Statistical Texture and Normalized Discrete Cosine Transform-Based Automatic Soya Plant Foliar Infection Cataloguing

Abstract

Soya beans are an important cash-crop, grown worldwide because of their use as a raw material in various industries involved in the production of sauces, mayonnaises, chocolates, baby-food, bakery, etc. Soya bean products are not only consumed by humans, but by pets too. They are also used as an alternative to fossil fuel in the form of bio-diesel. The research work presented in this paper highlights the problems associated with soya bean cultivation, and the reasons for yield loss in developing countries like India, China and others. In this paper, the colour image sensing and processing based infected lesion detection method is proposed. Structural texture and normalized DCT-based feature descriptors for refined lesion histograms have been developed. Hybrid feature descriptors have been used as the input samples for four major soya plant foliar infections. The classification and testing accuracies are quite encouraging, and are above 89.9% and 92.3% respectively. Also, the results have been compared for only ST, ST-DCT, and ST-NDCT feature-based methods, and the use of ST-NDCT descriptors in cataloguing systems is suggested. Moreover, the method can classify four diseases, which creates confusion because of similar colour shades, and irregular and random shapes and sizes of lesions.