Image-Based Analysis for Identification of Plant Leaf Pathologics Using Deep Learning

Abstract

This project introduces a Convolutional Neural Network (CNN) as the proposed system for plant disease prediction, with a comparative analysis conducted against two existing models: Recurrent Neural Networks (RNN_GRU) and Artificial Neural Networks (ANN_MLP). The proposed CNN model is specifically designed to address the limitations of traditional approaches, such as lower accuracy and slower prediction times, particularly when handling complex image data. The system allows users to upload images of plant leaves, select the type of plant (e.g., potato, tomato, grape), and choose between RNN_GRU, ANN_MLP, or the newly developed CNN model for disease prediction. Additionally, users can run all three models simultaneously to compare their outputs, enabling a comprehensive evaluation of performance. Predictions are securely stored in a SQLite database, along with metadata such as confidence scores, prediction times, timestamps, and a unique group ID for efficient retrieval and management. Built using Flask, the application provides a professional-grade user interface with features like secure authentication, prediction history tracking, and deletion of past predictions. Comparative analysis demonstrates that the proposed CNN model significantly outperforms RNN_GRU and ANN_MLP in terms of accuracy, prediction speed, and overall reliability, making it a more effective tool for real-time agricultural applications. This advancement highlights the potential of CNNs in transforming agricultural practices by providing faster, more accurate, and reliable disease predictions, thereby contributing to improved crop health, reduced losses, and increased agricultural productivity.

Plant phenotyping relevance

植物葉画像から病害状態を推定するCNN手法を開発し、既存モデルとの精度・速度比較を行っているため、植物フェノタイピング手法が中心である。

Code and data availability

The paper describes a Flask-based plant disease prediction system (CNN, RNN_GRU, ANN_MLP) but provides no public dataset, image collection, code repository, trained model, or supplement with availability language. The dataset of plant leaf images is mentioned only generically ('data collection, where a dataset of plant

No evidence-backed public reproduction asset is currently recorded.