Automated detection of mechanically induced bruise areas in golden delicious apples using fluorescence imagery

Y. C. Chiu, X. L. Chou, T. E. Grift, M. T. Chen

Research output: Contribution to journalArticle

Abstract

This study pursues the detection of bruised areas caused by mechanical impact on Golden Delicious apples using chlorophyll fluorescence imagery. When a fruit is impacted by a mechanical force and a bruise occurs, the chlorophyll nuclei inside the peel are damaged, which causes a reduction in fluorescence excitation compared to non-impacted areas. This difference allows automated detection of bruises and removal of damaged fruits to maintain optimal quality. In this study, fruit bruises were created using impact forces of 68.6, 88.2, and 107.8 N, and the resulting damage to chlorophyll nuclei inside the fruit peel was observed. Expansion of the area of damaged chlorophyll nuclei over time was observed using fluorescence imagery 0.5, 1, 2, and 4 h after the mechanical impact. This study employed a continuous capture of fruit fluorescence images and used MATLAB software for image processing and analysis. Edge contour noise was filtered by presetting a proper threshold, and the contour features of fruit bruises were distinguished using local adaptive binarization and a size filter. The experimental results showed that the mean recognition rate of a bruise 0.5 h after impact forces of 68.6, 88.2, and 107.8 N was as high as 86.7%, and the bruise recognition rate 1 h after impact was 100%. In conclusion, the fluoroscopic examination system for bruises was capable of detecting bruises accurately before the bruises were visible to the naked eye.

Original languageEnglish (US)
Pages (from-to)215-225
Number of pages11
JournalTransactions of the ASABE
Volume58
Issue number2
DOIs
StatePublished - Jan 1 2015

Fingerprint

bruising (plant)
Contusions
Imagery (Psychotherapy)
Malus
Fruits
imagery
fluorescence
fruit
apples
Fluorescence
Chlorophyll
Fruit
chlorophyll
fruits
image processing
image analysis
Image analysis
MATLAB
detection
fruit peels

Keywords

  • Adaptive binarization
  • Chlorophyll
  • Image processing
  • Non-destructive inspection

ASJC Scopus subject areas

  • Forestry
  • Food Science
  • Biomedical Engineering
  • Agronomy and Crop Science
  • Soil Science

Cite this

Automated detection of mechanically induced bruise areas in golden delicious apples using fluorescence imagery. / Chiu, Y. C.; Chou, X. L.; Grift, T. E.; Chen, M. T.

In: Transactions of the ASABE, Vol. 58, No. 2, 01.01.2015, p. 215-225.

Research output: Contribution to journalArticle

@article{3f7b9331a18a49ccb0461dda79e01311,
title = "Automated detection of mechanically induced bruise areas in golden delicious apples using fluorescence imagery",
abstract = "This study pursues the detection of bruised areas caused by mechanical impact on Golden Delicious apples using chlorophyll fluorescence imagery. When a fruit is impacted by a mechanical force and a bruise occurs, the chlorophyll nuclei inside the peel are damaged, which causes a reduction in fluorescence excitation compared to non-impacted areas. This difference allows automated detection of bruises and removal of damaged fruits to maintain optimal quality. In this study, fruit bruises were created using impact forces of 68.6, 88.2, and 107.8 N, and the resulting damage to chlorophyll nuclei inside the fruit peel was observed. Expansion of the area of damaged chlorophyll nuclei over time was observed using fluorescence imagery 0.5, 1, 2, and 4 h after the mechanical impact. This study employed a continuous capture of fruit fluorescence images and used MATLAB software for image processing and analysis. Edge contour noise was filtered by presetting a proper threshold, and the contour features of fruit bruises were distinguished using local adaptive binarization and a size filter. The experimental results showed that the mean recognition rate of a bruise 0.5 h after impact forces of 68.6, 88.2, and 107.8 N was as high as 86.7{\%}, and the bruise recognition rate 1 h after impact was 100{\%}. In conclusion, the fluoroscopic examination system for bruises was capable of detecting bruises accurately before the bruises were visible to the naked eye.",
keywords = "Adaptive binarization, Chlorophyll, Image processing, Non-destructive inspection",
author = "Chiu, {Y. C.} and Chou, {X. L.} and Grift, {T. E.} and Chen, {M. T.}",
year = "2015",
month = "1",
day = "1",
doi = "10.13031/trans.58.10578",
language = "English (US)",
volume = "58",
pages = "215--225",
journal = "Transactions - American Society of Agricultural Engineers: General Edition",
issn = "2151-0032",
publisher = "American Society of Agricultural and Biological Engineers",
number = "2",

}

TY - JOUR

T1 - Automated detection of mechanically induced bruise areas in golden delicious apples using fluorescence imagery

AU - Chiu, Y. C.

AU - Chou, X. L.

AU - Grift, T. E.

AU - Chen, M. T.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - This study pursues the detection of bruised areas caused by mechanical impact on Golden Delicious apples using chlorophyll fluorescence imagery. When a fruit is impacted by a mechanical force and a bruise occurs, the chlorophyll nuclei inside the peel are damaged, which causes a reduction in fluorescence excitation compared to non-impacted areas. This difference allows automated detection of bruises and removal of damaged fruits to maintain optimal quality. In this study, fruit bruises were created using impact forces of 68.6, 88.2, and 107.8 N, and the resulting damage to chlorophyll nuclei inside the fruit peel was observed. Expansion of the area of damaged chlorophyll nuclei over time was observed using fluorescence imagery 0.5, 1, 2, and 4 h after the mechanical impact. This study employed a continuous capture of fruit fluorescence images and used MATLAB software for image processing and analysis. Edge contour noise was filtered by presetting a proper threshold, and the contour features of fruit bruises were distinguished using local adaptive binarization and a size filter. The experimental results showed that the mean recognition rate of a bruise 0.5 h after impact forces of 68.6, 88.2, and 107.8 N was as high as 86.7%, and the bruise recognition rate 1 h after impact was 100%. In conclusion, the fluoroscopic examination system for bruises was capable of detecting bruises accurately before the bruises were visible to the naked eye.

AB - This study pursues the detection of bruised areas caused by mechanical impact on Golden Delicious apples using chlorophyll fluorescence imagery. When a fruit is impacted by a mechanical force and a bruise occurs, the chlorophyll nuclei inside the peel are damaged, which causes a reduction in fluorescence excitation compared to non-impacted areas. This difference allows automated detection of bruises and removal of damaged fruits to maintain optimal quality. In this study, fruit bruises were created using impact forces of 68.6, 88.2, and 107.8 N, and the resulting damage to chlorophyll nuclei inside the fruit peel was observed. Expansion of the area of damaged chlorophyll nuclei over time was observed using fluorescence imagery 0.5, 1, 2, and 4 h after the mechanical impact. This study employed a continuous capture of fruit fluorescence images and used MATLAB software for image processing and analysis. Edge contour noise was filtered by presetting a proper threshold, and the contour features of fruit bruises were distinguished using local adaptive binarization and a size filter. The experimental results showed that the mean recognition rate of a bruise 0.5 h after impact forces of 68.6, 88.2, and 107.8 N was as high as 86.7%, and the bruise recognition rate 1 h after impact was 100%. In conclusion, the fluoroscopic examination system for bruises was capable of detecting bruises accurately before the bruises were visible to the naked eye.

KW - Adaptive binarization

KW - Chlorophyll

KW - Image processing

KW - Non-destructive inspection

UR - http://www.scopus.com/inward/record.url?scp=84929156901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929156901&partnerID=8YFLogxK

U2 - 10.13031/trans.58.10578

DO - 10.13031/trans.58.10578

M3 - Article

AN - SCOPUS:84929156901

VL - 58

SP - 215

EP - 225

JO - Transactions - American Society of Agricultural Engineers: General Edition

JF - Transactions - American Society of Agricultural Engineers: General Edition

SN - 2151-0032

IS - 2

ER -