1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190 2.Department of Automation, North China Electric Power University, Baoding 071003 3.Department of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454003
Abstract An image feature based on image gradient is proposed, called Harris correlation. It is used to construct feature descriptors including point descriptor, line descriptor as well as curve descriptor. These feature descriptors are invariant to image rotation and linear intensity changes. Constructing descriptors for both line and curve explores a new way for line and curve matching. Experimental results show that the point descriptor performs well on image transformations, and the line and curve descriptors are effective in real image matching as well.
[1] Zhang Zhengyou, Deriche R, Faugeras O, et al. A Robust Technique for Matching Two Un-Calibrated Images through the Recovery of the Unknown Epipolar Geometry. Artificial Intelligence, 1995, 78(1): 87-119 [2] Johnson A E, Hebert M. Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes. IEEE Trans on Pattern Analysis and Machine Intelligence, 1999, 21(5): 433-449 [3] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [4] Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630 [5] Belongie S, Malik J, Puzicha J. Shape Matching and Object Recognition Using Shape Contexts. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(4): 509-522 [6] Floract L M J, Romeny B M, Koenderink J J, et al. General Intensity Transformations and Differential Invariants. Journal of Mathematical Imaging and Vision, 1994, 4(2): 171-187 [7] Freeman W T, Adelson E H. The Design and Use of Steerable Filters. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991, 13(9): 891-906 [8] van Gool L J, Moons T, Ungureanu D. Affine/Photometric Invariants for Planar Intensity Patterns // Proc of the 4th European Conference on Computer Vision. Cambridge, UK, 1996: 642-651 [9] Schaffalitzky F, Zisserman A. Viewpoint Invariant Texture Matching and Wide Baseline Stereo // Proc of the 8th IEEE International Conference on Computer Vision. Vancouver, Canada, 2001, Ⅱ: 636-643 [10] Schaffalitzky F, Zisserman A. Multi-View Matching for Unordered Image Sets // Proc of the 7th European Conference on Computer Vision. Copenhagen, Denmark, 2002, Ⅰ: 414-431 [11] Tang A W K, Ng T P, Hung Y S, et al. Projective Reconstruction from Line-Correspondences in Multiple Uncalibrated Images. Pattern Recognition, 2006, 39(5): 889-896 [12] Shi Fanhuai, Wang Jianhua, Zhang Jing, et al. Motion Segmentation of Multiple Translating Objects from Line Correspondences. Pattern Recognition, 2005, 38(10): 1775-1778 [13] Aider O A, Hoppenot P, Colle E. A Model-Based Method for Indoor Mobile Robot Localization Using Monocular Vision and Straight-Line Correspondences. Robotics and Autonomous Systems, 2005, 52(2/3): 229-246 [14] Bartoli A, Sturm P. Multiple-View Structure and Motion from Line Correspondences // Proc of the IEEE International Conference on Computer Vision. Nice, France, 2003: 207-212 [15] Schmid C, Zisserman A. Automatic Line Matching across Views // Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. San Juan, Puerto Rico, 1997: 666-671 [16] Deng Yi, Lin Xueyin. A Fast Line Segment Based Dense Stereo Algorithm Using Tree Dynamic Programming // Proc of the European Conference on Computer Vision. Graz, Austria, 2006: 201-212 [17] Hartley R. A Linear Method for Reconstruction from Lines Arid Points // Proc of the 5th IEEE International Conference on Computer Vision. Boston, USA, 1995: 882-887 [18] Lourakis M I A, Halkidis S T, Orphanoudakis S C. Matching Disparate Views of Planar Surfaces Using Projective Invariants. Image and Vision Computing, 2000, 18(9): 673-683 [19] Schmid C, Zisserman A. The Geometry and Matching of Lines and Curves over Multiple Views. International Journal of Computer Vision, 2000, 40(3): 199-233 [20] Bay H, Ferraris V, van Gool L J. Wide-Baseline Stereo Matching with Line Segments // Proc of the 14th International Conference on Pattern Recognition. San Diego, USA, 2005, Ⅰ: 329-336 [21] Goedem′e T, Tuytelaars T, van Gool L. Fast Wide Baseline Matching for Visual Navigation // Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. Washington, USA, 2004, Ⅰ: 24-29 [22] Harris C, Stephens M J. A Combined Corner and Edge Detector // Proc of the 4th Alvey Vision Conference. Manchester, UK, 1988: 147-151 [23] Lindeberg T. Detecting Salient Blob-Like Image Structures and Their Scales with a Scale-Space Primal Sketch: A Method for Focus-of-Attention. International Journal of Computer Vision, 1993, 11(3): 283-318 [24] Hartley R, Zisserman A. Multiple View Geometry in Computer Vision. Cambridge, UK: Cambridge University Press, 2000 [25] Mokhtarian F, Suomela R. Robust Image Corner Detection through Curvature Scale Space. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1376-1381 [26] Mikolajczyk K, Schmid C. Scale and Affine Invariant Interest Point Detectors. International Journal of Computer Vision, 2004, 60(1): 63-86
2009, Vol. 22 
