Machine Learning Based Novel Hybrid Approach for PlantLeaf Disease Detection and Feature Extraction Alongwith Statistical Analysis Using Big Data

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.