STRUCTURAL MATCHING IN COMPUTER VISION USING PROBABILISTIC RELAXATION

被引:303
作者
CHRISTMAS, WJ
KITTLER, J
PETROU, M
机构
[1] Vision, Speech, and Signal Processing Group, Department of Electronic and Electrical Engineering, University of Surrey, Guildford
关键词
MATCHING; PROBABILISTIC RELAXATION; OBJECT RECOGNITION;
D O I
10.1109/34.400565
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we develop the theory of probabilistic relaxation for matching features extracted from 2D images, derive as limiting cases the various heuristic formulae used by researchers in matching problems, and state the conditions under which they apply. We successfully apply our theory to the problem of matching and recognizing aerial road network images based on road network models and to the problem of edge matching in a stereo pair. For this purpose, each line network is represented by an attributed relational graph where each node is a straight line segment characterized by certain attributes and related with every other node via a set of binary relations.
引用
收藏
页码:749 / 764
页数:16
相关论文
共 44 条
[1]  
ACKLEY DH, 1985, COGNITIVE SCI, V9, P147
[2]  
BAIRD HS, 1985, MODEL BASED IMAGE MA
[3]  
Ballard DH, 1982, COMPUTER VISION
[4]  
BEVERIDGE JR, 1992, C COMPUTER VISION PA, P432
[5]   SHAPE-MATCHING OF TWO-DIMENSIONAL OBJECTS [J].
BHANU, B ;
FAUGERAS, OD .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (02) :137-156
[7]  
BIENENSTOCK E, 1988, NEURAL INFORMATION P, P211
[8]  
BLAKE A., 1987, VISUAL RECONSTRUCTIO
[9]   The least-disturbance principle and weak constraints [J].
Blake, Andrew .
PATTERN RECOGNITION LETTERS, 1983, 1 (5-6) :393-399
[10]  
BOLLES RC, 1979, P SOC PHOTOOPT INSTR, V182, P140