DETECTION OF DAMAGED LEAF USING CONVOLUTIONAL NEURAL NETWORK

Authors:

M. Senthamil Selvi,K. Deepa,Mrs. S. Jansirani Sankar,

DOI NO:

https://doi.org/10.26782/jmcms.spl.7/2020.02.00012

Keywords:

CNN,Alexnet,Pesticides,Insecticides,MATLAB,

Abstract

In recent years, Deep Learning technologies are more popular and used in many fields like agriculture, healthcare, manufacturing etc. One of the areas in deep learning is image classification and the results are useful, successful with more accuracy. Deep learning algorithm for image classification is CNN (Convolutional Neural Network). This paper uses the leaf image dataset like Good leaf images, leaf with worms and leaf with insect images. It is very important to classify the leaf in the agriculture field to spray the pesticide or insectides. Sometimes, some leaves are good in particular areas; those areas need only water for growth. This paper deals with deep learning techniques such CNN, used to classify leaf images using MATLAB. The objectives of the work is to classify leaves as Good, Worms, Insects for better understanding and spray of Pesticides, Insecticides, this helps farm owners for better yield and it indirectly increases the economic growth of the country.

Refference:

I. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Adv. Neural Inf. Process. Syst., pp. 1–9, 2012.

II. H. Durmus¸ E. O. Gunes ¨ ¸ and M. Kırcı, “Disease detection on the leaves of the tomato plants by using deep learning”, In Agro-Geoinformatics, IEEE 6th International Conference on, pp. 1-5, 2017.
III. http://www.llojibwe.org/drm/greenteam/pesticides_Article.pdf

IV. https://in.mathworks.com/help/deeplearning/ug/transfer-learning-with-deep-network-designer.html

V. MelikeSardogan ;AdemTuncer ; YunusOzen, “Plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm,” 2018 3rd International Conference on Computer Science and Engineering (UBMK) on pp.382-385
VI. Y. Le Cun, Y. Bengio and G. Hinton, “Deep Learning”, Nature, vol. 521, pp. 436-444, 2015

View | Download