Real-time defect inspection of textured surfaces

被引：32

作者：

Baykut, A ^{[1
]}

Atalay, A ^{[1
]}

Erçil, A ^{[1
]}

Güler, M ^{[1
]}

机构：

[1] Bogazici Univ, Dept Ind Engn, TR-80815 Bebek, Turkey

来源：

REAL-TIME IMAGING | 2000年 / 6卷 / 01期

关键词：

Defects - Digital signal processing - Inspection - Markov processes - Mathematical models - Real time systems;

D O I：

10.1006/rtim.1998.0153

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Texture analysis plays an important role in the automated visual inspection of textured images to detect their defects. For this purpose, model-based and feature-based methods are implemented and tested for textile images in a laboratory environment. The methods are compared in terms of their success rates in determining the defects. The Markov Random Field model is applied on different DSP systems for real-time inspection. (C) 2000 Academic Press.

引用

页码：17 / 27

页数：11

共 21 条

[11]

FUKUNAG AK, 1990, INTRO STAT PATTERN R

[12]

GUL E, 1995, P IEEE SIU A, VA, P141

[13]

RAO TR, 1990, TAXONOMY TEXTURE DES

[14]

REED TR, 1993, CVGIP-IMAG UNDERSTAN, V57, P359, DOI 10.1006/ciun.1993.1024

[15] TEXTURE MEASURES FOR CARPET WEAR ASSESSMENT [J].

SIEW, LH ;

HODGSON, RM ;

WOOD, EJ .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1988, 10 (01) :92-105

[16] LOCAL FREQUENCY FEATURES FOR TEXTURE CLASSIFICATION [J].

STRAND, J ;

TAXT, T .

PATTERN RECOGNITION, 1994, 27 (10) :1397-1406

[17]

*TEX INSTR INC, 1991, TMS320 FLOAT POINT D

[18]

*TEX INSTR INC, 1993, TMS320C4X US GUID

[19]

Tuceryan M., 1993, HDB PATTERN RECOGNIT

[20] TEXTURE ANALYSIS ANNO 1983 [J].

VANGOOL, L ;

DEWAELE, P ;

OOSTERLINCK, A .

COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1985, 29 (03) :336-357

← 1 2 3 →