Author : M. Christy Rama 1
Date of Publication :31st December 2017
Abstract: Remote sensing image classification plays a vital role in a wide range of applications and classifies the multispectral remotely sensed image into various land covers such as urban, vegetation, forest, water, etc., Feature extraction is an important step in multispectral remote sensing image classification before classifying the image. In the case of classification of remotely sensed images, colour and texture models should have the capacity of capturing and discriminating even minute pattern differences. In this paper, features are extracted using opponent colour texture pattern with different color space histograms. HSV and LUV color histogram and the opponent patterns in the feature space are used to train a random forest classifier. The performance can be evaluated based on several metrics such as accuracy, specificity, sensitivity and f-score. An IRS LISS IV orthorectified dataset is used as the input image for this experiment.
Reference :
-
- Jenicka and A. Suruliandi, “Texture based land cover classification algorithm using gabor wavelet and anfis classifier”, Ictact journal on image and video processing, Vol.6, 2016.
- Matti Pietik.inen, Topi M.enp and Jaakko Viertola, “Color Texture Classification with Color Histograms and Local Binary Patterns” University of Oulu, Finland
- Monika Deswal and Neetu Sharma, “A Fast HSV Image Color and Texture Detection and Image Conversion Algorithm”, International Journal of Science and Research (IJSR) Vol.3 Issue 6, 2014.
- Lakshmi N. Kantakumar and Priti Neelamsetti, “Multitemporal land use classification using hybrid approach”, The Egyptian Journal of Remote Sensing and Space Sciences, Elsevier, vol. 18, pp.289–295, 2015.
- Claudio Cusano, Paolo Napoletano and Raimondo Schettini, “Combining local binary patterns and local color contrast for texture classification under varying illumination”, Optical Society of America, Vol. 31, No. 7, 2014.
- Mansi Saraswat, Anil Kumar Goswami and Aastha Tiwari, “Object Recognition Using Texture Based Analysis”, International Journal of Computer Science and Information Technologies, Vol. 4 (6), pp. 775-782, 2013.