APPLY K-MEANS IN OUTLIER REMOVAL TO IMPROVE RICE LEAF DISEASE CLASSIFICATION PERFORMANCE USING MOBILENETV3 MODEL

Vũ Huy Lượng; Nguyễn Thị Mai Phương

doi:10.34238/tnu-jst.8919

APPLY K-MEANS IN OUTLIER REMOVAL TO IMPROVE RICE LEAF DISEASE CLASSIFICATION PERFORMANCE USING MOBILENETV3 MODEL

About this article

Received: 06/10/23 Revised: 30/10/23 Published: 30/10/23

Authors

1. Vu Huy Luong , TNU - University of Information and Communication Technology
2. Nguyen Thi Mai Phuong, TNU - University of Information and Communication Technology

Abstract

The population is continuously increasing, urbanization is accelerating, and agricultural land is shrinking. Diseases on rice leaves cause significant yield losses, necessitating early diagnosis to mitigate their impact on productivity and ensure food security. The application of technology in detecting and diagnosing rice leaf diseases is essential. This study proposes a method to enhance the accuracy of the MobileNetV3 deep learning model. The technique involves removing duplicate and outlier images to improve the efficiency of the MobileNetV3 model using K-Means. The dataset used in the experiment is acquired from a secondary source. The data consists of 5932 images of four common diseases on rice leaves. Three sets of data are created (Set-1, Set-2 and Set-3), corresponding to the outlier thresholds set at 0.00, 0.05, and 0.06, respectively. The results show a considerable increase in accuracy when applying this method. The Top-1 accuracy rose from 80.11% to 86.85% and 87.69%, respectively.

Keywords

Deep learning; K-means clustering; MobileNetV3; Rice leaf disease; Classification

Full Text:

PDF

References

[1] J. Harris, P. H. Nguyen, L. M. Tran, and P. N. Huynh, “Nutrition transition in Vietnam: changing food supply, food prices, household expenditure, diet and nutrition outcomes,” Food Security, vol. 12, no. 5, pp. 1141–1155, Oct. 2020.

[2] M. Mavaddat, M. Naderan, and S. E. Alavi, “Classification of rice leaf diseases using cnn-based pre-trained models and transfer learning,” in 2023 6th International Conference on Pattern Recognition and Image Analysis (IPRIA), 2023, pp. 1–6.

[3] N. Cherukuri, G. Kumar, O. Gandhi, V. S. K. Thotakura, D. NagaMani, and C. Z. Basha, “Automated classification of rice leaf disease using deep learning approach,” in 2021 5th International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2021, pp. 1206–1210.

[4] S. P. Singh, K. Pritamdas, K. J. Devi, and S. D. Devi, “Custom convolutional neural network for detection and classification of rice plant diseases,” International Conference on Machine Learning and Data Engineering, vol. 218, pp. 2026–2040, 2023.

[5] E. D. S. Mulyani, H. J. Pramana, L. Listiani, N. N. Febriani SM, R. A. Wiyono, and F. P. Pratiwi, “Classification of rice leaf diseases based on texture and leaf colour,” in 2022 4th International Conference on Cybernetics and Intelligent System (ICORIS), 2022, pp. 1–6.

[6] B. D. Satoto, D. R. Anamisa, M. Yusuf, M. K. Sophan, N. Alamsyah, and B. Irmawati, “Rice disease classification based on leaf damage using deep learning,” in 2022 6th International Conference on Informatics and Computational Sciences (ICICoS), 2022, pp. 42–47.

[7] S. Ghosal and K. Sarkar, “Rice leaf diseases classification using CNN with transfer learning,” in 2020 IEEE Calcutta Conference (CALCON), 2020, pp. 230–236.

[8] H. L. Vu, T. M. P. Nguyen, V. N. Pham, V. S. Nguyen, and V. C. Tran, “An evaluation of eye diseases classification using ResNet on fundus image dataset collected from Thai Binh hospital,” TNU Journal of Science and Technology, vol. 228, no. 07, pp.100-107, 2023.

[9] Rukhsar and S. K. Upadhyay, “Rice leaves disease detection and classification using transfer learning technique,” in 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), 2022, pp. 2151–2156.

[10] S. Zakzouk, M. Ehab, S. Atef, R. Yousri, R. M. Tawfik, and M. S. Darweesh, “Rice leaf diseases detector based on Alexnet,” in 2021 9th International Japan-Africa Conference on Electronics, Communications, and Computations (JAC-ECC), 2021, pp. 170–174.

[11] R. Bishwas, S. Yasmin, and N. A. Turzo, “Relative comparison of k-means clustering segmented rice leaves image based nitrogen, phosphorus, and potassium nutrient deficiency classification using convolutional neural network,” in 2021 International Conference on Science and Contemporary Technologies (ICSCT), 2021, pp. 1–6.

[12] F. Contributor, “Fastup manage, clean and curate visual data - fast and scale,” 2023. [Online]. Available: https://github.com/visual-layer/fastdup. [Accessed September 5, 2023].

[13] A. Howard, M. Sandler, G. Chu, L. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, Q. V. Le, and H. Adam, “Searching for mobilenetv3,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019, pp. 1314-1324.

[14] M. Contributors, “Openmmlab’s pre-training toolbox and benchmark,” 2023. [Online]. Available: https://github.com/open-mmlab/mmpretrain. [Accessed September 5, 2023].

DOI: https://doi.org/10.34238/tnu-jst.8919

Refbacks

There are currently no refbacks.



Remember me