ANN-based mango external quality grading system

A. Aziz, M. Rashdi and Htike@Muhammad Yusof, Zaw Zaw (2017) ANN-based mango external quality grading system. In: First Bi-annual Engineering Conference on Undergraduate Research, 17 Jan 2017, Gombak. (Unpublished)

	PDF Restricted to Repository staff only Download (517kB) | Request a copy
	PDF Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

This paper discuss about intelligent system for fruit grading system by using an artificial neural network (ANN) based on image processing techniques. Due to some constraint, this automatic grading system purpose is to overcome the most common problem faced by the farmer to determine and classify thousand units of fruits. There are several types of algorithms that have been used to extract the features of fruit characters based on the physical parameters by capturing the fruit image and from the extracted information, those samples (mango fruit) will be detected, graded and sorted accordingly to the desired quality. In this project, Python programming language is used since the selected hardware for this particular system to run the image processing is by using the Raspberry Pi (mini computer). The morphological feature such as RGB color model (Red, Green, and Blue), size, and blemish of the fruit is used to identify classes of them by using image processing and classified by the ANN. At the end of the process, all the fruits are being sorted to their grades which is determined by the ANN based on the training data that have been taught to it.

Item Type:	Conference or Workshop Item (Other)
Additional Information:	6919/55020
Subjects:	A General Works > AC Collections. Series. Collected works
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering Kulliyyah of Engineering > Department of Mechatronics Engineering
Depositing User:	Mr. Zaw Zaw Htike
Date Deposited:	08 Feb 2017 03:40
Last Modified:	11 Mar 2017 01:30
URI:	http://irep.iium.edu.my/id/eprint/55020

Actions (login required)

View Item