Increasing the discrimination power of the co-occurrence matrix-based features

被引：40

作者：

Gelzinis, A.

Verikas, A.

Bacauskiene, M.

机构：

[1] Halmstad Univ, Intelligent Syst Lab, S-30118 Halmstad, Sweden

[2] Kaunas Univ Technol, Dept Appl Econ, LT-3031 Kaunas, Lithuania

来源：

PATTERN RECOGNITION | 2007年 / 40卷 / 09期

关键词：

image texture; co-occurrence matrix; support vector machine;

D O I：

10.1016/j.patcog.2006.12.004

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 is concerned with an approach to exploiting information available from the co-occurrence matrices computed for different distance parameter values. A polynomial of degree n is fitted to each of 14 Haralick's coefficients computed from the average co-occurrence matrices evaluated for several distance parameter values. Parameters of the polynomials constitute a set of new features. The experimental investigations performed substantiated the usefulness of the approach. (c) 2007 Pattern Recognition Society. Published by Elsevier Ltd. All fights reserved.

引用

页码：2367 / 2372

页数：6

共 13 条

[1] MULTICHANNEL TEXTURE ANALYSIS USING LOCALIZED SPATIAL FILTERS [J].