期刊
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
卷 24, 期 5, 页码 635-646出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jvcir.2013.04.012
关键词
Common visual pattern; Graph matching; Maximal clique; Quadratic optimization; Feature correspondence; Point set matching; Object recognition; Near-duplicate image retrieval
资金
- National Nature Science Foundation of China [61271428, 61273247]
- National Key Technology Research and Development Program of China [2012BAH39B02]
- Beijing Municipal Education Commission
- Chinese Academy of Sciences [XDA06030200]
Discovering common visual patterns (CVPs) between two images is a difficult and time-consuming task, due to the photometric and geometric transformations. The state-of-the-art methods for CVPs discovery are either computationally expensive or have complicated constraints. 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 a novel framework which consists of three components: Preliminary Initialization Optimization (PIO), Guided Expansion (GE) and Post Agglomerative Combination (PAC). PIO gets the initial CVPs and reduces the search space of CVPs discovery, based on the internal homogeneity of CVPs. Then, GE anchors on the initializations and gradually explores them, to find more and more correct correspondences. Finally, to reduce false and miss detection, PAC refines the discovery result in an agglomerative way. Experiments and applications conducted on benchmark datasets demonstrate the effectiveness and efficiency of our method. (C) 2013 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据