Object-Based Image Retrieval Using the Statistics of Images

We propose a new Bayesian approach to object-based image retrieval with relevance feedback. Although estimating the object posterior probability density from few examples seems infeasible, we are able to approximate this density by exploiting statistics of the image database domain. Unlike previous approaches that assume an arbitrary distribution for the unconditional density of the feature vector, we learn both the structure and the parameters of this density. These density estimates enable us to construct a Bayesian classifier. Traditional region-based image retrieval systems require segmentation of the image; instead, using this Bayesian classifier, we perform a windowed scan over images for objects of interest. The user’s feedback on the search results is used to train a second classifier that focuses on eliminating difficult false positives. We have incorporated this algorithm into an object-based image retrieval system. We demonstrate the effectiveness of our approach with experiments using a set of categories from the Corel