Image segmentation based on colour and texture features

C. Mythili and V. Kavitha

International Journal of Enterprise Network Management, 2016, vol. 7, issue 3, 272-283

Abstract: A new segmentation approach is proposed in this paper which combines colour texture features to get accurate segmentation. The input images obtained from Berkeley databases are in RGB colour model. The colour image is transformed from RGB colour space to lab colour space. The statistical colour features are extracted from lab colour space. The fuzzy texture unit is determined by the extraction of local texture information from each pixel. The combined feature extraction of colour and texture are implemented using effective robust kernelised fuzzy C-means (ERKFCM) clustering strategy. It is concluded that ERKFCM method has outperformed quantitatively and qualitatively results in terms of root mean square error (RMSE), Pearson correlation coefficient, structural similarity (SSIM) and time taken when compared to the existing methods in segmentation.

Keywords: colour features; image segmentation; texture features; ERKFCM; fuzzy C-means clustering; feature extraction. (search for similar items in EconPapers)
Date: 2016
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=78972 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijenma:v:7:y:2016:i:3:p:272-283

Access Statistics for this article

More articles in International Journal of Enterprise Network Management from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().