Evaluating bag-of-visual-words representations in scene classification

Jun Yang, Yu-Gang Jiang, Alexander G. Hauptmann, Chong-Wah Ngo
2007 Proceedings of the international workshop on Workshop on multimedia information retrieval - MIR '07  
Based on keypoints extracted as salient image patches, an image can be described as a "bag of visual words" and this representation has been used in scene classification. The choice of dimension, selection, and weighting of visual words in this representation is crucial to the classification performance but has not been thoroughly studied in previous work. Given the analogy between this representation and the bag-of-words representation of text documents, we apply techniques used in text
more » ... ization, including term weighting, stop word removal, feature selection, to generate image representations that differ in the dimension, selection, and weighting of visual words. The impact of these representation choices to scene classification is studied through extensive experiments on the TRECVID and PASCAL collection. This study provides an empirical basis for designing visual-word representations that are likely to produce superior classification performance.
doi:10.1145/1290082.1290111 dblp:conf/mir/YangJHN07 fatcat:ov3j6mttdjcdhdeqltr3boepfa