Coffee leaf rust disease detection using MobileNetV2-based feature extractor, SVM classifier and visualization technique
DOI:
https://doi.org/10.54939/1859-1043.j.mst.CSCE8.2024.33-43Keywords:
CNN feature extractor; Classifiers; Transfer learning; Coffee leaf rust disease detection; Visualization technique.Abstract
The coffee plant is a vital crop, particularly in Vietnam, and is vulnerable to weather, cultivation methods, and diseases like rust disease. Early detection and treatment of rust disease are essential to ensuring coffee yield and quality. This study introduces a hybrid model for automated rust disease detection from coffee leaf images. The approach employs MobileNetV2 for feature extraction using convolutional neural networks (CNNs) and a Support Vector Machine (SVM) for classification. Experiments also evaluated other lightweight CNNs like MobileNet and NASNetMobile, as well as classifiers like DecisionTree and RandomForest, but MobileNetV2 and SVM delivered optimal results. The model was trained on the publicly available RoCoLe dataset and achieved a rust disease detection accuracy of 97.13%, surpassing standard CNN approaches by 2.39%. Additionally, the study uses Grad-CAM to visualize key areas in coffee leaf images that influence the classification process, offering insights into how the model distinguishes between healthy and diseased leaves. This methodology supports early disease detection and provides tools for understanding the model's decision-making process, contributing to more effective coffee plant disease management.
References
[1]. Beche, Dinkissa, Ayco JM Tack, Sileshi Nemomissa, Debissa Lemessa, Bikila Warkineh, and Kristoffer Hylander. "Prevalence of major pests and diseases in wild and cultivated coffee in Ethiopia." Basic and Applied Ecology 73: 3-9, (2023). DOI: https://doi.org/10.1016/j.baae.2023.06.005
[2]. Sandler, Mark, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. "Mobilenetv2: Inverted residuals and linear bottlenecks." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4510-4520. (2018). DOI: https://doi.org/10.1109/CVPR.2018.00474
[3]. Ma, Yunqian, and Guodong Guo, eds. Support vector machines applications. Vol. 649. New York: Springer, (2014). DOI: https://doi.org/10.1007/978-3-319-02300-7
[4]. Hussein, Mohammed A., and Amel H. Abbas. "Plant leaf disease detection using sup-port vector machine." Al-Mustansiriyah Journal of Science 30, no. 1: 105-110, (2019). DOI: https://doi.org/10.23851/mjs.v30i1.487
[5]. Zhang, Shanwen, Haoxiang Wang, Wenzhun Huang, and Zhuhong You. "Plant dis-eased leaf segmentation and recognition by fusion of superpixel, K-means and PHOG." Optik 157: 866-872, (2018). DOI: https://doi.org/10.1016/j.ijleo.2017.11.190
[6]. Mengistu, Abrham Debasu, Dagnachew Melesew Alemayehu, and Seffi Gebeyehu Mengistu. "Ethiopian coffee plant diseases recognition based on imaging and ma-chine learning techniques." International Journal of Database Theory and Application 9, no. 4: 79-88, (2016). DOI: https://doi.org/10.14257/ijdta.2016.9.4.07
[7]. Hayit, Tolga, Hasan Erbay, Fatih Varçın, Fatma Hayit, and Nilüfer Akci. "Determina-tion of the severity level of yellow rust disease in wheat by using convolutional neural networks." Journal of Plant Pathology 103, no. 3: 923-934, (2021). DOI: https://doi.org/10.1007/s42161-021-00886-2
[8]. Ahila Priyadharshini, Ramar, Selvaraj Arivazhagan, Madakannu Arun, and Annamalai Mirnalini. "Maize leaf disease classification using deep convolutional neural net-works." Neural Computing and Applications 31: 8887-8895, (2019). DOI: https://doi.org/10.1007/s00521-019-04228-3
[9]. Al‐gaashani, Mehdhar SAM, Fengjun Shang, Mohammed SA Muthanna, Mashael Khayyat, and Ahmed A. Abd El‐Latif. "Tomato leaf disease classification by exploit-ing transfer learning and feature concatenation." IET Image Processing 16, no. 3: 913-925, (2022). DOI: https://doi.org/10.1049/ipr2.12397
[10]. Yebasse, Milkisa, Birhanu Shimelis, Henok Warku, Jaepil Ko, and Kyung Joo Cheoi. "Coffee disease visualization and classification." Plants 10, no. 6: 1257, (2021). DOI: https://doi.org/10.3390/plants10061257
[11]. Abuhayi, Biniyam Mulugeta, and Abdela Ahmed Mossa. "Coffee disease classifica-tion using Convolutional Neural Network based on feature concatenation." Informat-ics in Medicine Unlocked 39: 101245, (2023). DOI: https://doi.org/10.1016/j.imu.2023.101245
[12]. Clinton Sheppard. Tree-based machine learning algorithms: Decision trees, random forests, and boosting. CreateSpace Independent Publishing Platform, (2017).
[13]. Parraga-Alava, Jorge, Kevin Cusme, Angélica Loor, and Esneider Santander. "RoCoLe: A robusta coffee leaf images dataset for evaluation of machine learning based methods in plant diseases recognition." Data in brief 25: 104414, (2019). DOI: https://doi.org/10.1016/j.dib.2019.104414
[14]. Zoph, Barret, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. "Learning transfer-able architectures for scalable image recognition." In Proceedings of the IEEE con-ference on computer vision and pattern recognition, pp. 8697-8710. (2018). DOI: https://doi.org/10.1109/CVPR.2018.00907
[15]. Selvaraju, Ramprasaath R., Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. "Grad-cam: Visual explanations from deep networks via gradient-based localization." In Proceedings of the IEEE international conference on computer vision, pp. 618-626. (2017). DOI: https://doi.org/10.1109/ICCV.2017.74
[16]. Esgario, José GM, Renato A. Krohling, and José A. Ventura. "Deep learning for clas-sification and severity estimation of coffee leaf biotic stress." Computers and Electron-ics in Agriculture 169: 105162, (2020). DOI: https://doi.org/10.1016/j.compag.2019.105162
