Large Vocabularies for Keypoint-Based Representation and Matching of Image Patches

被引：0
作者：
Sluzek, Andrzej [1 ]
机构：
[1] Khalifa Univ, Abu Dhabi, U Arab Emirates
来源：
COMPUTER VISION - ECCV 2012: WORKSHOPS AND DEMONSTRATIONS, PT I | 2012年 / 7583卷
关键词：
keypoint description; keypoint correspondences; visual vocabulary; near-duplicate patches; affine invariance; GEOMETRY; SCALE;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In large visual databases, detection of prospectively similar contents requires simple and robust methods. Keypoint correspondences are a popular approach which, nevertheless, cannot detect (using typical descriptions) similarities in a wider image context, e.g. detection of similar fragments. For such capabilities, the analysis of configuration constraints is needed. We propose keypoint descriptions which (by using sets of words from large vocabularies) represent semi-local characteristics of images. Thus, similar image patches (including similarly looking objects) can be preliminarily retrieved by straightforward keypoint matching. A limited-scale experimental verification is provided. The approach can be prospectively used as a simple mid-level feature matching in large and unpredictable visual databases.
引用
收藏
页码：229 / 238
页数：10
相关论文
共 17 条
  • [1] [Anonymous], 2008, PAPER NO 2511
  • [2] [Anonymous], 2010, PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2010.5539963
  • [3] Matching with PROSAC - Progressive Sample Consensus
    Chum, O
    Matas, J
    [J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 220 - 226
  • [4] Chum O, 2009, PROC CVPR IEEE, P17, DOI 10.1109/CVPRW.2009.5206531
  • [5] Fischler M., 1996, ECCV, P683
  • [6] Product Quantization for Nearest Neighbor Search
    Jegou, Herve
    Douze, Matthijs
    Schmid, Cordelia
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (01) : 117 - 128
  • [7] Lowe D. G., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1150, DOI 10.1109/ICCV.1999.790410
  • [8] Distinctive image features from scale-invariant keypoints
    Lowe, DG
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) : 91 - 110
  • [9] Scale & affine invariant interest point detectors
    Mikolajczyk, K
    Schmid, C
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (01) : 63 - 86
  • [10] Paradowski M, 2011, STUD COMPUT INTELL, V339, P195
12