Common visual pattern discovery via graph matching

Hongtao Xie, Ke Gao, Yongdong Zhang, Jintao Li, Huamin RenACM Multimedia 2011 · OpenReview

Abstract

Discovering common visual patterns (CVPs) between two images is a challenging problem, due to the significant photometric and geometric transformations, and the high computational cost. In this paper, we formulate CVPs discovery as a graph matching problem, depending on pairwise geometric compatibility between feature correspondences. To efficiently find all CVPs, we propose two algorithms--Preliminary Initialization Optimization (PIO) and Post Agglomerative Combining (PAC). PIO reduces the search space of CVPs discovery based on the internal homogeneity of CVPs, while PAC refines the discovery result in an agglomerative way. Experiments on object recognition and near-duplicate image re-trieval validate the effectiveness and efficiency of our method.
BibTeX
@inproceedings{xie2011common,
  author = {Hongtao Xie and Ke Gao and Yongdong Zhang and Jintao Li and Huamin Ren},
  title = {{Common visual pattern discovery via graph matching}},
  booktitle = {ACM Multimedia},
  year = {2011},
  url = {https://openreview.net/forum?id=wl1COaMGyck},
}

Loading related content...

Figure