The role of relational constraints in region matching

被引:2
作者
Ahmadyfard, A [1 ]
Kittler, J
机构
[1] Shahrood Univ, Dept Elect Engn, Shahrood, Iran
[2] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford GU2 7XH, Surrey, England
关键词
object recognition; affine invariants; binary relations; relaxation labeling;
D O I
10.1142/S0218001404003290
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a graph-based representation for the elliptic region shape descriptors introduced by Tuytelaars et al.(13) In this representation we use image profiles to describe the relation between a pair of image regions. This new representation and a graph matching technique proposed in Ref. 1 are the basis of an object recognition method. An experimental comparative study between the original method and the new graph-based method is carried out. The results show that the graph-based method is more robust to scaling than the original method. Moreover, the misclassification rate using the graph-based method is considerably lower than that yielded by the original method.
引用
收藏
页码:443 / 454
页数:12
相关论文
共 13 条
[1]  
AHMADYFARD A, 2002, P 11 EUR SIGN PROC C, V3, P551
[2]  
Baumberg A, 2000, PROC CVPR IEEE, P774, DOI 10.1109/CVPR.2000.855899
[3]   STRUCTURAL MATCHING IN COMPUTER VISION USING PROBABILISTIC RELAXATION [J].
CHRISTMAS, WJ ;
KITTLER, J ;
PETROU, M .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (08) :749-764
[4]   Robust recognition using eigenimages [J].
Leonardis, A ;
Bischof, H .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2000, 78 (01) :99-118
[5]   3-DIMENSIONAL OBJECT RECOGNITION FROM SINGLE TWO-DIMENSIONAL IMAGES [J].
LOWE, DG .
ARTIFICIAL INTELLIGENCE, 1987, 31 (03) :355-395
[6]  
Matas J., 2000, BMV2000. Proceedings of the 11th British Machine Vision Conference, P606
[7]   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
[8]  
NAGAO K, 1994, OBJECT RECOGNITION A
[9]  
POPE AR, 1994, MODEL BASED OBJECT R
[10]   Local grayvalue invariants for image retrieval [J].
Schmid, C ;
Mohr, R .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (05) :530-535