Detection of potato leaf disease using deep learning approaches

Abstract

Throughout the globe, potatoes are one of the most important food crops. Potato farming has grown quite common across Bangladesh in the previous few decades. Plants of potatoes cannot grow properly under several conditions. This plant has obvious illnesses in its leaf area. Potato Early Blight (EB) , Late Blight (LB), Septoria blight etc. are both prevalent and well-known leaf diseases of potato crops will target potato plants and display their symptoms in the affected leaves. Whenever these pandemics are identified in their early stages and appropriate intervention is done, the landowner will not be concerned about suffering significant financial losses. That being said, improved crop productivity would result from early detection of these illnesses. Image processing is the greatest alternative for finding and assessing these illnesses in order to fix the issue at hand. This work puts forward a technology that uses deep learning and image processing to recognize and categorize potato diseases of the leaves. In this particular work, there have been use three types of classes like: Early blight, Late blight and healthy leaf with using of deep learning models. Four models use for predicting and detecting potato leaf classification MobilenetV3 large, EfficientNetB7, MobileNetV2 and RestNet50. The MobileNetV3 Large model emulate provides a reliability of 99.67% within them. my suggested method thus opens the door to autonomous plant-leaf illness recognition. Ultimately, the CNN InceptionV3 model is used for classification with the goal to identify potato leaves to create web prototype