By Topic

Evaluation of texture methods for image analysis

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Sharma, M. ; Dept. of Comput. Sci., Exeter Univ., UK ; Singh, S.

The evaluation of texture features is important for several image processing applications. Texture analysis forms the basis of object recognition and classification in several domains. There is a range of texture extraction methods and their performance evaluation is an important part of understanding the utility of feature extraction tools in image analysis. In this paper we evaluate five different feature extraction methods. These are autocorrelation, edge frequency, primitive-length., Law's method, and co-occurrence matrices. All these methods are used for texture analysis of Meastex database. This is a publicly available database and therefore a meaningful comparison between the various methods is useful to our understanding of texture algorithms. Our results show that the Law's method and co-occurrence matrix method yield the best results. The overall best results;are obtained when we use features from all five methods. Results are produced using leave-one-out method.

Published in:

Intelligent Information Systems Conference, The Seventh Australian and New Zealand 2001

Date of Conference:

18-21 Nov. 2001