International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 13, No. 5, 8 Oct. 2021
Cover page and Table of Contents: PDF (size: 999KB)
Evaluation of Image Segmentation Algorithms for Plant Disease Detection
Full Text (PDF, 999KB), PP.14-26
Views: 0 Downloads: 0
Author(s)
Index Terms
Image processing, image segmentation, plant disease, plant disease classification
Abstract
Processing images efficiently may be influenced by some important factors which are the techniques chosen, the field of study and the quality of images. In this work, we study the field of agriculture with the focus on the early detection of plant diseases through image processing. To detect plant diseases such bacterial diseases, fungal diseases and virus, two main techniques exist: The traditional techniques provided by agricultural experts during visit on the field and the artificial techniques based on images processing algorithms. Since plantations are usually distant from the cities where experts are not easy to find, the artificial techniques incorporated in computer programs become suitable. The modern techniques used to analyse images rely on existing algorithms such as k-nearest neighbor, k-means clustering, fuzzy logic, genetic algorithm, neural networks, etc. Five main phases characterise the process of images analysis: image acquisition, pre-treatment, segmentation, feature extraction and classification. Amongst these phases, we particularly focus on the segmentation which allows to locate portions of leaf that are affected by a disease. Doing so, in this paper we propose a method to evaluate segmentation algorithms (k-means clustering, canny edge and k-nearest neighbor) on the diagnostic of diseases of three of the most cultivated plants (corn, potato, tomato) in the region of study. We study and compare performance values using the ROC-AUC of disease classification using the Support Vector Machine (SVM) algorithm. The obtained results show that the canny edge algorithm produces very poor performances on the family of solanaceae plants including potato. The k-nearest neighbour algorithm produces very poor performance due to the difficulty of choosing the k-value. Finally, the k-means algorithm makes it possible to obtain good prediction rates on all the chosen plants.
Cite This Paper
Paul DAYANG, Armandine Sorel KOUYIM MELI, " Evaluation of Image Segmentation Algorithms for Plant Disease Detection", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.13, No.5, pp. 14-26, 2021. DOI: 10.5815/ijigsp.2021.05.02
Reference
[1]H. J. Vala anf A.A. Baxi, “Review on Otsu Image Segmentation Algorithm”. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), vol. 2, issue 2, 2013.
[2]P. Sivakumar and S. Meenakshi,” A review on image segmentation techniques”, International Journal of Advanced Research in Computer Engineering & Technology, vol. 5, issue 3, 2016.
[3]M. Muhammad, “A Survey: Image Segmentation Techniques”, International Journal of Future Computer and Communication, vol. 3, no 2, pp. 89-93, Avril 2014.
[4]V. Kurama, S. Alla, R. Vishnu K, “Image Semantic Segmentation Using Deep Learning”, International Journal of Image, Graphics and Signal Processing (IJIGSP), vol.10, no.12, 2018.
[5]S. Sheela and M. Sumathi, “Study and theoretical analysis of various segmentation techniques for ultrasound images”, Procedia computer Science, volume 87, pp. 67-73, 2016.
[6]K. P.Jayamal and R. Kumar, “Advances in image processing for detection of plant disease”, Journal of advanced Bioinformatics application and research, vol. 2, issue 2, pp. 135-141, 2011.
[7]M. Vinay an N. R. Dhumale, “Leaf disease using Fuzzy Logic”, International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), vol. 7, issue 6, pp. 6801-6807, 2018.
[8]K. Elangovan and S. Nalini, “Plant disease classification using image segmentation and SVM techniques”, International Journal of Computational Research ISSN 0973-1873, vol. 13, pp. 1821-1828, 2017.
[9]N.T. Trini, “Plant disease detection using diffferent algorithms”, Proceedings of the Second International Conference on Research in Intelligent and Computing in Engineering, volume 10, 2017, pp. 103–106.
[10]S.G. Dhambal, R. Dhivya, S. Latha, and R. Rajesh, “Plant disease detection and its solution using image classification”, International Journal of Pure and Applied Mathematics, vol. 119, no 14, pp. 879-884, 2018.
[11]S. Sukhchain, and R. Rachna, “Implementation paper to detect and classification of fungal disease in grapes leaves using genetic algorithm”, 2017.
[12]S. Nagasai, and S.R: Jhansi, “Plant Disease Identification using Segmentation Techniques”, International Journal of Advanced Research in Computer and Communication Engineering, vol. 4, issue 9, pp. 411-413, 2015
[13]S. Vijai and A. K. Misra, “Detection of plant leaves diseases using image segmentation and soft computing techniques”, Information Processing in Agriculture, vol. 4, pp. 41–49, 2017.
[14]T. Bera, A. Das, and J. Sil, “A Survey on Rice Plant Disease Identification Using Image Processing and Data Mining Techniques”, Proceedings of IEMIS 2018, vol. 3, 2019.
[15]A. Rafid, A. Raha Niloy, A. Islam Chowdhury, N. Sharmin, “A Brief Review on Different Driver's Drowsiness Detection Techniques”, International Journal of Image, Graphics and Signal Processing (IJIGSP), vol.12, no.3, 2020.
[16]PlantVillage, https ://plantvillage.psu.edu/ [visited on January 2020].
[17]Singh, K., .K., Singh, A. “A Study of Image Segmentation Algorithms for Different Types of Images”,International Journal of Computer Science, Vol. 7, Issue 5, Sept.
[18]Hui Zhang et al. Image segmentation evaluation: a survey of unsupervised methods. Computer Vision and Image Understanding 110 (2008), pp. 260–280.
[19]SuryaPrabla, D., Satheesh, J. K. performance evaluation of image segmentation using objective method. INDJST, Volume 9, Issue 8, February 2016.