Object Recognition based on SIFT Feature Points

被引:0
作者
Huang, Wen-qing [1 ]
Hu, Hai-yan [1 ]
Li, Wen-jie [1 ]
Jiang, Ming-feng [1 ]
机构
[1] Zhejiang Sci Tech Univ, Inst Comp Vis & Pattern Recognit, Hangzhou, Zhejiang, Peoples R China
来源
ISBE 2011: 2011 INTERNATIONAL CONFERENCE ON BIOMEDICINE AND ENGINEERING, VOL 2 | 2011年
关键词
SIFT; Scale space; Match; BBF algorithm;
D O I
暂无
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
An approach to recognize object based on SIFT (Scale Invariant Feature Transform) feature points is proposed in this paper. First, the method to obtain SIFT feature points in different scale space is discussed. Then, a k-d tree of SIFT feature points is created. The matching between two images is completed by using BBF (Best Bin First) algorithm on k-d tree. Finally, the values of some parameters are given by analyzing the datum and curves of experiment. Experiment results show that SIFT feature point is invariant to rotation, scale and intensity change, to some extent, is invariant to affine, noise and the change in viewpoint. By means of SIFT feature points, the robust recognition can be performed.
引用
收藏
页码:517 / 520
页数:4
相关论文
共 10 条
[1]  
BROWN M., 2002, BRIT MACHINE VISION, P656, DOI DOI 10.5244/C.16.23
[2]  
Lowe D. G., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1150, DOI 10.1109/ICCV.1999.790410
[3]   Distinctive image features from scale-invariant keypoints [J].
Lowe, DG .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) :91-110
[4]   VISUAL LEARNING AND RECOGNITION OF 3-D OBJECTS FROM APPEARANCE [J].
MURASE, H ;
NAYAR, SK .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1995, 14 (01) :5-24
[5]   Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects [J].
Ohba, K ;
Ikeuchi, K .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (09) :1043-1048
[6]  
Park Changhan, 2009, 34 IEEE INT C INFR M, V2, P1
[7]  
Schiele B., 1996, Computer Vision - ECCV '96. 4th Eurpean Conference on Computer Proceedings, P610, DOI 10.1007/BFb0015571
[8]   Local grayvalue invariants for image retrieval [J].
Schmid, C ;
Mohr, R .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (05) :530-535
[9]  
Wang Guo-mei, 2007, J YANCHENG I TECHNOL, V20, p[1, 10]
[10]   A ROBUST TECHNIQUE FOR MATCHING 2 UNCALIBRATED IMAGES THROUGH THE RECOVERY OF THE UNKNOWN EPIPOLAR GEOMETRY [J].
ZHANG, ZY ;
DERICHE, R ;
FAUGERAS, O ;
LUONG, QT .
ARTIFICIAL INTELLIGENCE, 1995, 78 (1-2) :87-119