This paper focuses on classification of varieties of plants’, animals’ and minerals’ origin fabric materials from images. The morphological operations, namely, erosion and dilation are used. ANN classifier is used to predict the classification rates and the rates of 89%, 87% and 88% are obtained for plants’, animals’ and minerals’ origin fabric images respectively. The overall classification rate of 88% is obtained. 

The proposed work gives a comparative study of three different classifiers, namely, decision tree (DT), support vector machine (SVM) and artificial neural network (ANN) for variety classification of certain thin and thick fabric images. The textural features are used in the work. The overall classification rates of 85%, 86% and 94% are obtained for DT, SVM and ANN classifiers respectively. Better results for varieties of thick fabric images are obtained compared to the varieties of thin fabric images. Further, the ANN classifier has given good classification rate than DT and SVM classifiers. But, it is also observed that, DT classifier gives better results in case of varieties of thick fabric images. The work finds applications in apparel industry, cost estimation, setting the washing time, fashion design etc.