Machine Learning Based Novel Hybrid Approach for Plant Leaf Disease Detection and Feature Extraction Along with Statistical Analysis Using Big Data
Year: 2025
Type: article
Abstract: Plant diseases pose a serious threat to global food security and agricultural productivity [29]. They are commonly caused by pathogens such as viruses, bacteria, fungi, insects, rusts, and nematodes, with most infections affecting the stem and leaves of plants [2]. To address these challenges, researchers have applied various approaches including deep learning methods, image processing techniques, and machine learning algorithms. This study focuses on two main techniques: Canny Edge Detection (CED) and color-based feature extraction, selected after reviewing 43 research articles published in reputed journals. Additionally, Long Short-Term Memory (LSTM) networks were integrated with Canny Edge Detection to enable disease detection in videos and time-series data. For experimental evaluation, leaf samples from lady’s finger, brinjal, and tomato were tested. The proposed model demonstrated high accuracy: 99.55%, 99.10%, and 98.7% using Canny Edge Detection; 99.62%, 99.23%, and 99.13% with color-based feature extraction; and 99.48%, 99.50%, and 99.39% using the hybrid model. This digital plant disease detection framework can provide significant support to farmers and cultivators by enabling timely and accurate identification of crop diseases.
DOI: 10.14419/0726ga64
Institution: Periyar University
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W7117918532
FWCI:
Cites:
Cited by:
Related to: