S. Shenbaha
V. Sreepriya
- Assistant Professor, Department of Computer Science with Data Analytics, Dr. N. G. P. Arts and Science College, Coimbatore, Tamil Nadu, India
- Student, Department of Computer Science with Data Analytics, Dr. N. G. P. Arts and Science College, Coimbatore, Tamil Nadu, India
Abstract
Advancements in agricultural technology and the integration of artificial intelligence for diagnosing plant and leaf diseases are crucial for sustainable agricultural development. Conditions like early blight and late blight exert a notable influence on both the quality and quantity of potato harvests. Identifying these leaf diseases manually demands significant labor and a considerable level of expertise. Therefore, efficient, and automated methods for disease detection are essential to improve potato production. This study introduces a model that utilizes pre-trained models like VGG16 for fine-tuning via transfer learning to extract relevant features from the dataset. The dataset is sourced from a publicly available plant database. Several trained models are employed to detect and categorize both diseased and healthy leaves. The system achieves an impressive testing accuracy of 99.23%, with 25% test data and 75% train data split. The results demonstrate that machine learning surpasses existing methods in potato disease detection. This research underscores the significance of leveraging advanced technologies in agriculture to address crucial challenges and improve productivity.
Keywords: feature extraction, VGG16, CNN, transfer learning fine-tuning
[This article belongs to Journal of Artificial Intelligence Research & Advances(joaira)]
References
[1] Plant Village Dataset, Version1, Abdallah Ali (2019,September), retrieved 22 February 2020, https://www.kaggle.com/xabdallahali/plantvillage-dataset.
[2] Ms. Priti Badar, Girish, and Athanikar. “Detection and Classification System for Potato Leaf Diseases, Mr.” (2016).
[3] “Detection of potato diseases using image segmentation and multiclass support vector machine,” 2017, IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE), Windsor, ON, pp. 1-4, by M. Islam, Anh Dinh, K. Wahid, and P. Bhowmik.
[4] “Leaf Disease Detection: Feature Extraction with K-means clustering and Classification with ANN,” C. U. Kumari, S. Jeevan Prasad, and G. Mounika, 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 2019, pp. 1095-1098.
[5] Li, Guanlin, Wang, Haiguang, and Ma, Zhanhong (2011). Using a Support Vector Machine, Grape Powdery and Grape Downy Mildew images are recognised. 10.1007/978-3-642-27275-2_17. IFIP Advances in Information and Communication Technology. 370. 151-162.
[6] Jing Chen, Qi Liu, and Ling Wang Gao. (2019). Convolutional Neural Network Model-Based Visual Tea Leaf Disease Recognition. 11. 343. 10.3390/sym11030343; Symmetry.
[7] Zisserman, A. and K. Simonyan. Very Deep Convolutional Networks for Large-Scale Image Recognition. Chapters 1–14, Computational and Biological Learning Society, 2015. [8] Theodoros Evgeniou and Massimiliano Pontil. (2001). Theory and Applications of Support Vector Machines, 2049, 249–257, 10.1007/3-540-44673-7_12.
[9] Wu, Haiyan & Li, Youguo (2012). A K-Means Algorithm-Based Clustering Technique. 25. 1104-1109, Physics Procedia 10.1016/j.phpro.2012.03.206.
[10] Huang, di; Shan, Caifeng; Chen, Liming; Ardabilian, Mohsen. (2011). A survey on local binary patterns and their use in facial image analysis. 10.1109/TSMCC.2011.2118750 IEEE Transactions on Systems, Man, and Cybernetics, Part C 41, 765-781.
[11]Amanda Ramcharan, Kelsee Baranowski, Peter McCloskey, Ahmed Babuali, James Legg, and David Hughes. (2017). Employing Transfer Learning in Image-Based Cassava Disease Identification. Plant Science Frontiers, 8. 10.3389/fpls.2017.01852.
[12] Ingersoll, Gary & Peng, Joanne & Lee, Kuk (2002). A Guide to Reporting and Analysis of Logistic Regression. 10.1080/00220670209598786 Journal of Educational Research – J EDUC RES. 96. 3–14.
[13] Hinton, Geoffrey & Sutskever, Ilya & Krizhevsky, Alex (2012). Deep Convolutional Neural Networks for ImageNet Classification. 25. 10.1145/3065386; Neural Information Processing Systems.
[14]Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and ZB Wojna (2016). reevaluating the computer vision-focused Inception architecture. CVPR.2016.308 10.1109/. [15] Leif Peterson. (2009). K is for the closest neighbor. 10.4249/scholarpedia.1883. Scholarpedia. 4. 1883.
[16] Shani, Guy & Erlich, Orly & Tsror, Leah & Oppenheim, Dor. 2018). Deep Learning for Image-Based Potato Tuber Disease Detection. 109. 10.1094/PHYTO-08-180288-R, Phytopathology.
[17] Alvaro Fuentes & Yoon, Sook & Kim, Sang & Dong Park. (2017). A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition. 17. 2022. 10.3390/s17092022. Sensors.
[18] Barré, Pierre; Müller, Kai; Steinhage, Volker; Stöver, Ben. (2017). LeafNet: An automated computer vision system for identifying plant species. 40. 10.1016/j.ecoinf.2017.05.005, Ecological Informatics.
[19] Tony Lindeberg. (2012). 10.4249/scholarpedia.10491 Scale Invariant Feature Transform.
[20] Yufeng Zheng, Clifford Yang, and Aleksey Merkulov (2018). Convolutional neural networks and follow-up digital mammography are used in breast cancer screening. 4. 12.304564/12.10.1117.
[21] R. M. Prakash, G. P. Saraswathy, G. Ramalakshmi, K. H. Mangaleswari and T. Kaviya, “Detection of leaf diseases and classification using digital image processing,” 2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS)
[22] F. T. Pinki, N. Khatun and S. M. M. Islam, “Content based paddy leaf disease recognition and remedy prediction using support vector machine,” 2017 20th International Conference of Computer and Information Technology (ICCIT), Dhaka, 2017, pp. 1–5.
[23] S. Biswas, B. Jagyasi, B. P. Singh and M. Lal, “Severity identification of Potato Late Blight disease from crop images captured under uncontrolled environment,” 2014 IEEE Canada International Humanitarian Technology Conference—(IHTC), Montreal, QC, 2014
[24] Hossain S, Mou RM, Hasan MM, Chakraborty S, Razzak MA. Recognition and detection of tea leaf’s diseases using support vector machine. In2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA) 2018 Mar 9 (pp. 150-154). IEEE.
[25] Prakash RM, Saraswathy GP, Ramalakshmi G, Mangaleswari KH, Kaviya T. Detection of leaf diseases and classification using digital image processing. In2017 international conference on innovations in information, embedded and communication systems (ICIIECS) 2017 Mar 17 (pp. 1-4). IEEE.
[26] Howlader MR, Habiba U, Faisal RH, Rahman MM. Automatic recognition of guava leaf diseases using deep convolution neural network. In2019 international conference on electrical, computer and communication engineering (ECCE) 2019 Feb 7 (pp. 1-5). IEEE.
[27] Waghmare H, Kokare R, Dandawate Y. Detection and classification of diseases of grape plant using opposite colour local binary pattern feature and machine learning for automated decision support system. In2016 3rd international conference on signal processing and integrated networks (SPIN) 2016 Feb 11 (pp. 513-518). IEEE.
Journal of Artificial Intelligence Research & Advances
| Volume | 11 |
| Issue | 01 |
| Received | February 29, 2024 |
| Accepted | April 7, 2024 |
| Published | April 22, 2024 |