Computer Vision Estimation Of Volume And Weight Of Apple By Using 2d Noncontact Measuring Method

Afiq Ikhwan, Mohd Fauzi (2022) Computer Vision Estimation Of Volume And Weight Of Apple By Using 2d Noncontact Measuring Method. College of Engineering, Universiti Malaysia Pahang Al-Sultan Abdullah.

[img]
Preview
Pdf
EA18090_AFIQ IKHWAN_Thesis_V2 - Afiq Ikhwan.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Apple is one of the most famous fruits that have been picked by a lot of families in Malaysia. There are several factors that determine apple quality which are volume and weight. The two parameters have been used as a benchmark to identify the quality of apples. These two parameters can be easily measured individually by using a weighing balance to measure weight and water displacement method (WDM) to measure volume. However, these two methods are not suitable to apply in industries since both methods required a lot of time to obtain the final output. Therefore, new technology is needed in order to estimate the weight and volume of apples. The main objective of this project is to develop a vision-based system that is able to estimate the volume and weight of apples. The volume of the apple is calculated by using the width and height of the apple via images. The camera needs to calibrate in order to get the ratio of pixel/cm which is used for conversion data. Detectron2 with a custom dataset will be used to detect and segment apple images. The output of detection and segmentation images will be used to create boundary boxes to obtain the height and width of apples. The developed systems are tested by four different settings which have different variables. The volume and weight of apples are able to obtain 85.41% and 85.26% of accuracy by using the formula. Overall, the project is able to estimate all the parameters of apple with an accuracy of more than 80% which can be concluded as a successful project.

Item Type: Undergraduates Project Papers
Additional Information: SV: Prof. Madya Ir. Ts. Dr. Fahmi Samsuri
Uncontrolled Keywords: Noncontact Measuring Method
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: College of Engineering
Depositing User: Mr. Nik Ahmad Nasyrun Nik Abd Malik
Date Deposited: 08 Jan 2024 08:14
Last Modified: 08 Jan 2024 08:14
URI: http://umpir.ump.edu.my/id/eprint/39901
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item