Tomato leaf disease detection using cnn

Computer Engineering

Abstract— The detection of tomato leaf is the critical task in agriculture, as it can help to prevent crop loss and increase yields. It is the most crucial and widely utilised crops in the world, Considering the quantity and quality of the yield can be greatly impacted by leaf diseases. These diseases cannot only affect the agricultural industry, but also human health and financials. One of the major challenges in managing leaf diseases is detecting infected plants in the early stages, as diseases can spread rapidly and infest entire farms if left untreated. These systems typically involve capturing images of tomato leaves, pre-processing the images to enhance visual features, and using machine learning techniques to develop illness detection models. CNN is one of the most well-known and effective image classificationtechniques, and it has been effectively used to address a number of tomato disease- related issues including object identification, image classification, and semantic segmentation. The suggested technique makes use of image processing methods and a machine learning classifier, specifically a CNN, to diagnose the disease. The results show good accuracy in disease identification using the suggested approach, which uses a dataset of tomato leaf pictures to test performance. The proposed method can be a useful early detection tool and management of tomato leaf diseases, potentially leading to increased crop yields and reduced use of pesticides. The study also aims to implement a CNN specifically for the application of plant disease detection in tomato leaves.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.