Use Bin-Ratio Information for Category and Scene Classification

In this paper we propose using bin-ratio information, which is collected from the ratios between bin values of histograms, for scene and category classification. To use such information, a new histogram dissimilarity, bin-ratio dissimilarity (BRD), is designed. We show that BRD provides several attractive advantages for category and scene classification tasks: First, BRD is robust to cluttering, partial occlusion and histogram normalization; Second, BRD captures rich co-occurrence information while enjoying a linear computational complexity; Third, BRD can be easily combined with other dissimilarity measures, such as L1 and χ2 , to gather complimentary information. We apply the proposed methods to category and scene classification tasks in the bag-of-words framework. The experiments are conducted on several widely tested datasets including PASCAL 2005, PASCAL 2008, Oxford flowers, and Scene-15 dataset. In all experiments, the proposed methods demonstrate excellent performance in ...

• Type: Conference
• Year: 2010
• Where: CVPR
• Authors: Nianhua Xie, Haibin Ling, Weiming Hu, Xiaoqin Zhang
• Keywords: BRD Captures, Computer Vision, CVPR 2010, Linear Computational Complexity, Scene Classification Tasks