M. Mohan, V. Vijayaganth and M. Naveenkumar, Department of CSE, KPR Institute of Engineering and Technology, Coimbatore, Tamilnadu, India.
Online First : 30 December 2020
Publisher Name : IJAICT India Publications, India.
Print ISBN : 978-81-950008-0-7
Online ISBN : 978-81-950008-1-4
Page :174-176
Abstract
Plant leaf diseases and ruinous bugs are a significant test in the horticulture area. Quicker and an exact forecast of leaf diseases in plant could assist with building up an early treatment strategy while extensively decreasing financial misfortunes. Current progressed advancements in profound learning permitted analysts to amazingly improve the presentation and exactness of article identification and acknowledgment frameworks. A profound learning-based way to deal with recognize leaf illnesses in various plants utilizing pictures of plant leaves. The picture handling ventures for plant illness recognizable proof incorporate obtaining of pictures, pre-preparing, division and highlight extraction. Focus in predominantly on the most used order systems in illness location of plants, for example, Convolutional Neural Network, Support Vector Machine, KNearest Neighbor, and Artificial Neural Network. It has been seen from the examination that advancement Convolutional Neural Network approach gives better precision contrasted with the conventional methodologies. Optimization based CNN convolution neural network the proposed framework can viably recognized various sorts of diseases with the capacity to manage complex situations from a plant's region.
Keywords
Deep learning, Convolutional Neural Network, Artificial Neural Network, Particle Swarm optimization (PSO).
Cite this article
M. Mohan, V. Vijayaganth and M. Naveenkumar, “Plant Leaf Diseases Prediction and Classification Using Optimization Based Convolution Neural Network”, Innovations in Information and Communication Technology, pp. 174-176, December 2020.
Copyright
© 2020 M. Mohan, V. Vijayaganth and M. Naveenkumar. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
