on method, the sequential resolution nearest neighbor (SRNN) classifier. Th e human eye has a typical fixation sequence that exploits the nonuniform sa mpling distribution of its retina. If the retinal resolution is not suffici ent 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. S imilarly, the SRNN classifier uses a sequence of increasing resolutions unt il a final class decision is made. Experimental results on texture segmenta tion show that the preprocessor used in the SRNN classifier is considerably faster than traditional multiresolution algorithms which use all the avail able resolution levels to analyze the input data.