Shape characteristics analysis for papaya size classification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

Prior to export, papaya are subjected to inspection for the purpose of quality control and grading. For size grading, the fruit is weighed manually hence the practice is tedious, time consuming and labor intensive. Therefore, this paper will discuss the development of a computer vision system for papaya size grading using shape characteristic analysis. The methodology involves data acquisition to collect the images and their weights. The RGB images were converted to binary images using automatic thresholding based on the Otsu method. Some morphological procedures were involved for image enhancement to distinguish the papaya object from the background. Then the shape characteristics consisting of area, mean diameter and perimeter were extracted from the papaya images. We classified according to combinations of the three features to study the uniqueness of the extracted features. Each combination was fed separately to a neural network for training and testing. The proposed technique showed the ability to perform papaya size classification with more than 94% accuracy in this research.

Original languageEnglish
Title of host publication2007 5th Student Conference on Research and Development, SCORED
DOIs
Publication statusPublished - 2007
Event2007 5th Student Conference on Research and Development, SCORED - Selangor
Duration: 11 Dec 200712 Dec 2007

Other

Other2007 5th Student Conference on Research and Development, SCORED
CitySelangor
Period11/12/0712/12/07

Fingerprint

grading
data acquisition
quality control
neural network
labor
methodology
ability
Grading

Keywords

  • Image processing
  • Neural network
  • Papaya fruit size grading
  • Shape characteristic

ASJC Scopus subject areas

  • Education
  • Management Science and Operations Research

Cite this

Shape characteristics analysis for papaya size classification. / Riyadi, Slamet; Abd Rahni, Ashrani Aizzuddin; Mustafa, Mohd. Marzuki; Hussain, Aini.

2007 5th Student Conference on Research and Development, SCORED. 2007. 4451426.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Riyadi, S, Abd Rahni, AA, Mustafa, MM & Hussain, A 2007, Shape characteristics analysis for papaya size classification. in 2007 5th Student Conference on Research and Development, SCORED., 4451426, 2007 5th Student Conference on Research and Development, SCORED, Selangor, 11/12/07. https://doi.org/10.1109/SCORED.2007.4451426
Riyadi S, Abd Rahni AA, Mustafa MM, Hussain A. Shape characteristics analysis for papaya size classification. In 2007 5th Student Conference on Research and Development, SCORED. 2007. 4451426 https://doi.org/10.1109/SCORED.2007.4451426
Riyadi, Slamet ; Abd Rahni, Ashrani Aizzuddin ; Mustafa, Mohd. Marzuki ; Hussain, Aini. / Shape characteristics analysis for papaya size classification. 2007 5th Student Conference on Research and Development, SCORED. 2007.
@inproceedings{bf975345f338420a9fcac92ab34b21c9,
title = "Shape characteristics analysis for papaya size classification",
abstract = "Prior to export, papaya are subjected to inspection for the purpose of quality control and grading. For size grading, the fruit is weighed manually hence the practice is tedious, time consuming and labor intensive. Therefore, this paper will discuss the development of a computer vision system for papaya size grading using shape characteristic analysis. The methodology involves data acquisition to collect the images and their weights. The RGB images were converted to binary images using automatic thresholding based on the Otsu method. Some morphological procedures were involved for image enhancement to distinguish the papaya object from the background. Then the shape characteristics consisting of area, mean diameter and perimeter were extracted from the papaya images. We classified according to combinations of the three features to study the uniqueness of the extracted features. Each combination was fed separately to a neural network for training and testing. The proposed technique showed the ability to perform papaya size classification with more than 94{\%} accuracy in this research.",
keywords = "Image processing, Neural network, Papaya fruit size grading, Shape characteristic",
author = "Slamet Riyadi and {Abd Rahni}, {Ashrani Aizzuddin} and Mustafa, {Mohd. Marzuki} and Aini Hussain",
year = "2007",
doi = "10.1109/SCORED.2007.4451426",
language = "English",
isbn = "1424414709",
booktitle = "2007 5th Student Conference on Research and Development, SCORED",

}

TY - GEN

T1 - Shape characteristics analysis for papaya size classification

AU - Riyadi, Slamet

AU - Abd Rahni, Ashrani Aizzuddin

AU - Mustafa, Mohd. Marzuki

AU - Hussain, Aini

PY - 2007

Y1 - 2007

N2 - Prior to export, papaya are subjected to inspection for the purpose of quality control and grading. For size grading, the fruit is weighed manually hence the practice is tedious, time consuming and labor intensive. Therefore, this paper will discuss the development of a computer vision system for papaya size grading using shape characteristic analysis. The methodology involves data acquisition to collect the images and their weights. The RGB images were converted to binary images using automatic thresholding based on the Otsu method. Some morphological procedures were involved for image enhancement to distinguish the papaya object from the background. Then the shape characteristics consisting of area, mean diameter and perimeter were extracted from the papaya images. We classified according to combinations of the three features to study the uniqueness of the extracted features. Each combination was fed separately to a neural network for training and testing. The proposed technique showed the ability to perform papaya size classification with more than 94% accuracy in this research.

AB - Prior to export, papaya are subjected to inspection for the purpose of quality control and grading. For size grading, the fruit is weighed manually hence the practice is tedious, time consuming and labor intensive. Therefore, this paper will discuss the development of a computer vision system for papaya size grading using shape characteristic analysis. The methodology involves data acquisition to collect the images and their weights. The RGB images were converted to binary images using automatic thresholding based on the Otsu method. Some morphological procedures were involved for image enhancement to distinguish the papaya object from the background. Then the shape characteristics consisting of area, mean diameter and perimeter were extracted from the papaya images. We classified according to combinations of the three features to study the uniqueness of the extracted features. Each combination was fed separately to a neural network for training and testing. The proposed technique showed the ability to perform papaya size classification with more than 94% accuracy in this research.

KW - Image processing

KW - Neural network

KW - Papaya fruit size grading

KW - Shape characteristic

UR - http://www.scopus.com/inward/record.url?scp=50449099311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50449099311&partnerID=8YFLogxK

U2 - 10.1109/SCORED.2007.4451426

DO - 10.1109/SCORED.2007.4451426

M3 - Conference contribution

SN - 1424414709

SN - 9781424414703

BT - 2007 5th Student Conference on Research and Development, SCORED

ER -