Flexible image similarity computation using hyper-spatial matching

Yu Zhang, Jianxin Wu, Jianfei Cai, Weiyao Lin

Research output: Contribution to journalArticleResearchpeer-review

9 Citations (Scopus)


Spatial pyramid matching (SPM) has been widely used to compute the similarity of two images in computer vision and image processing. While comparing images, SPM implicitly assumes that: in two images from the same category, similar objects will appear in similar locations. However, this is not always the case. In this paper, we propose hyper-spatial matching (HSM), a more flexible image similarity computing method, to alleviate the mis-matching problem in SPM. The match between corresponding regions, HSM considers the relationship of all spatial pairs in two images, which includes more meaningful match than SPM. We propose two learning strategies to learn SVM models with the proposed HSM kernel in image classification, which are hundreds of times faster than a general purpose SVM solver applied to the HSM kernel (in both training and testing). We compare HSM and SPM on several challenging benchmarks, and show that HSM is better than SPM in describing image similarity.

Original languageEnglish
Pages (from-to)4112-4125
Number of pages14
JournalIEEE Transactions on Image Processing
Issue number9
Publication statusPublished - Sep 2014
Externally publishedYes


  • fast SVM learning
  • mage similarity
  • spatial matching

Cite this