Object Categorization by Learned Universal Visual Dictionary

This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). Compact and yet discriminative appearance-based object class models are automatically learned from a set of training images. The method is simple and extremely fast, making it suitable for many applications such as semantic image retrieval, web search, and interactive image editing. It classifies a region according to the proportions of different visual words (clusters in feature space). The specific visual words and the typical proportions in each object are learned from a segmented training set. The main contribution of this paper is two fold: i) an optimally compact visual dictionary is learned by pair-wise merging of visual words from an initially large dictionary. The final visual words are described by GMMs. ii) A novel statistical measure of discrimination is proposed which is optimized by each merge operation. High classification accuracy is demonstrated for ni...

• Type: Conference
• Year: 2005
• Where: ICCV
• Authors: John M. Winn, Antonio Criminisi, Thomas P. Minka
• Keywords: Computer Vision, Discriminative Appearance-based Object, ICCV 2005, Object Classes, Visual Words