Image Texture Feature Extraction Method Based on Regional Average Binary Gray Level Difference Co-occurrence Matrix

Jian Yang,Jingfeng Guo

doi:10.20870/ijvr.2011.10.3.2823

Abstract

Texture feature is a measure method about relationship among the pixels in local area, reflecting the changes of image space gray levels. This paper presents a texture feature extraction method based on regional average binary gray level difference co-occurrence matrix, which combined the texture structural analysis method with statistical method. Firstly, we calculate the average binary gray level difference of eight-neighbors of a pixel to get the average binary gray level difference image which expresses the variation pattern of the regional gray levels. Secondly, the regional co-occurrence matrix is constructed by using these average binary gray level differences. Finally, we extract the second-order statistic parameters reflecting the image texture feature from the regional co-occurrence matrix. Theoretical analysis and experimental results show that the image texture feature extraction method has certain accuracy and validity

Highlights

By investigating the traditional gray level co-occurrence matrix which constructs based on pixels, we discover a pair of drawbacks is: (1) it cannot express the change information of the image regional exactly, (2) it is unable to express the spatial relationship of different local texture patterns in the image
This paper presents a novel method based on the idea of Local Binary Patterns (LBP) operator, and proposes a new coding rule which is Regional Average Binary Gray Level Difference (RABGLD)
This paper aims at constructing the co-occurrence matrix based on distance and direction in the different RABGLD patterns, which is called regional co-occurrence matrix

Summary

INTRODUCTION

It is a property of areas, and consists of sub-patterns which are related to the pixel distribution in a region. Texture is a contextual property and its definition must involve gray values in a spatial neighborhoods

THE CALCULATION OF REGIONAL AVERAGE BINARY GRAY LEVEL DIFFERENCE

Calculating the Regional Binary Gray Level Value

CONSTRUCTING REGIONAL CO-OCCURRENCE MATRIX

TEXTURE FEATURES EXTRACTED FROM REGIONAL CO-OCCURRENCE MATRIX

The first image group

EXPERIMENTAL RESULTS AND ANALYSIS