An Intelligent CNN-Based System for Automated Crop Disease Diagnosis and Farmer Assistance

Abstract

Agriculture constitutes a foundational pillar of the Indian economy, yet crop diseases remain one of the most persistent threats to agricultural productivity, particularly for smallholder farmers who lack immediate access to plant pathology expertise. To bridge this critical gap, the present work proposes Smart Crop Doctor, an intelligent web-based platform that leverages Artificial Intelligence to perform automated detection of crop diseases. Within this framework, users submit photographs of plant foliage, which are subsequently analyzed by a trained Convolutional Neural Network (CNN) capable of recognizing pathological conditions across 15 distinct disease categories spanning tomato, potato, and bell pepper cultivars. A dedicated input validation mechanism is incorporated to ascertain whether a submitted photograph genuinely depicts leaf tissue, thereby filtering out extraneous objects such as rocks or paper-based documents. Upon successful identification, the platform furnishes comprehensive output including disease characterization, recommended treatment protocols, and guidance on both organic and chemical fertilizer application, in addition to broader agronomic advisory content. Beyond disease diagnosis, the system integrates a suite of ancillary services: a%, confirming that the system delivers dependable performance suited to practical deployment in agricultural settings.

Plant phenotyping relevance

植物葉の画像から病害状態をCNNで推定する診断システムが研究の中心であり、植物病害フェノタイピング手法・プラットフォームに該当する。

Code and data availability

The paper describes a CNN crop-disease system trained on PlantVillage data, but provides no authors' public dataset, code, model checkpoint, or supplement URL. PlantVillage is cited prior work, and other URLs (OpenWeatherMap, OpenRouter, Flask, React, i18next) are generic third-party tools, not paper-specific assets.

No evidence-backed public reproduction asset is currently recorded.