Shortwave infrared hyperspectral imaging for detecting sour skin (Burkholderia cepacia)-infected onions

Weilin Wang, Changying Li, Ernest W. Tollner, Ronald D. Gitaitis, Glen Christopher Rains

Research output: Contribution to journalArticle

60 Citations (Scopus)

Abstract

Sour skin (Burkholderia cepacia) is a major postharvest disease for onions and causes substantial production and economic losses in onion postharvest. In this study, a shortwave infrared hyperspectral imaging system was explored to detect sour skin. The hyperspectral reflectance images (950-1650 nm) of onions were obtained for the healthy and sour skin-infected onions. Principal component analysis conducted on the spectra of the healthy and sour skin-infected onions suggested that the neck area of the onion at two wavelengths (1070 and 1400 nm) was most indicative of the sour skin. Log-ratio images utilizing the two optimal wavelengths were used for two different image analysis approaches. The first method applied a global threshold (0.45) to segregate the sour skin-infected areas from log-ratio images. Using the pixel number of the segregated areas, Fisher's discriminant analysis recognized 80% healthy and sour skin-infected onions. The second classification approach used three parameters (max, contrast, and homogeneity) of the log-ratio images as the input features of support vector machine (Gaussian kernel, γ = 1.5), which discriminated 87.14% healthy and sour skin-infected onions. The result of this study can be used to further develop a multispectral imaging system to detect sour skin-infected onions on packing lines.

Original languageEnglish
Pages (from-to)38-48
Number of pages11
JournalJournal of Food Engineering
Volume109
Issue number1
DOIs
Publication statusPublished - Mar 1 2012

Fingerprint

Burkholderia cepacia
Onions
onions
image analysis
Skin
wavelengths
postharvest diseases
Discriminant Analysis
Principal Component Analysis
discriminant analysis
neck
reflectance
principal component analysis
Neck
Economics
economics

All Science Journal Classification (ASJC) codes

  • Food Science

Cite this

Shortwave infrared hyperspectral imaging for detecting sour skin (Burkholderia cepacia)-infected onions. / Wang, Weilin; Li, Changying; Tollner, Ernest W.; Gitaitis, Ronald D.; Rains, Glen Christopher.

In: Journal of Food Engineering, Vol. 109, No. 1, 01.03.2012, p. 38-48.

Research output: Contribution to journalArticle

Wang, Weilin ; Li, Changying ; Tollner, Ernest W. ; Gitaitis, Ronald D. ; Rains, Glen Christopher. / Shortwave infrared hyperspectral imaging for detecting sour skin (Burkholderia cepacia)-infected onions. In: Journal of Food Engineering. 2012 ; Vol. 109, No. 1. pp. 38-48.
@article{59d4aa58e7c1462ca183381131c8680e,
title = "Shortwave infrared hyperspectral imaging for detecting sour skin (Burkholderia cepacia)-infected onions",
abstract = "Sour skin (Burkholderia cepacia) is a major postharvest disease for onions and causes substantial production and economic losses in onion postharvest. In this study, a shortwave infrared hyperspectral imaging system was explored to detect sour skin. The hyperspectral reflectance images (950-1650 nm) of onions were obtained for the healthy and sour skin-infected onions. Principal component analysis conducted on the spectra of the healthy and sour skin-infected onions suggested that the neck area of the onion at two wavelengths (1070 and 1400 nm) was most indicative of the sour skin. Log-ratio images utilizing the two optimal wavelengths were used for two different image analysis approaches. The first method applied a global threshold (0.45) to segregate the sour skin-infected areas from log-ratio images. Using the pixel number of the segregated areas, Fisher's discriminant analysis recognized 80{\%} healthy and sour skin-infected onions. The second classification approach used three parameters (max, contrast, and homogeneity) of the log-ratio images as the input features of support vector machine (Gaussian kernel, γ = 1.5), which discriminated 87.14{\%} healthy and sour skin-infected onions. The result of this study can be used to further develop a multispectral imaging system to detect sour skin-infected onions on packing lines.",
author = "Weilin Wang and Changying Li and Tollner, {Ernest W.} and Gitaitis, {Ronald D.} and Rains, {Glen Christopher}",
year = "2012",
month = "3",
day = "1",
doi = "10.1016/j.jfoodeng.2011.10.001",
language = "English",
volume = "109",
pages = "38--48",
journal = "Journal of Food Engineering",
issn = "0260-8774",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - Shortwave infrared hyperspectral imaging for detecting sour skin (Burkholderia cepacia)-infected onions

AU - Wang, Weilin

AU - Li, Changying

AU - Tollner, Ernest W.

AU - Gitaitis, Ronald D.

AU - Rains, Glen Christopher

PY - 2012/3/1

Y1 - 2012/3/1

N2 - Sour skin (Burkholderia cepacia) is a major postharvest disease for onions and causes substantial production and economic losses in onion postharvest. In this study, a shortwave infrared hyperspectral imaging system was explored to detect sour skin. The hyperspectral reflectance images (950-1650 nm) of onions were obtained for the healthy and sour skin-infected onions. Principal component analysis conducted on the spectra of the healthy and sour skin-infected onions suggested that the neck area of the onion at two wavelengths (1070 and 1400 nm) was most indicative of the sour skin. Log-ratio images utilizing the two optimal wavelengths were used for two different image analysis approaches. The first method applied a global threshold (0.45) to segregate the sour skin-infected areas from log-ratio images. Using the pixel number of the segregated areas, Fisher's discriminant analysis recognized 80% healthy and sour skin-infected onions. The second classification approach used three parameters (max, contrast, and homogeneity) of the log-ratio images as the input features of support vector machine (Gaussian kernel, γ = 1.5), which discriminated 87.14% healthy and sour skin-infected onions. The result of this study can be used to further develop a multispectral imaging system to detect sour skin-infected onions on packing lines.

AB - Sour skin (Burkholderia cepacia) is a major postharvest disease for onions and causes substantial production and economic losses in onion postharvest. In this study, a shortwave infrared hyperspectral imaging system was explored to detect sour skin. The hyperspectral reflectance images (950-1650 nm) of onions were obtained for the healthy and sour skin-infected onions. Principal component analysis conducted on the spectra of the healthy and sour skin-infected onions suggested that the neck area of the onion at two wavelengths (1070 and 1400 nm) was most indicative of the sour skin. Log-ratio images utilizing the two optimal wavelengths were used for two different image analysis approaches. The first method applied a global threshold (0.45) to segregate the sour skin-infected areas from log-ratio images. Using the pixel number of the segregated areas, Fisher's discriminant analysis recognized 80% healthy and sour skin-infected onions. The second classification approach used three parameters (max, contrast, and homogeneity) of the log-ratio images as the input features of support vector machine (Gaussian kernel, γ = 1.5), which discriminated 87.14% healthy and sour skin-infected onions. The result of this study can be used to further develop a multispectral imaging system to detect sour skin-infected onions on packing lines.

UR - http://www.scopus.com/inward/record.url?scp=81055140090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81055140090&partnerID=8YFLogxK

U2 - 10.1016/j.jfoodeng.2011.10.001

DO - 10.1016/j.jfoodeng.2011.10.001

M3 - Article

VL - 109

SP - 38

EP - 48

JO - Journal of Food Engineering

JF - Journal of Food Engineering

SN - 0260-8774

IS - 1

ER -