Work

Areca-CEDNet: Arecanut Plant Disease Classification Using Convolutional Encoder–decoder Network

Year: 2026
Type: article
Abstract: Plant disease classification is crucial in agriculture for ensuring food security and sustainability.Traditional methods require expert knowledge, are time-consuming, and does not appropriate for large-scale analysis.Deep Learning (DL)-assisted image classification techniques offer effective performance in identifying plant diseases.This research proposes the arecanut leaf disease classification approach called Areca-Convolutional Encoder-Decoder Network (Areca-CEDNet) architecture, which builds on and extends the concepts of the CED-Net and the Temporal Convolutional Network (TCN).The study uses two datasets: a private Arecanut and the publicly available PlantVillage dataset, for implementing the proposed approach.A Visual Geometric Group-16 (VGG16) architecture extracts both low-and high-level features.Experimental results demonstrate that the proposed Areca-CEDNet method achieves an impressive accuracy of 99.93% on Arecanut dataset and 99.65% on PlantVillage dataset.This approach makes a significant contribution to sustainable Artificial Intelligence (AI) for plant disease detection by improving model generalization and allowing precise classification over diverse classes with smaller image sizes in DL-based agricultural applications.
Language: English
Subfield: Plant Science
Open Access status: hybrid
OpenAlex ID: W7204087470
FWCI:
Cites: 30
Cited by:
Related to: 10