Detecting surface cracks on dates using color imaging technique

S. Al-Rahbi, A. Manickavasagan, R. Al-Yahyai, L. Khriji, P. Alahakoon

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Surface or external qualities of fresh and dried fruits are the important factors in determining the consumer acceptability. An automated and objective method to detect the surface defects on fruits would be highly beneficial in handling and processing facilities. The objective of this study was to determine the efficiency of a computer vision system with RGB color camera to detect the surface cracks on dates. Three grades of dates (no-crack dates, low-crack dates and high-crack dates) were obtained from two commercial dates processing factories in Oman. After the confirmation of grade standards by a dates-qualityexpert, the samples were imaged individually using a color camera (105 dates in each grade). Eleven features were extracted from each image and used in classification models. Red, hue and value intensities of three grades of dates were significantly different from each other. In a three classes model, the classification accuracy was 62%, 58% and 78% for high-crack, low-crack and no-crack dates, respectively using linear discriminant analysis (LDA). LDA yielded a classification accuracy of 88% and 75% for the dates with-crack and without-crack, respectively in a two classes model. In pairwise discrimination, the highest classification (96%) was achieved between high-crack and no-crack dates, and the lowest accuracy (59%) was between low-crack and high-crack dates.

Original languageEnglish
Pages (from-to)795-804
Number of pages10
JournalFood Science and Technology Research
Volume19
Issue number5
DOIs
Publication statusPublished - 2013

Fingerprint

Color
image analysis
Cracks
Imaging techniques
color
Discriminant Analysis
cameras
discriminant analysis
Fruit
Oman
dried fruit
Artificial Intelligence
computer vision
raw fruit
methodology
factories
Discriminant analysis
Fruits
fruits
Imaging

Keywords

  • Color imaging
  • Dates
  • Image processing
  • Surface crack

ASJC Scopus subject areas

  • Food Science
  • Industrial and Manufacturing Engineering
  • Chemical Engineering(all)
  • Biotechnology
  • Marketing

Cite this

Detecting surface cracks on dates using color imaging technique. / Al-Rahbi, S.; Manickavasagan, A.; Al-Yahyai, R.; Khriji, L.; Alahakoon, P.

In: Food Science and Technology Research, Vol. 19, No. 5, 2013, p. 795-804.

Research output: Contribution to journalArticle

Al-Rahbi, S. ; Manickavasagan, A. ; Al-Yahyai, R. ; Khriji, L. ; Alahakoon, P. / Detecting surface cracks on dates using color imaging technique. In: Food Science and Technology Research. 2013 ; Vol. 19, No. 5. pp. 795-804.
@article{b6cbedd459274e6dadf5175b778da3a8,
title = "Detecting surface cracks on dates using color imaging technique",
abstract = "Surface or external qualities of fresh and dried fruits are the important factors in determining the consumer acceptability. An automated and objective method to detect the surface defects on fruits would be highly beneficial in handling and processing facilities. The objective of this study was to determine the efficiency of a computer vision system with RGB color camera to detect the surface cracks on dates. Three grades of dates (no-crack dates, low-crack dates and high-crack dates) were obtained from two commercial dates processing factories in Oman. After the confirmation of grade standards by a dates-qualityexpert, the samples were imaged individually using a color camera (105 dates in each grade). Eleven features were extracted from each image and used in classification models. Red, hue and value intensities of three grades of dates were significantly different from each other. In a three classes model, the classification accuracy was 62{\%}, 58{\%} and 78{\%} for high-crack, low-crack and no-crack dates, respectively using linear discriminant analysis (LDA). LDA yielded a classification accuracy of 88{\%} and 75{\%} for the dates with-crack and without-crack, respectively in a two classes model. In pairwise discrimination, the highest classification (96{\%}) was achieved between high-crack and no-crack dates, and the lowest accuracy (59{\%}) was between low-crack and high-crack dates.",
keywords = "Color imaging, Dates, Image processing, Surface crack",
author = "S. Al-Rahbi and A. Manickavasagan and R. Al-Yahyai and L. Khriji and P. Alahakoon",
year = "2013",
doi = "10.3136/fstr.19.795",
language = "English",
volume = "19",
pages = "795--804",
journal = "Food Science and Technology Research",
issn = "1344-6606",
publisher = "Japanese Society for Food Science and Technology",
number = "5",

}

TY - JOUR

T1 - Detecting surface cracks on dates using color imaging technique

AU - Al-Rahbi, S.

AU - Manickavasagan, A.

AU - Al-Yahyai, R.

AU - Khriji, L.

AU - Alahakoon, P.

PY - 2013

Y1 - 2013

N2 - Surface or external qualities of fresh and dried fruits are the important factors in determining the consumer acceptability. An automated and objective method to detect the surface defects on fruits would be highly beneficial in handling and processing facilities. The objective of this study was to determine the efficiency of a computer vision system with RGB color camera to detect the surface cracks on dates. Three grades of dates (no-crack dates, low-crack dates and high-crack dates) were obtained from two commercial dates processing factories in Oman. After the confirmation of grade standards by a dates-qualityexpert, the samples were imaged individually using a color camera (105 dates in each grade). Eleven features were extracted from each image and used in classification models. Red, hue and value intensities of three grades of dates were significantly different from each other. In a three classes model, the classification accuracy was 62%, 58% and 78% for high-crack, low-crack and no-crack dates, respectively using linear discriminant analysis (LDA). LDA yielded a classification accuracy of 88% and 75% for the dates with-crack and without-crack, respectively in a two classes model. In pairwise discrimination, the highest classification (96%) was achieved between high-crack and no-crack dates, and the lowest accuracy (59%) was between low-crack and high-crack dates.

AB - Surface or external qualities of fresh and dried fruits are the important factors in determining the consumer acceptability. An automated and objective method to detect the surface defects on fruits would be highly beneficial in handling and processing facilities. The objective of this study was to determine the efficiency of a computer vision system with RGB color camera to detect the surface cracks on dates. Three grades of dates (no-crack dates, low-crack dates and high-crack dates) were obtained from two commercial dates processing factories in Oman. After the confirmation of grade standards by a dates-qualityexpert, the samples were imaged individually using a color camera (105 dates in each grade). Eleven features were extracted from each image and used in classification models. Red, hue and value intensities of three grades of dates were significantly different from each other. In a three classes model, the classification accuracy was 62%, 58% and 78% for high-crack, low-crack and no-crack dates, respectively using linear discriminant analysis (LDA). LDA yielded a classification accuracy of 88% and 75% for the dates with-crack and without-crack, respectively in a two classes model. In pairwise discrimination, the highest classification (96%) was achieved between high-crack and no-crack dates, and the lowest accuracy (59%) was between low-crack and high-crack dates.

KW - Color imaging

KW - Dates

KW - Image processing

KW - Surface crack

UR - http://www.scopus.com/inward/record.url?scp=84891881811&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891881811&partnerID=8YFLogxK

U2 - 10.3136/fstr.19.795

DO - 10.3136/fstr.19.795

M3 - Article

VL - 19

SP - 795

EP - 804

JO - Food Science and Technology Research

JF - Food Science and Technology Research

SN - 1344-6606

IS - 5

ER -