Understanding visual dictionaries via Maximum Mutual Information curves

Visual dictionaries have been successfully applied to ¿bags-of-points¿ image representations for generic object recognition. Usually the choice of low-level interest region detector and region descriptor (channel) has significant impact on the performance of visual dictionaries. In this paper, we propose a discriminative evaluation method-Maximum Mutual Information (MMI) curves to analyze the properties of the visual dictionaries built from different channels. Experimental results on benchmark datasets show that MMI curves can give us not only insight into the discriminative characteristics of the visual dictionaries, but also provide straightforward guidelines for the design of the image classifier.