Intuitionistic Fuzzy Representation of Plant Images captured using Unmanned Aerial Vehicle for Measuring Mango Crop Health

The bacterial, viral, or fungal plant diseases are still taking a heavier toll on food production in developing countries like India. India loses, almost, 35% of the annual crop yield due to plant diseases. Early detection of plant diseases remains difficult due to the lack of lab infrastructure and expertise. Though in the past three decades, there have been marked improvements in agricultural production with the aid of disease-resistant methods to pause the significant reduction in both the quantity and quality of needed items.The major focus of this work is to identify the mango crop health issues at an earlier stage so that the diseases can be recognized using the Intuitionistic fuzzy set (IFS) approach over traditional segmentation techniques.The IFS method is used to compare with conventional segmentation techniques such as K-means clustering, Otsu's thresholding, region growing, and Felzenswalb segmentation to achieve the best results in the segmentation of the diseased area on the crop.As the Intuitionistic fuzzy logic allows a certain amount of incomplete information, the imprecision in the grey level definitions of UAV crop images can be accounted for in defining the delicacy of boundaries of disease-affected areas. Initially, all the experimental UAV images are pre-processed and segmented by using four types of segmentation techniques.The experimental results were obtained by the conventional segmentation techniques and intuitionistic fuzzy set approach as well. The experimental result shows the best visible strained region (around 95-98% affected area) from UAV captured field-area images along with statistical comparing parameters.This also infers the strength of IFS to handle disease complications in the crop which can further help farmers of India to increase their yield production.