期刊文献+

一种颜色仿射变换下的局部特征描述子 被引量:15

A Local Feature Descriptor under Color Affine Transformation
下载PDF
导出
摘要 提出一种颜色仿射变换下局部特征的描述子,它分别处理特征点邻域内每个像素的RGB 3个颜色通道,并利用仿射不变量计算每个颜色通道的仿射梯度;为控制特征点处描述子的维数,根据邻域内像素到特征点的距离和相对特征点主方向的角度对特征点邻域内的仿射梯度进行累加,构成局部特征点的特征描述子.所提出的特征描述子增强了特征点对光度变化和仿射变换的不变性,提高了图像局部特征匹配的准确度;并通过一组典型图像的特征点匹配实验验证了其有效性. A new local feature’s affine gradient descriptor(AGDES) is presented. It handles each color channel of every pixel in local features’ neighborhood, and computes affine gradient for each channel. In order to control the dimensions of descriptors, local features are described by accumulating their affine gradient of different directions and distances to the feature points. The new descriptor is more robust to photometric changes and color affine transformation, and can improve the matching precision. Extensive experimental results have demonstrated the effectiveness and efficiency of the proposed algorithm.
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2013年第1期26-33,共8页 Journal of Computer-Aided Design & Computer Graphics
基金 国家"八六三"高技术研究发展计划(2007AA01Z317) 国家自然科学基金(60873164)
关键词 局部特征 特征描述 光照变化 颜色仿射变换 图像匹配 local feature feature description illumination change color affine transformation image matching
  • 相关文献

参考文献27

  • 1Brown M, Lowe D G. Automatic panoramic image stitching using invariant features [J].International journal of Computer Vision, 2007, 74(1): 59-73.
  • 2Lowe D G. Object recognition from local scale-invariant features [C] //Proceedings of the 7th IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 1999:1150-1157.
  • 3Schaffalitzky F, Zisserman A. Multi view matching for unordered image sets, of how do I organize my holiday snaps?[C] //Proceedings of the 7th European Conference on Computer Vision. Berlin: Springer, 2002:414-431.
  • 4Snavely N, Seitz S M, Szeliski R. Photo tourism: exploring photo collections in 3D [J]. ACM Transactions on Graphics, 2006, 25(3):835-846.
  • 5李晓明,秦茜茜.基于准稠密匹配的结构化场景三维重建[J].计算机辅助设计与图形学学报,2011,23(5):849-854. 被引量:7
  • 6Florack L M J, Ter Haar Romeny B M, Koenderink J J, el al. General intensity transformations and differential invariants [J]. Journal of Mathematical Imaging and Vision, 1994, 4(2):171-187.
  • 7Mindru F, Tuytelaars T, Van Gool L, et al. Moment invariants for recognition under changing viewpoint and illumination [J]. Computer Vision and Image Understanding, 2004, 94(1/3): 3-27.
  • 8Baumberg A. Reliable feature matching across widely separated views [C] //Proceedings of IEEB Computer Society Conference on Computer Vision and Pattern Recognition. 1.os Alamitos: IEEE Computer Society Press, 2000, 1: 1774- 1781.
  • 9Freeman W T, Adelson E H. The design and use of steerable filters [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(9): 891-906.
  • 10Carneiro G, Jepson A D. Multi scale phase based local features [C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2003: 736-743.

二级参考文献34

  • 1Schaffalitzky F,Zisserman A.Multi-view matching for unordered image sets,or "how do I organize my holiday snaps?"// Proceedings of the 7th European Conference on Computer Vision.Copenhagen,2002:414-431.
  • 2Brown M,Szeliski R,Winder S.Multi-image matching using multi-scale oriented patches//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.San Diego,2005:510-517.
  • 3Snavely N,Seitz S M,Szeliski R.Photo tourism:Exploring photo collections in 3D.ACM Transactions on Graphics,2006,25(3):835-846.
  • 4Brown M,Lowe D G.Automatic panoramic image stitching using invariant features.International Journal of Computer Vision,2007,74(1):59-73.
  • 5Mikolajczyk K,Leibe B,Schiele B.Local feature for object class recognition//Proceedings of the 10th IEEE International Conference on Computer Vision.Beijing,2005:1792-1799.
  • 6Schmid C,Mohr R.Local grayvalue invariants for image retrieval.IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(5):530-534.
  • 7Schmid C,Mohr R,Bauckhage C.Evaluation of interest point detectors.International Journal of Computer Vision,2000,37(2):151-172.
  • 8Dufournaud Y,Schmid C,Horaud R.Matching images with different resolutions//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Hilton Head Island,South Carolina,2000:612-618.
  • 9Lindeberg T.Feature detection with automatic scale selection.International Journal of Computer Vision,1998,30 (2):79-116.
  • 10Lowe D G.Distinctive image features from scale-invariant keypoints.International Journal of Computer Vision,2004,60(2):91-110.

共引文献40

同被引文献181

  • 1明德烈,柳健,田金文.仿射变换在增强现实中的应用[J].系统仿真学报,2001,13(S2):286-289. 被引量:8
  • 2罗钟铉,刘成明.灰度图像匹配的快速算法[J].计算机辅助设计与图形学学报,2005,17(5):966-970. 被引量:72
  • 3赵文彬,张艳宁.角点检测技术综述[J].计算机应用研究,2006,23(10):17-19. 被引量:83
  • 4Szeliski R. Video mosaics for virtual environments[J]. IEEE Computer Graphics and Applications, 1996, 16 (2) : 22-30.
  • 5Peleg S, Rousso B. Mosaicing on adaptive manifolds [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22(10): 1144-1154.
  • 6Brown M, Lowe D G. Automatic panoramic image stitching using invariant features[J]. International J. of Computer Vision, 2007, 74(1) : 59-73.
  • 7Fan X, Fan G L. Graphical models for joint segmentation andrecognition of license plate characters [J]. IEEE SignalProcessing Letters, 2009,16(1) : 10-13.
  • 8Egozi A, Keller Y, Guterman H . Improving shape retrievalby spectral matching and meta similarity [J]. IEEETransactions on Image Processing, 2010* 19(5) : 1319-1327.
  • 9Xu K,Chen K. Fu H, et al. Sketch2Scene: sketch-based co-retrieval and co-placement of 3D models [J]. ACMTransactions on Graphics* 2013,32(4) : Article No. 123.
  • 10Koutsourakis P,Simon L, Teboul 0,et al. Single viewreconstruction using shape grammars for urban environments[C] //Proceedings of the 12th IEEE International Conferenceon Computer Vision. Los Alamitos: IEEE Computer SocietyPress, 2009: 1795-1802.

引证文献15

二级引证文献111

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部