Texture image segmentation based on estimating the local statistical features
- Authors: Kuprijanov A.V.1
-
Affiliations:
- Image Processing Systems Institute of the RAS
- Issue: Vol 7, No 2 (2008)
- Pages: 245-251
- Section: CONTROL, COMPUTER SCIENCE AND INFORMATION SCIENCE
- URL: https://journals.ssau.ru/vestnik/article/view/597
- DOI: https://doi.org/10.18287/2541-7533-2008-0-2(15)-245-251
- ID: 597
Cite item
Full Text
Abstract
This work is aimed at studying the efficiency of the features based on texture energy measures when solving the image segmentation problem. An algorithm for feature space generation based on the texture energy measures is proposed. The texture features are used for segmentation of diagnostic crystallogram images. Using test texture images, the segmentation quality is estimated and the feature efficiency is studied when solving the texture segmentation problem.
About the authors
A. V. Kuprijanov
Image Processing Systems Institute of the RAS
Author for correspondence.
Email: akupr@ssau.ru
Russian Federation