Citation

Elhammamy, Youssef Yasser Salaheldin and Chung, Gwo Chin and Gan, Ming Tao and Tiang, Jun Jiat and Teong, Khan Vun (2024) Classification and Detection of Rice Crop Using Deep Learning for Smart Agriculture. In: 2024 Multimedia University Engineering Conference (MECON), 23-25 July 2024, Cyberjaya, Malaysia.

Text Classification and Detection of Rice Crop Using Deep Learning for Smart Agriculture.pdf - Published Version Restricted to Repository staff only Download (786kB)

Abstract

Rice is the fundamental food source, particularly in countries like Malaysia, where it forms the cornerstone of the diet. However, the task of monitoring and managing rice crops poses significant challenges, especially considering the vast expanses of land dedicated to their cultivation. Traditional methods, reliant on manual labor and visual inspection, are time-consuming and often imprecise, leading to sub-optimal agricultural outcomes. This paper aims to implement advanced image processing techniques such as data masking, data annotation, and data augmentation applied to drone-captured images of rice fields in Malaysia, a critical region for rice production. By leveraging TensorFlow and PyTorch, tools for training deep learning models, this study attempts to improve the accuracy for image classification, object detection, and segmentation of rice crops, which are crucial for effective crop management. After substantial training and validation, the models are able to achieve an accuracy of nearly 99%, and 90% for the classification of rice fields and the segmentation of rice growth. For rice crop detection, the model shows considerably high precision, recall, and mean average precision scores. Hence, the results underscore the transformative potential of integrating machine learning with aerial imagery to refine and improve traditional farming practices, making them more accurate and effective.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Rice crop, deep learning, drone images, smart agriculture
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics S Agriculture > S Agriculture (General)
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	06 Feb 2025 07:03
Last Modified:	06 Feb 2025 07:03
URII:	http://shdl.mmu.edu.my/id/eprint/13370

Downloads

Edit (login required)