Matching the resolution level to salient image features

被引：5

作者：

Bottoni, P ^{[1
]}

Cinque, L ^{[1
]}

Levialdi, S ^{[1
]}

Mussio, P ^{[1
]}

机构：

[1] Univ Rome La Sapienza, Dipartimento Sci Informaz, I-00198 Rome, Italy

来源：

PATTERN RECOGNITION | 1998年 / 31卷 / 01期

关键词：

pyramids; structural description; rewriting systems; granularity level; resolution level; level selection;

D O I：

10.1016/S0031-3203(97)00021-6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper illustrates how strategies for structural description of images-based on the detection of salient features in the image-can be more efficiently realised by integrating them with the multiresolution approach to reduce details, up to the level at which such features are still recognisable. Since different structures of interest are visible in a restricted range of resolution levels, the combination of structural description with multi-resolution allows the automatic recognition of features at the minimum sufficient level, thus saving a costly description which would store irrelevant details. (C) 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.

引用

页码：89 / 104

页数：16

共 36 条

[31] SYMBOLIC CONSTRUCTION OF A 2-D SCALE-SPACE IMAGE [J].

SAUND, E .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (08) :817-830

[32]

Segen J., 1989, From Pixels to Features. Proceedings of a Workshop, P237

[33]

SIROMONEY G, 1974, COMPUT GRAPHICS IMAG, V3, P63

[34] EXTENDED CONTROLLED TABLE L-ARRAYS [J].

SIROMONEY, R ;

SIROMONEY, G .

INFORMATION AND CONTROL, 1977, 35 (02) :119-138

[35] ATTRIBUTED GRAMMAR - A TOOL FOR COMBINING SYNTACTIC AND STATISTICAL APPROACHES TO PATTERN-RECOGNITION [J].

TSAI, WH ;

FU, KS .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1980, 10 (12) :873-885

[36]

Witkin A.P., 1987, International Joint Conference on Artificial Intelligence, Karlsruhe, Germany, P329, DOI DOI 10.1007/978-3-8348-9190-729

← 1 2 3 4 →