Diffusion Distance for Histogram Comparison

In this paper we propose diffusion distance, a new dissimilarity measure between histogram-based descriptors. We define the difference between two histograms to be a temperature field. We then study the relationship between histogram similarity and a diffusion process, showing how diffusion handles deformation as well as quantization effects. As a result, the diffusion distance is derived as the sum of dissimilarities over scales. Being a cross-bin histogram distance, the diffusion distance is robust to deformation, lighting change and noise in histogram-based local descriptors. In addition, it enjoys linear computational complexity which significantly improves previously proposed cross-bin distances with quadratic complexity or higher. We tested the proposed approach on both shape recognition and interest point matching tasks using several multi-dimensional histogram-based descriptors including shape context, SIFT, and spin images. In all experiments, the diffusion distance performs ...

• Type: Conference
• Year: 2006
• Where: CVPR
• Authors: Haibin Ling, Kazunori Okada
• Keywords: Computer Vision, Cross-bin Histogram Distance, CVPR 2006, Diffusion Distance, Diffusion Handles Deformation, Diffusion Process, State-of-the-art Distance Measures