Citation

Ho, Jun Kang and Yogarayan, Sumendra and Mogan, Jashila Nair and Pa, Pa Min (2024) Deep Learning-Based Fruit and Vegetable Detection. In: 9th International Conference on Information Technology and Digital Applications, ICITDA 2024, 7 - 8 November 2024, Nilai, Malaysia.

Text Deep Learning-Based Fruit and Vegetable Detection.pdf - Published Version Restricted to Repository staff only Download (435kB)

Abstract

In recent times, suppliers in the agricultural sector are under increasing pressure to enhance efficiency in sorting and categorizing fruits and vegetables. Ensuring accurate and efficient detection is crucial for optimizing supply chain operations. This study presents the development of an embedded system using deep learning techniques to address these challenges. Specifically, a Convolutional Neural Network (CNN) model is implemented on a Raspberry Pi 5, designed to improve the accuracy of fruit and vegetable identification for suppliers. The system integrates image capture and real-time detection capabilities, streamlining the sorting process. The dataset, which includes images of various produce, undergoes preprocessing steps such as grayscale conversion and feature scaling. A train-test split is employed, with 60% of the data allocated for training, 20% for validation, and 20% for testing. The CNN model is trained and evaluated, demonstrating high classification accuracy.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Fruit and vegetable detection, deep learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics S Agriculture > S Agriculture (General)
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	20 Feb 2025 06:44
Last Modified:	20 Feb 2025 07:55
URII:	http://shdl.mmu.edu.my/id/eprint/13519

Downloads

Edit (login required)