Interest of the Multi-Resolution Analysis based on the Co-occurrence Matrix for Texture Classification

被引：0

作者：

Ben Othmen, M. ^{[1
]}

Sayadi, A. ^{[2
,3
]}

Fnaiech, F. ^{[2
,3
]}

机构：

[1] ESSTT, Res Grp SICISI, 5 Av Taha Hussein, Tunis 1008, Tunisia

[2] ESSTT, SICISI, Tunis 1008, Tunisia

[3] Univ Picardie, LTI Grp, F-80000 Amiens, France

来源：

2008 IEEE MEDITERRANEAN ELECTROTECHNICAL CONFERENCE, VOLS 1 AND 2 | 2008年

关键词：

Classification; Wavelet; Co-occurrence; Euclidian Distance; Classifier; Texture;

D O I：

暂无

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Wavelet transform provides several important characteristics which can be used in a texture analysis and classification. In this work, an efficient texture classification method, which combines concepts from wavelet and co-occurrence matrices, is presented. An Euclidian distance classifier is used to evaluate the various methods of classification. A comparative study is essential to determine the ideal method. Using this conjecture, we developed a novel feature set for texture classification and demonstrate its effectiveness.

引用

页码：831 / +

页数：2

共 14 条

[1]

AHMED K, 2005, INT C SETIT MARS SOU

[2]

Amet Ahmet Latif, EFFICIENT METHOD TEX

[3]

Brodatz P., 1956, TEXTURES PHOTOGRAPHI

[4]

GERMAIN C, 1997, THESIS U BORDEAUX 1

[5] THE TWO-DIMENSIONAL ADAPTIVE LMS (TDLMS) ALGORITHM [J].

HADHOUD, MM ;

THOMAS, DW .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (05) :485-494

[6]

HELA SM, 2005, INT C SCI EL TECHN I

[7]

Kara B., 2003, IJCI PROC INT C SIGN, V1, P159

[8] An efficient method for texture defect detection:: sub-band domain co-occurrence matrices [J].

Latif-Amet, A ;

Ertüzün, A ;

Erçil, A .

IMAGE AND VISION COMPUTING, 2000, 18 (6-7) :543-553

[9]

Materka M. Strzelecki, 1998, B11 COST TU LODZ I E

[10]

MJAHED M, C JTEA 2000 NAB HAMM, P89

← 1 2 →