Novel approach for quantification for severity estimation of blight diseases on leaves of tomato plant

Abstract

AbstractThis study uses digital image processing and machine learning to quantify the infection patterns on tomato leaves due to blight diseases. Quantification, also known as severity measurement, is a technique to determine how much a leaf is diseased by calculating a numeric value. This value could be a fraction representing how much the diseased region is present on the leaf compared to the entire leaf region, or it can be a percentage value too. There are two main approaches to measuring disease severity; the first technique involves visual estimation using references like standard area diagrams. The second approach involves taking a digital image of the leaf, separating the diseased regions from the healthy regions, and then calculating the area of those two regions. The approach we took is similar. We first took the digital image and segmented the diseased and healthy regions. For quantification, we calculated the ratio of total pixels representing the diseased region to the total number of pixels representing the leaf. While finding ways to improve the accuracy of the segmentation algorithm, we also discovered our segmentation technique which automatically segments the diseased regions of the leaves from the healthy areas using k‐means clustering. The clustering‐segmentation algorithm did give good results for the sample images to which it was applied. The main thing about the clustering‐segmentation algorithm is that it tends to be automatic compared to some of the semi‐automatic segmentation approaches that have been discovered till now. We could reproduce the validated quantification results as other authors achieved in the recent work, which also validated our methodology.