Study on the potential of combined GLCM features towards medicinal plant classification

The gray level co-occurrence matrix (GLCM) is widely used for textural feature extraction. The features obtained from GLCM matrix are subjected to the classifiers for the purpose of identification and classification. In this paper the combinations between different features, obtained from GLCM matrix, are studied. For experiments, the leaves of medicinal plants are considered, as proper identification of medicinal plant is crucial for appropriate utilization of their medicinal values. Two popular Indian medicinal plants, namely, Neem and Tulsi have been considered for classification using back propagation multi layer perceptron (BP-MLP) neural network classifier. Beside combination the further classification improvements may be achieved using different preprocessing techniques, which have also been experimented. The results show that preprocessed combined GLCM features can provide higher classification rate compared to raw single GLCM features.