Identification of Plant Leaf Disease Using CNN and Image Processing

Abstract

Agriculture is an important sector for the growing people of the world to fulfil the minimum requirements of food. Identifying plant infection in the agricultural sector is complex. If the detection is wrong, there is more damage to crop production and economic loss of the market. Leaf infection identification need a large number of labors, command of plant disorders and requires a lot of observing time. Therefore, this analysis explains detection of plant leaf disease by utilizing CNN and image processing. Alex Net and ResNet-50 are Convolutional Neural Network (CNN) models. First, this method is performed on Kaggle datasets of potato and tomato plants to examine the characteristics of an infected leaves. Then, feature extraction and categorization method is executed on dataset pictures to observe leaf disorders using Alex Net and ResNet-50 models by executing image processing. Observational outputs demonstrate potential of described method, in which it reaches a complete accuracy of 98% and 95% of Alex Net and ResNet50. The output shows that described model particularly predicts defective plant leaves from healthy leaf images.

Plant phenotyping relevance

植物葉の病害状態を画像から推定するCNN・画像処理手法が研究の中心であり、精度評価も行っているため含める。

Code and data availability

The paper uses a Kaggle dataset of tomato/potato leaf images and MATLAB-based AlexNet/ResNet-50 analysis, but provides no dataset URL, no author code/model availability statement, and no supplement with data or scripts. The Kaggle dataset is referenced only generically without a link or identifier, so no paper-specific

No evidence-backed public reproduction asset is currently recorded.