Machine vision based quality evaluation of Iyokan orange fruit using neural networks

Naoshi Kondo, Usman Ahmad, Mitsuji Monta, Haruhiko Murase

Research output: Contribution to journalArticle

85 Citations (Scopus)

Abstract

It is a common belief that a sweet Iyokan orange fruit is reddish in color, of medium size, with a height to width ratio less than one, and having a glossy surface. However, the criteria are ambiguous and vary from people to people and locations to locations. In this paper, sugar content and acid content of Iyokan orange fruit were evaluated using a machine vision system. Images of 30 Iyokan orange fruits were acquired by a color TV camera. Features representing fruit color, shape, and roughness of fruit surface were extracted from the images. The features included R/G color component ratio, Feret's diameter ratio, and textural features. These features and weight of the fruit were entered to the input layers of neural networks, while sugar content or pH of the fruit was used as the values of the output layers. Several neural networks were found to be able to predict the sugar content or pH from the fruit appearance with a reasonable accuracy. (C) 2000 Published by Elsevier Science B.V.

Original languageEnglish
Pages (from-to)135-147
Number of pages13
JournalComputers and Electronics in Agriculture
Volume29
Issue number1-2
DOIs
Publication statusPublished - Oct 2000

Fingerprint

computer vision
Fruits
neural networks
Computer vision
fruit
Neural networks
fruits
Sugars
sugar content
sugar
color
Color
Color television
evaluation
sugar acids
roughness
cameras
Surface roughness
Cameras
Acids

Keywords

  • Machine vision
  • Neural networks
  • Orange
  • Quality

ASJC Scopus subject areas

  • Agronomy and Crop Science
  • Forestry
  • Computer Science Applications

Cite this

Machine vision based quality evaluation of Iyokan orange fruit using neural networks. / Kondo, Naoshi; Ahmad, Usman; Monta, Mitsuji; Murase, Haruhiko.

In: Computers and Electronics in Agriculture, Vol. 29, No. 1-2, 10.2000, p. 135-147.

Research output: Contribution to journalArticle

Kondo, Naoshi ; Ahmad, Usman ; Monta, Mitsuji ; Murase, Haruhiko. / Machine vision based quality evaluation of Iyokan orange fruit using neural networks. In: Computers and Electronics in Agriculture. 2000 ; Vol. 29, No. 1-2. pp. 135-147.
@article{0f9300619f3e4844bf0b87e222355c33,
title = "Machine vision based quality evaluation of Iyokan orange fruit using neural networks",
abstract = "It is a common belief that a sweet Iyokan orange fruit is reddish in color, of medium size, with a height to width ratio less than one, and having a glossy surface. However, the criteria are ambiguous and vary from people to people and locations to locations. In this paper, sugar content and acid content of Iyokan orange fruit were evaluated using a machine vision system. Images of 30 Iyokan orange fruits were acquired by a color TV camera. Features representing fruit color, shape, and roughness of fruit surface were extracted from the images. The features included R/G color component ratio, Feret's diameter ratio, and textural features. These features and weight of the fruit were entered to the input layers of neural networks, while sugar content or pH of the fruit was used as the values of the output layers. Several neural networks were found to be able to predict the sugar content or pH from the fruit appearance with a reasonable accuracy. (C) 2000 Published by Elsevier Science B.V.",
keywords = "Machine vision, Neural networks, Orange, Quality",
author = "Naoshi Kondo and Usman Ahmad and Mitsuji Monta and Haruhiko Murase",
year = "2000",
month = "10",
doi = "10.1016/S0168-1699(00)00141-1",
language = "English",
volume = "29",
pages = "135--147",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",
number = "1-2",

}

TY - JOUR

T1 - Machine vision based quality evaluation of Iyokan orange fruit using neural networks

AU - Kondo, Naoshi

AU - Ahmad, Usman

AU - Monta, Mitsuji

AU - Murase, Haruhiko

PY - 2000/10

Y1 - 2000/10

N2 - It is a common belief that a sweet Iyokan orange fruit is reddish in color, of medium size, with a height to width ratio less than one, and having a glossy surface. However, the criteria are ambiguous and vary from people to people and locations to locations. In this paper, sugar content and acid content of Iyokan orange fruit were evaluated using a machine vision system. Images of 30 Iyokan orange fruits were acquired by a color TV camera. Features representing fruit color, shape, and roughness of fruit surface were extracted from the images. The features included R/G color component ratio, Feret's diameter ratio, and textural features. These features and weight of the fruit were entered to the input layers of neural networks, while sugar content or pH of the fruit was used as the values of the output layers. Several neural networks were found to be able to predict the sugar content or pH from the fruit appearance with a reasonable accuracy. (C) 2000 Published by Elsevier Science B.V.

AB - It is a common belief that a sweet Iyokan orange fruit is reddish in color, of medium size, with a height to width ratio less than one, and having a glossy surface. However, the criteria are ambiguous and vary from people to people and locations to locations. In this paper, sugar content and acid content of Iyokan orange fruit were evaluated using a machine vision system. Images of 30 Iyokan orange fruits were acquired by a color TV camera. Features representing fruit color, shape, and roughness of fruit surface were extracted from the images. The features included R/G color component ratio, Feret's diameter ratio, and textural features. These features and weight of the fruit were entered to the input layers of neural networks, while sugar content or pH of the fruit was used as the values of the output layers. Several neural networks were found to be able to predict the sugar content or pH from the fruit appearance with a reasonable accuracy. (C) 2000 Published by Elsevier Science B.V.

KW - Machine vision

KW - Neural networks

KW - Orange

KW - Quality

UR - http://www.scopus.com/inward/record.url?scp=0034306908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034306908&partnerID=8YFLogxK

U2 - 10.1016/S0168-1699(00)00141-1

DO - 10.1016/S0168-1699(00)00141-1

M3 - Article

AN - SCOPUS:0034306908

VL - 29

SP - 135

EP - 147

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

IS - 1-2

ER -