Deep Learning For Coffee Disease Classification

  IJCTT-book-cover
 
         
 
© 2021 by IJCTT Journal
Volume-69 Issue-9
Year of Publication : 2021
Authors : Mikias Legesse
DOI :  10.14445/22312803/IJCTT-V69I9P105

How to Cite?

Mikias Legesse, "Deep Learning For Coffee Disease Classification," International Journal of Computer Trends and Technology, vol. 69, no. 9, pp. 27-32, 2021. Crossref, https://doi.org/10.14445/22312803/IJCTT-V69I9P105

Abstract
Coffee production in Ethiopia has a long story and is also one of the major agricultural products that exported a huge amount. But coffee production faces different challenges from that widespread coffee diseases result in huge production loss in both quantity and quality. Even if different coffee diseases are still a major challenge, detection and classification of those diseases are performed only by experts, or there is not much technological advancement in this sector. This research aims to apply deep learning methods to overcome the existing problem. A deep learning model was fine-tuned and optimized to detect and classify different coffee diseases to assist farmers in applying appropriate treatment; for this research, 5600 images were captured and used for training and testing. And the best-performing model achieves 97% of accuracy. Proper tuning of hyperparameters can prevent overfitting and an appropriate choice of optimizers, resulting in an efficient classifier finally, as future research work indicated applying the model for real-life scenarios.

Keywords
Deep learning, CNN, Plant disease, CBD, CWD, CLR.

Reference

[1] M. B. Etana, Review on the Management of Coffee Berry Disease (Colletotrichum kahawae) in Ethiopia, Food Science and Quality Management, 76 (2018) 73-76.
[2] Eshetu Derso Teame Gebrezgi Girma Adugna Significance of minor diseases of coffea arabica L. in Ethiopia: a review EARO, (2000).
[3] D. Oppenheim and G. Shani, Potato Disease Classification Using Con- volution Neural Networks, Advances in Animal Biosciences: Precision Agriculture (ECPA), 8 (2) (2017) 244-249.
[4] Liu, Bing, Supervised learning, in Web data mining, Springer, (2011) 63-132.
[5] Y. LeCun, K. Kavukcuoglu, and C. Farabet, Convolutional networks and applications in vision, Proceedings of 2010 IEEE International Symposium on Circuits and Systems, Paris, (2010) 253-256.
[6] D. H. Hubel and T. N. Wiesel, Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex, The Journal of physiology, (1962) 106-154.
[7] Le Lu, Yefeng Zheng, Gustavo Carneiro Lin Yang, Deep Learning and convolutional neural networks for medical image computing, Switzer- land: Springer International Publishing, (2017).
[8] A. Ng. Convolutional Neural Network. UFLDL. [On- line]. Available: http://ufldl.stanford.edu/tutorial/supervised/ Convolu- tionalNeuralNetwork/ (2018).
[9] Kamal KC, Zhendong Yin y, Bo Li, Bo Ma, Mingyang Wu, transfer learning for fine-grained crop disease classi-Fication based on leaf images, 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), (2019).
[10] Vinod Kumar Hritik Arora Harsh Jatin Sisodia, ResNet-based approach for Detection and Classification of Plant Leaf Diseases, Proceedings of the International Conference on Electronics and Sustainable Communication Systems, (2020) 495-502.
[11] Sardogan, Melike, and Tuncer, Adem and Ozen, Yunus, plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm, 3rd International Conference on Computer Science and Engineering (UBMK), (2018) 382-385.
[12] Bhimavarapu, Sumathi, and Vinitha, Panicker J, Analysis and Characterization of Plant Diseases using Transfer Learning, 2020 International Conference on Communication and Signal Processing (ICCSP) (2020) 1293-1296.
[13] Ishrat Zahan Mukti and Dipayan Biswas, Transfer Learning Based Plant Diseases Detection Using ResNet50, 2019 4th International Conference on Electrical Information and Communication Technology (EICT), (2019) 1-6.
[14] Karen Simonyan and Andrew Zisserman, very deep convo- lutional networks for large-scale image recogni-tion, International Conference on Learning Representations (ICLR), (2015)1-14.
[15] Chu, V. Madhavan, O. Beijbom, J. Hoffman, and T. Darrell, Best practices for fine-tuning visual classifiers to new domains, in Proc.Eur. Conf. Comput. Vis., (2016)435–442.