Authors: A. Suruliandi; S. Jenicka
Addresses: Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli 627012, Tamil Nadu, India ' Einstein College of Engineering, Tirunelveli 627007, Tamil Nadu, India
Abstract: Texture is a significant spatial property that precisely captures patterns in a satellite image. Texture-based classification plays a vital role in land use-land cover application of remotely sensed images. In this paper, texture features were extracted using Multivariate Local Binary Pattern (MLBP), Multivariate Local Texture Pattern (MLTP), Multivariate Advanced Local Binary Pattern (MALBP), wavelet and Gabor wavelet. Texture-based classification was performed on IRS-P6, LISS-IV data, and the results were evaluated based on error matrix, classification accuracy and kappa statistics. From the experiments, it was found that MLTP outperformed other texture models.
Keywords: texture classification; feature extraction; Gabor wavelet; signal processing; remote sensing; error matrix; classification accuracy; kappa statistics; local binary pattern; LBP; local texture pattern; LTP; texture models; modelling; satellite images.
International Journal of Signal and Imaging Systems Engineering, 2015 Vol.8 No.4, pp.260 - 272
Available online: 10 Jul 2015Full-text access for editors Access for subscribers Purchase this article Comment on this article