Welcome to the InfoSci Platform
Reference Hub3
Performance Analysis of Anisotropic Diffusion Based Colour Texture Descriptors in Industrial Applications

Performance Analysis of Anisotropic Diffusion Based Colour Texture Descriptors in Industrial Applications

Prakash S. Hiremath, Rohini A. Bhusnurmath
Copyright: © 2017 |Volume: 7 |Issue: 2 |Pages: 14
ISSN: 2155-6997|EISSN: 2155-6989|EISBN13: 9781522514404|DOI: 10.4018/IJCVIP.2017040104
Cite Article Cite Article

MLA

Hiremath, Prakash S., and Rohini A. Bhusnurmath. "Performance Analysis of Anisotropic Diffusion Based Colour Texture Descriptors in Industrial Applications." IJCVIP vol.7, no.2 2017: pp.50-63. http://doi.org/10.4018/IJCVIP.2017040104

APA

Hiremath, P. S. & Bhusnurmath, R. A. (2017). Performance Analysis of Anisotropic Diffusion Based Colour Texture Descriptors in Industrial Applications. International Journal of Computer Vision and Image Processing (IJCVIP), 7(2), 50-63. http://doi.org/10.4018/IJCVIP.2017040104

Chicago

Hiremath, Prakash S., and Rohini A. Bhusnurmath. "Performance Analysis of Anisotropic Diffusion Based Colour Texture Descriptors in Industrial Applications," International Journal of Computer Vision and Image Processing (IJCVIP) 7, no.2: 50-63. http://doi.org/10.4018/IJCVIP.2017040104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

A novel method of colour texture analysis based on anisotropic diffusion for industrial applications is proposed and the performance analysis of colour texture descriptors is examined. The objective of the study is to explore different colour spaces for their suitability in automatic classification of certain textures in industrial applications, namely, granite tiles and wood textures, using computer vision. The directional subbands of digital image of material samples obtained using wavelet transform are subjected to anisotropic diffusion to obtain the texture components. Further, statistical features are extracted from the texture components. The linear discriminant analysis is employed to achieve class separability. The texture descriptors are evaluated on RGB, HSV, YCbCr, Lab colour spaces and compared with gray scale texture descriptors. The k-NN classifier is used for texture classification. For the experimentation, benchmark databases, namely, MondialMarmi and Parquet are considered. The experimental results are encouraging as compared to the state-of-the-art-methods.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.