Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/3999
Title: A New Approach for Leaf Disease Detection using Multilayered Convolutional Neural Network
Authors: Shukla, Vivek
Rani, Sweta
Mohapatra, Ramesh Kumar
Keywords: Plant Leaf Disease Detection
Images Processing
CNN
Agriculture
Deep Learning
Issue Date: Mar-2023
Citation: 3rd International Conference on Artificial Intelligence and Signal Processing(AISP'23), VIT-AP University, Vijayawada, India, 18-20 March 2023
Abstract: Leaf diseases reduce agricultural yield by 35% annually in India, where agriculture is the main sector. Manual detection of the type of disease present in leaves takes a long time since laboratories lack the necessary tools and expertise to recognise early leaf diseases. Diseases include early blight, late blight, black root, bacterial spot, mould leaf, healthy leaf, etc. Automated leaf disease detection systems are beneficial for spotting disease symptoms on plant leaves as soon as they appear, which helps to ease the time-consuming process of monitoring large agricultural farms. Recent advances in deep learning (DL) and computer vision models have highlighted the importance of developing autonomous leaf disease detection algorithms based on visual symptoms on leaves. The fundamental goal of the proposed model is to tackle the problem of leaf disease diagnosis using the most basic strategy while utilising the fewest computer resources to generate results comparable to state-of-the-art techniques. We used the multilayered architecture of convolutional neural networks (CNN) to identify and overcome leaf diseases. When compared to existing techniques, our proposed method can successfully train an image classification model to achieve 98.5% accuracy.
Description: Copyright belongs to proceeding publisher
URI: http://hdl.handle.net/2080/3999
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2023_AISP_Shukla_ANew.pdf990.48 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.