Local operators to detect regions of interest

被引：15

作者：

Di Gesu, V ^{[1
]}

Valenti, C

Strinati, L

机构：

[1] Univ Palermo, Dipartimento Matemat & Applicaz, Palermo, Italy

[2] Univ Paris Val De Marne, Paris, France

来源：

PATTERN RECOGNITION LETTERS | 1997年 / 18卷 / 11-13期

关键词：

attention; segmentation; face recognition; symmetry operators;

D O I：

10.1016/S0167-8655(97)00084-6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The performance of a visual system is strongly influenced by the information processing that is done in the early vision phase. The need exists to limit the computation on areas of interest to reduce the total amount of data and their redundancy. This paper describes a new method to drive the attention during the analysis of complex scenes. Two new local operators, based on the computation of local moments and symmetries, are combined to drive the selection. Experimental results on real data are also reported. (C) 1997 Elsevier Science B.V.

引用

页码：1077 / 1081

页数：5

共 12 条

[1]

Aloimonos J., 1987, International Journal of Computer Vision, V1, P333, DOI 10.1007/BF00133571

[2] PATTERN-RECOGNITION WITH MOMENT INVARIANTS - A COMPARATIVE-STUDY AND NEW RESULTS [J].

BELKASIM, SO ;

SHRIDHAR, M ;

AHMADI, M .

PATTERN RECOGNITION, 1991, 24 (12) :1117-1138

[3]

BROWN C, 1992, P 11 ICPR HAG NETH A, V1, P21

[4] THE INTENSITY AXIS OF SYMMETRY AND ITS APPLICATION TO IMAGE SEGMENTATION [J].

GAUCH, JM ;

PIZER, SM .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (08) :753-770

[5] VISUAL-PATTERN RECOGNITION BY MOMENT INVARIANTS [J].

HU, M .

IRE TRANSACTIONS ON INFORMATION THEORY, 1962, 8 (02) :179-&

[6]

KELLY MF, 1994, TRCIM9412 MCGILL U

[7]

KHOLER W, 1944, P AM PHILOS SOC, V88, P269

[8]

LACASCIA M, P ICASSP 96

[9]

Papoulis A., 1984, Probability, Random Variables and Stochastic Processes, V2nd

[10] CONTEXT-FREE ATTENTIONAL OPERATORS - THE GENERALIZED SYMMETRY TRANSFORM [J].

REISFELD, D ;

WOLFSON, H ;

YESHURUN, Y .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 1995, 14 (02) :119-130

← 1 2 →