Object Recognition Based on Dependent Pachinko Allocation Model

Abstract

Recently the bag of model becomes popular in the approaches to object recognition. These approaches model an image as a collection of local patches called words, and recognize objects in the image through inferring latent topics associated with the set of visual words. In this paper, we apply an extension version of Pachinko allocation model (PAM) to object recognition. Our PAM based approach models the correlation-ship of latent topics explicitly in a hierarchical structure. To relax the independent assumption for visual words and refine the topic inferring, we incorporate the prior knowledge of cooccurrence dependence among visual words into PAM. Highly competitive recognition results on both Caltech4 and Caltech101 datasets show the proposed approach is more expressive and discriminative than most existing methods of object recognition.