Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling

Kim Cluff, Govindarajan Konda Naganathan, Jeyamkondan Subbiah, Ashok K Samal, Chris R. Calkins

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

The objective of this study was to develop a non-destructive method for classifying cooked-beef tenderness using hyperspectral imaging of optical scattering on fresh beef muscle tissue. A hyperspectral imaging system (λ = 922-1739. nm) was used to collect hyperspectral scattering images of the longissimus dorsi muscle (n = 472). A modified Lorentzian function was used to fit optical scattering profiles at each wavelength. After removing highly correlated parameters extracted from the Lorentzian function, principal component analysis was performed. Four principal component scores were used in a linear discriminant model to classify beef tenderness. In a validation data set (n = 118 samples), the model was able to successfully classify tough and tender samples with 83.3% and 75.0% accuracies, respectively. Presence of fat flecks did not have a significant effect on beef tenderness classification accuracy. The results demonstrate that hyperspectral imaging of optical scattering is a viable technology for beef tenderness classification.

Original languageEnglish (US)
Pages (from-to)42-50
Number of pages9
JournalMeat Science
Volume95
Issue number1
DOIs
StatePublished - Sep 1 2013

Fingerprint

longissimus muscle
beef
image analysis
Muscles
muscles
Optical Imaging
nondestructive methods
Principal Component Analysis
muscle tissues
wavelengths
Linear Models
principal component analysis
Fats
Red Meat
Technology
sampling
lipids

Keywords

  • Beef tenderness
  • Computer vision
  • Linear discriminant analysis
  • Lorentzian distribution function
  • Optical scattering
  • Principal component analysis

ASJC Scopus subject areas

  • Food Science

Cite this

Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling. / Cluff, Kim; Konda Naganathan, Govindarajan; Subbiah, Jeyamkondan; Samal, Ashok K; Calkins, Chris R.

In: Meat Science, Vol. 95, No. 1, 01.09.2013, p. 42-50.

Research output: Contribution to journalArticle

Cluff, Kim ; Konda Naganathan, Govindarajan ; Subbiah, Jeyamkondan ; Samal, Ashok K ; Calkins, Chris R. / Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling. In: Meat Science. 2013 ; Vol. 95, No. 1. pp. 42-50.
@article{397e99d3358744f8a502a9194dc0de66,
title = "Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling",
abstract = "The objective of this study was to develop a non-destructive method for classifying cooked-beef tenderness using hyperspectral imaging of optical scattering on fresh beef muscle tissue. A hyperspectral imaging system (λ = 922-1739. nm) was used to collect hyperspectral scattering images of the longissimus dorsi muscle (n = 472). A modified Lorentzian function was used to fit optical scattering profiles at each wavelength. After removing highly correlated parameters extracted from the Lorentzian function, principal component analysis was performed. Four principal component scores were used in a linear discriminant model to classify beef tenderness. In a validation data set (n = 118 samples), the model was able to successfully classify tough and tender samples with 83.3{\%} and 75.0{\%} accuracies, respectively. Presence of fat flecks did not have a significant effect on beef tenderness classification accuracy. The results demonstrate that hyperspectral imaging of optical scattering is a viable technology for beef tenderness classification.",
keywords = "Beef tenderness, Computer vision, Linear discriminant analysis, Lorentzian distribution function, Optical scattering, Principal component analysis",
author = "Kim Cluff and {Konda Naganathan}, Govindarajan and Jeyamkondan Subbiah and Samal, {Ashok K} and Calkins, {Chris R.}",
year = "2013",
month = "9",
day = "1",
doi = "10.1016/j.meatsci.2013.04.014",
language = "English (US)",
volume = "95",
pages = "42--50",
journal = "Meat Science",
issn = "0309-1740",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling

AU - Cluff, Kim

AU - Konda Naganathan, Govindarajan

AU - Subbiah, Jeyamkondan

AU - Samal, Ashok K

AU - Calkins, Chris R.

PY - 2013/9/1

Y1 - 2013/9/1

N2 - The objective of this study was to develop a non-destructive method for classifying cooked-beef tenderness using hyperspectral imaging of optical scattering on fresh beef muscle tissue. A hyperspectral imaging system (λ = 922-1739. nm) was used to collect hyperspectral scattering images of the longissimus dorsi muscle (n = 472). A modified Lorentzian function was used to fit optical scattering profiles at each wavelength. After removing highly correlated parameters extracted from the Lorentzian function, principal component analysis was performed. Four principal component scores were used in a linear discriminant model to classify beef tenderness. In a validation data set (n = 118 samples), the model was able to successfully classify tough and tender samples with 83.3% and 75.0% accuracies, respectively. Presence of fat flecks did not have a significant effect on beef tenderness classification accuracy. The results demonstrate that hyperspectral imaging of optical scattering is a viable technology for beef tenderness classification.

AB - The objective of this study was to develop a non-destructive method for classifying cooked-beef tenderness using hyperspectral imaging of optical scattering on fresh beef muscle tissue. A hyperspectral imaging system (λ = 922-1739. nm) was used to collect hyperspectral scattering images of the longissimus dorsi muscle (n = 472). A modified Lorentzian function was used to fit optical scattering profiles at each wavelength. After removing highly correlated parameters extracted from the Lorentzian function, principal component analysis was performed. Four principal component scores were used in a linear discriminant model to classify beef tenderness. In a validation data set (n = 118 samples), the model was able to successfully classify tough and tender samples with 83.3% and 75.0% accuracies, respectively. Presence of fat flecks did not have a significant effect on beef tenderness classification accuracy. The results demonstrate that hyperspectral imaging of optical scattering is a viable technology for beef tenderness classification.

KW - Beef tenderness

KW - Computer vision

KW - Linear discriminant analysis

KW - Lorentzian distribution function

KW - Optical scattering

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=84877315220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877315220&partnerID=8YFLogxK

U2 - 10.1016/j.meatsci.2013.04.014

DO - 10.1016/j.meatsci.2013.04.014

M3 - Article

C2 - 23648431

AN - SCOPUS:84877315220

VL - 95

SP - 42

EP - 50

JO - Meat Science

JF - Meat Science

SN - 0309-1740

IS - 1

ER -