Color sensing and image processing-based automatic soybean plant foliar disease severity detection and estimation

Soybean is among one of the most important commercial crops, which is cultivated worldwide. The research work presented in this paper is focused on the problems associated with the cultivation and highlights the effect of various Soya plant foliar diseases on its yield. It has been presented a fully automatic disease detection and level estimation system which is based on color image sensing and processing. Various new parameters, namely Disease-Severity-Index (DSI), Infection-Per Region (IPR), and Disease-Level-Parameter (DLP) for measuring the disease severity level and level-classification have also been formulated and derived. The proposed method has been tested on a real database of Soya leaves collected between July 2012 and September 2012 and found to be at an excellent methodology for the purpose mentioned above. Experimentation has shown that the method is superior to the methods proposed by Cui et al. (Sens & Instrumen. Food Qual. 3(1),49-56, 2009) & (Biosyst Eng. 107(3), 186-193, 2010) in terms of adopted methodology and measuring parameters used.