Chili crop segregation system design and development strategies

Wan Daud, Wan Mohd Bukhari and Abdul Aziz, Mohd Fareezuan and Ahmad Izzuddin, Tarmizi and Norasikin, Mohd Adili and Abdul Rasid, Ahmad Fuad and Wakhi Anuar, Nur Farah Bazilah and M. N. Sukhaimie (2021) Chili crop segregation system design and development strategies. Journal of Engineering and Technology, 12 (2). 01-22. ISSN 2180-3811

Text pdf_127 Download (3kB)

Abstract

An automation process is a need in the agricultural industry specifically chili crops, that implemented image processing techniques and classification of chili crops usually based on their color, shape, and texture. The goal of this study was to review the development of a portable sorting machine that will be able to segregate chili based on their color. Digital Image Processing (DIP), which is a crucial part to perform the Feature Extraction process was discussed with the elaboration of steps to execute the DIP process. Besides, the analysis of different methods to extract the chili color based on the RGB color component was included. This paper focused more on the Machine Learning (ML) technique, which is the main component of Artificial Intelligence. The image data taken from chili samples can be trained by using Learning Algorithm in the MATLAB program. The performance of the trained network then can be evaluated by using the Confusion Matrix technique. The methods that have been reviewed in this paper were general enough to be used in the agricultural industry that requires a high volume of chili crops and with other differentiating features to be processed at the same time. Improvements can be made to the sorting system but will come at a higher price.

Item Type:	Article
Uncontrolled Keywords:	Artificial neural network (ANN), Chili, Plot confusion, Sorting machine
Divisions:	Faculty of Mechanical and Manufacturing Engineering Technology
Depositing User:	Sabariah Ismail
Date Deposited:	25 Apr 2024 16:31
Last Modified:	25 Apr 2024 16:31
URI:	http://eprints.utem.edu.my/id/eprint/26709
Statistic Details:	View Download Statistic

Actions (login required)

View Item