You are here

Grey level co-occurrence integrated algorithm (GLCIA): a superior computational method to rapidly determine co-occurrence probability texture features

TitleGrey level co-occurrence integrated algorithm (GLCIA): a superior computational method to rapidly determine co-occurrence probability texture features
Publication TypeJournal Article
Year of Publication2003
AuthorsClausi, D. A., and Y. Zhao
JournalComputers & Geosciences
Volume29
Pagination837 - 850
ISSN0098-3004
Keywordstexture analysis
Abstract

A critical shortcoming of determining co-occurrence probability texture features using Haralick's popular grey level co-occurrence matrix (GLCM) is the excessive computational burden. In this paper, the design, implementation, and testing of a more efficient algorithm to perform this task are presented. This algorithm, known as the grey level co-occurrence integrated algorithm (GLCIA), is a dramatic improvement on earlier implementations. This algorithm is created by integrating the preferred aspects of two algorithms: the grey level co-occurrence hybrid structure (GLCHS) and the grey level co-occurrence hybrid histogram (GLCHH). The GLCHS utilizes a dedicated two-dimensional data structure to quickly generate the probabilities and apply statistics to generate the features. The GLCHH uses a more efficient one-dimensional data structure to perform the same tasks. Since the GLCHH is faster than the GLCHS yet the GLCHH is not able to calculate features using all available statistics, the integration of these two methods generates a superior algorithm (the GLCIA). The computational gains vary as a function of window size, quantization level, and statistics selected. Using a variety of test parameters, experiments indicate that the GLCIA requires a fraction (27-54%) of the computational time compared to using the GLCHS alone. The GLCIA computational time relative to that of the standard GLCM method ranges from 0.04% to 16%. The GLCIA is a highly recommended technique for anyone wishing to calculate co-occurrence probability texture features, especially from large digital images.

URLhttp://www.sciencedirect.com/science/article/pii/S009830040300089X
DOI10.1016/S0098-3004(03)00089-X