Lemon Leaf Disease Detection using Machine Learning

International Journal of Computer Science and Engineering

© 2024 by SSRG - IJCSE Journal

Volume 11 Issue 1

Year of Publication : 2024

Authors : V. Sudha, U. Hemalatha, S. Ganesh Shankar, Thiyagarajan

10.14445/23488387/IJCSE-V11I1P101

How to Cite?

V. Sudha, U. Hemalatha, S. Ganesh Shankar, Thiyagarajan, "Lemon Leaf Disease Detection using Machine Learning," SSRG International Journal of Computer Science and Engineering , vol. 11,  no. 1, pp. 1-10, 2024. Crossref, https://doi.org/10.14445/23488387/IJCSE-V11I1P101

Abstract:

Agriculture income and manufacturing are decreased by leaf diseases, which results in food resource vulnerability. Thus, it results in huge economic costs. The most popular of all citrus plants, the lemon, is widely distributed around the globe and utilised for a variety of applications, particularly those related to health and nutrition. Parasites and different illnesses, however, seriously impair lemon output. Lemons are a crop that is very important to the global economy. Lemon cultivation consequently suffers from severe purity reductions and harvest issues. Upwards of 50 percent of the commodities are just not utilised in lemon harvesting annually because of several leaf illnesses as well as outside variables. Visual analysis and learning procedures have recently been widely applied in numerous industries, notably farming, and depend on the advancement of technology. This makes it possible to identify and classify plant pathogens straight on. Gardeners can benefit again from the automatic recognition of infections in order to protect their vegetation from them. Consequently, the purpose of this work is to identify and categorise both good and bad leaves using photographs. For that purpose, various photos first from the Lemon Leaf collection were pre-processed using techniques notably ROI, noise removal with the Mean filter, image improvement with the histogram equalisation, and augmentation data source offered for the research. Discrete wavelet transforms grey level cooccurrence and principal component analysis extract features in the second stage. Third, classification is done with KNN, CNN and SVM. The evaluation process is completed by creating a confusion matrix. A confusion matrix results in the creation of a contemporary design that uses CNN. The mean scores for the F1-score, precision, recall, and accuracy (%) according to the test outcomes of the developed framework were 96%, 94%, 100%, and 97%, respectively. The suggested framework essentially characterises lemon leaf as healthy or unhealthy, in keeping with the literature review. The suggested strategy is offered as a helpful website named "lemon leaf disease identification," where we may determine whether lemon leaf is healthy or sickly by submitting a picture.

Keywords:

SVM, KNN, CNN, DWT, GLCM, PCA, ROI, Noise removal, histogram equalization, Augmentation, F1-score, Precision, Recall, Accuracy, machine learning, website called “lemon leaf disease identification”.

References:

[1] Guan Wang, Yu Sun, and Jianxin Wang, “Automatic Image-based Plant Disease Severity Estimation Using Deep Learning,” Computational Intelligence and Neuroscience, vol. 2017, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Zahid Iqbal et al., “An Automated Detection and Classification of Citrus Plant Diseases Using Image Processing Techniques: A Review,” Computers and Electronics in Agriculture, vol. 153, pp. 12-32, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Muhammad Zubair Asghar et al., “Performance Evaluation of Supervised Machine Learning Techniques for Efficient Detection of Emotions from Online Content,” Arxiv, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Yun Wang et al., “Fuzzy-based Sentiment Analysis System for Analyzing Student Feedback and Satisfaction,” Computers, Materials & Continua, vol. 62, no. 2, pp. 631-655, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Mushtaq Ali, Muhammad Zubair Asghar, and Amanullah Baloch, “An Efficient Approach for Subimage Separation from Large Scale Multi-panel Images Using Dynamic Programming,” Multimedia Tools and Applications, vol. 80, no. 4, pp. 5449-5471, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Lu Yang, Qing Song, and Yingqi Wu, “Attacks on State-of-the-Art Face Recognition Using Attentional Adversarial Attack Generative Network,” Multimedia Tools and Applications, vol. 80, pp. 855-875, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Jie Fang, Bo Qu, and Yuan Yuan, “Distribution Equalization Learning Mechanism for Road Crack Detection,” Neurocomputing, vol. 424, pp. 193-204, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Hanene Ben Yedder, Ben Cardoen, and Ghassan Hamarneh, “Deep Learning for Biomedical Image Reconstruction: A Survey,” Artificial Intelligence Review, vol. 54, pp. 215-251, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Bin Zhao et al., “A CNN–RNN Architecture for Multi-Label Weather Recognition,” Neurocomputing, vol. 322, pp. 47-57, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Xi Zhu et al., “Soil Moisture Temporal Stability and Spatio-temporal Variability About a Typical Subalpine Ecosystem in Northwestern China,” Hydrological Processes, vol. 34, no. 11, pp. 2401-2417, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Benjamin Doh et al., “Automatic Citrus Fruit Disease Detection by Phenotyping Using Machine Learning,” Proceeding 25th International Conference on Automation and Computing (ICAC), Lancaster, UK, pp. 1-5, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Salman Qadri et al., “Machine Vision Approach for Classification of Citrus Leaves Using Fused Features,” International Journal of Food Properties, vol. 22, no. 1, pp. 2072-2089, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zhongqi Lin et al., “A Unified Matrix-based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases,” IEEE Access, vol. 7, pp. 11570-11590, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yang Lu et al., “Identification of Rice Diseases Using Deep Convolutional Neural Networks,” Neurocomputing, vol. 267, pp. 378-384, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Blake Richey et al., “Realtime Detection of Maize Crop Disease Via A Deep Learning-based Smartphone App,” Proceedings SPIE, vol. 11401, pp. 23-29, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] K. Padmavathi, and K. Thangadurai, “The Role of Image Enhancement in Citrus Canker Disease Detection,” International Journal of Advanced Computer Science and Applications, vol. 7, no. 9, pp. 293-296, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Hardik Patel, Rashmin Prajapati, and Milin Patel, “Detection of Quality in Orange Fruit Image Using SVM Classifier,” 3rd International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, pp. 74-78, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Harpreet Singh, Rajneesh Rani, and Shilpa Mahajan, Detection and Classification of Citrus Leaf Disease Using Hybrid Features, Advances in Intelligent Systems and Computing, Springer, Singapore, vol. 1053, pp. 737-745, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Shuli Xing, Marely Lee, and Keun Kwang Lee, “Citrus Pests and Diseases Recognition Model Using Weakly Dense Connected Convolution Network,” Sensors, vol. 19, no. 14, pp. 1-18, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Morteza Khanramaki, Ezzatollah Askari Asli-Ardeh, and Ehsan Kozegar, “Citrus Pests Classification Using An Ensemble of Deep Learning Models,” Computers and Electronics in Agriculture, vol. 186, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Shakeel Ahmad et al., “Classification of Poetry Text into The Emotional States Using Deep Learning Technique,” IEEE Access, vol. 8, pp. 73865-73878, 2020.[CrossRef] [Google Scholar] [Publisher Link]