Comparative Analysis on Segmentation Approaches for Plant Leaf Disease Detection
DOI:
https://doi.org/10.26438/ijcse/v6i5.412418Keywords:
Leaf disease, FCM, ABC, k-means clustering, GLCM, Support Vector Machine, K-Nearest Neighbor ApproachAbstract
Plant pathology is the scientific analysis of plant diseases caused by pathogens and different environmental conditions. The leaf is one of the significant plant parts which highlight the presence of diseases. Existing methods use spectroscopic techniques to detect the diseases present in plants. These techniques are very expensive and can only be utilized by trained persons only. The method mentioned in this paper is an easy and cost-effective way which utilizes the leaf image of the plant. This input image is subjected to segmentation of disease part, feature extraction and classification in order to identify the disease. The main objective of this paper is to compare the clustering approaches FCM, Artificial Bee Colony and K-Means which are useful in disease part segmentation and to identify the best approach yields accurate results for identifying the plant disease. This work utilizes the GLCM, Run Length, Color Moment and Color Histogram features for feature extraction. Once these features are extracted from the segmented disease part, the disease present in the leaf is identified using the KNN (K- Nearest Neighbor) technique. The experimental result shows that the Artificial Bee Colony approach segments the diseased part of the leaf in a better way than the other two approaches.
References
Shiddalingappa Kadakol, Jyothi B Maned, “Intelligence System for leaf Extraction and disease Diagnostic”, International Journal of computer sciences and Engineering “ Vol.4, Issue 3, May 2016, PP.62-66.
Aakanksha Rastogi, Ritika Arora, and Shanu Sharma,” Leaf Disease Detection and Grading using Computer Vision Technology &Fuzzy Logic” (SPIN) 2015, pp 500-505.
N. Swetha and N. Sasirehka,“Prediction of Leaf Disease uses Segmentation with Hierarchical Clustering”, International Journal of Engineering Technology, Science and Research, Vol. 3, Issue.6, June 2016, pp. 37-42.
Dubey S R., Dixit P., Singh N. And Gupta, J P, “Infected Fruit Part Detection uses K-Means Clustering Segmentation Technique”, International Journal of Artificial Intelligence and Interactive Multimedia, Vol. 2, Issue.2, 2013, pp. 65-72.
Lange P S., Patil S A., Khot D S., Otari O D And Malakar U G, “Automatic Detection and Classification of Plant Disease through Image Processing”, International Journal of Advanced Research in Computer Science and Software Engineering, Vol.3, Issue.7, July 2013, pp. 798-801.
Sungkur R K., Baichoo S. And Poligadu A, 2013, “An Automated System to Recognize Fungi-caused Diseases on Sugarcane Leaves”, Proceedings of Global Engineering, Science and Technology Conference, Singapore, 3-4 Oct. 2013, pp. 1-11.
Jagadeesh D. Pujari, Rajesh Yakkundimath and Abdulmunaf S. Byadgi, “ International journal of signal Processing, Image Processing and Pattern Recognition, Vol.6, Issue.6 (2013).
Pp. 321-330.
Al-Bashish, D., M. Braik, and S. Bani-Ahmad. “Detection and classification of leaf diseases using K-means-based segmentation and neural networks based classification”. Information Tech. Journal, Vol 10, Issue 2, 2011, pp 267-275.
Bauer, S. D., F. Koch, W. Forstner. “The potential of automatic methods of classification to identify leaf diseases from multispectral images”. Precision Agriculture, Vol 12, Issue 3, 2011, pp 361-377.
Giuliano Armano and Mohammad Reza Farmani,” Clustering Analysis with Combination of Artificial Bee Colony Algorithm and k-Means Technique”, International Journal of Computer Theory And Engineering”, Vol.6.No.2, April 2014, pp. 141-145.
P. Mohanaiah*, P. Sathyanarayana**, L. GuruKumar,” Image Texture Feature Extraction Using GLCM Approach”, International Journal of Scientific and Research Publications, Volume 3, Issue 5, May 2013, pp. 1-5.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
