Techno Press
Techno Press

Computers and Concrete
  Volume 14, Number 3, September 2014 , pages 315-325
DOI: https://doi.org/10.12989/cac.2014...315
 

Automated segmentation of concrete images into microstructures: A comparative study
Mehran Yazdi and Katayoon Sarafrazi

 
Abstract
    Concrete is an important material in most of civil constructions. Many properties of concrete can be determined through analysis of concrete images. Image segmentation is the first step for the most of these analyses. An automated system for segmentation of concrete images into microstructures using texture analysis is proposed. The performance of five different classifiers has been evaluated and the results show that using an Artificial Neural Network classifier is the best choice for an automatic image segmentation of concrete.
 
Key Words
    microstructural analysis; image segmentation; FLD; KNN; artificial neural networks; SVM; bayesian classification; co-occurrence matrix; texture analysis
 
Address
Mehran Yazdi: Department of Electronics and Computer Engineering,Shiraz University, Shiraz, Iran

Katayoon Sarafrazi: Department of Electronics and Computer Engineering, Shiraz University, Shiraz, Iran
 
Techno-Press: Publishers of international journals and conference proceedings.       Copyright © 2026 Techno Press
P.O. Box 33, Yuseong, Daejeon 305-600 Korea, Tel: +82-42-828-7996, Fax : +82-42-828-7997, Email: admin@techno-press.com