PCDRN: A Light Patch Based Attention U-Net for Plant Disease Detection in Modern Agriculture using Deep Learning

Read full text Summarise with VIRAT
Authors: V. Asha Merlin, P. L. Chithra
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Detecting plant diseases quickly is crucial for maintaining good crop yields and sustainable farming.Current approaches often depend on manual inspection or heavy convolutional neural networks that are computationally expensive and too large to run on IoT devices.To address these issues, this proposed work intro-duces PCDRN (Patch-based Channel Depth Refinement Network), an innovative lightweight enhanced Attention U-Net framework for plant disease detection in modern agriculture.This proposed work includes a Channel Excitation and Attention Unit (CEAU) to highlight disease-specific channels, Depth wise Separa-ble Convolutions for efficient feature extraction, and a Patch sampling method for recognizing discriminatively miserable patches in leaf images.Multiscale feature fusion has been rendered easier through the encoder-decoder architecture, which also ensures a low number of parameters with high inference efficiency.Findings from a dataset encompassing 19 distinct crop diseases reveal that PCDRN sur-passes existing techniques with its efficient network architecture, attaining a test accuracy of 95.79% and a significantly reduced parameter size ( 0.97MB)

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Industrial Vision Systems and Defect Detection

Publication details

Journal / source
Advances in intelligent systems research/Advances in Intelligent Systems Research
Pages
927–938
Publication date
1 April 2026
Language
EN
Document type
Book chapter