Visible/near-infrared hyperspectral imaging for beef tenderness prediction

Govindarajan Konda Naganathan, Lauren M. Grimes, Jeyamkondan Subbiah, Chris R. Calkins, Ashok K Samal, George E. Meyer

Research output: Contribution to journalArticle

160 Citations (Scopus)

Abstract

Beef tenderness is an important quality attribute for consumer satisfaction. The current beef quality grading system does not incorporate a direct measure of tenderness because there is currently no accurate, rapid, nondestructive method for predicting tenderness available to the beef industry. The objective of this study was to develop and test a visible/near-infrared hyperspectral imaging system to predict tenderness of 14-day aged, cooked beef from hyperspectral images of fresh ribeye steaks acquired at 14-day post-mortem. A pushbroom hyperspectral imaging system (wavelength range: 400-1000 nm) with a diffuse-flood lighting system was developed and calibrated. Hyperspectral images of beef-steak (n = 111) at 14-day post-mortem were acquired. After imaging, steaks were cooked and slice shear force (SSF) values were collected as a tenderness reference. All images were corrected for reflectance. After reflectance calibration, a region-of-interest (ROI) of 200 × 600 pixels at the center was selected and principal component analysis was carried out on the ROI images to reduce the dimension along the spectral axis. The first five principal components explained over 90% of the variance of all spectral bands in the image. Gray-level textural co-occurrence matrix analysis was conducted to extract second-order statistical textural features from the principal component images. These features were then used in a canonical discriminant model to predict three beef tenderness categories, namely tender (SSF ≤ 205.80 N), intermediate (205.80 N < SSF < 254.80 N), and tough (SSF ≥ 254.80 N). With a leave-one-out cross-validation procedure, the model predicted the three tenderness categories with a 96.4% accuracy. All of the tough samples were correctly identified. Our results indicate that hyperspectral imaging has considerable promise for predicting beef tenderness.

Original languageEnglish (US)
Pages (from-to)225-233
Number of pages9
JournalComputers and Electronics in Agriculture
Volume64
Issue number2
DOIs
StatePublished - Dec 1 2008

Fingerprint

Beef
Infrared imaging
near infrared
beef
image analysis
shears
steaks
prediction
hyperspectral imagery
reflectance
consumer satisfaction
Imaging systems
beef industry
beef quality
nondestructive methods
lighting
wavelengths
principal component analysis
calibration
Hyperspectral imaging

Keywords

  • Beef tenderness
  • Hyperspectral imaging
  • Instrument grading
  • Principal component analysis
  • Textural co-occurrence matrices

ASJC Scopus subject areas

  • Forestry
  • Agronomy and Crop Science
  • Computer Science Applications
  • Horticulture

Cite this

Visible/near-infrared hyperspectral imaging for beef tenderness prediction. / Naganathan, Govindarajan Konda; Grimes, Lauren M.; Subbiah, Jeyamkondan; Calkins, Chris R.; Samal, Ashok K; Meyer, George E.

In: Computers and Electronics in Agriculture, Vol. 64, No. 2, 01.12.2008, p. 225-233.

Research output: Contribution to journalArticle

Naganathan, Govindarajan Konda ; Grimes, Lauren M. ; Subbiah, Jeyamkondan ; Calkins, Chris R. ; Samal, Ashok K ; Meyer, George E. / Visible/near-infrared hyperspectral imaging for beef tenderness prediction. In: Computers and Electronics in Agriculture. 2008 ; Vol. 64, No. 2. pp. 225-233.
@article{2286a76c49104f8c952dbd74e75e1c64,
title = "Visible/near-infrared hyperspectral imaging for beef tenderness prediction",
abstract = "Beef tenderness is an important quality attribute for consumer satisfaction. The current beef quality grading system does not incorporate a direct measure of tenderness because there is currently no accurate, rapid, nondestructive method for predicting tenderness available to the beef industry. The objective of this study was to develop and test a visible/near-infrared hyperspectral imaging system to predict tenderness of 14-day aged, cooked beef from hyperspectral images of fresh ribeye steaks acquired at 14-day post-mortem. A pushbroom hyperspectral imaging system (wavelength range: 400-1000 nm) with a diffuse-flood lighting system was developed and calibrated. Hyperspectral images of beef-steak (n = 111) at 14-day post-mortem were acquired. After imaging, steaks were cooked and slice shear force (SSF) values were collected as a tenderness reference. All images were corrected for reflectance. After reflectance calibration, a region-of-interest (ROI) of 200 × 600 pixels at the center was selected and principal component analysis was carried out on the ROI images to reduce the dimension along the spectral axis. The first five principal components explained over 90{\%} of the variance of all spectral bands in the image. Gray-level textural co-occurrence matrix analysis was conducted to extract second-order statistical textural features from the principal component images. These features were then used in a canonical discriminant model to predict three beef tenderness categories, namely tender (SSF ≤ 205.80 N), intermediate (205.80 N < SSF < 254.80 N), and tough (SSF ≥ 254.80 N). With a leave-one-out cross-validation procedure, the model predicted the three tenderness categories with a 96.4{\%} accuracy. All of the tough samples were correctly identified. Our results indicate that hyperspectral imaging has considerable promise for predicting beef tenderness.",
keywords = "Beef tenderness, Hyperspectral imaging, Instrument grading, Principal component analysis, Textural co-occurrence matrices",
author = "Naganathan, {Govindarajan Konda} and Grimes, {Lauren M.} and Jeyamkondan Subbiah and Calkins, {Chris R.} and Samal, {Ashok K} and Meyer, {George E.}",
year = "2008",
month = "12",
day = "1",
doi = "10.1016/j.compag.2008.05.020",
language = "English (US)",
volume = "64",
pages = "225--233",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Visible/near-infrared hyperspectral imaging for beef tenderness prediction

AU - Naganathan, Govindarajan Konda

AU - Grimes, Lauren M.

AU - Subbiah, Jeyamkondan

AU - Calkins, Chris R.

AU - Samal, Ashok K

AU - Meyer, George E.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Beef tenderness is an important quality attribute for consumer satisfaction. The current beef quality grading system does not incorporate a direct measure of tenderness because there is currently no accurate, rapid, nondestructive method for predicting tenderness available to the beef industry. The objective of this study was to develop and test a visible/near-infrared hyperspectral imaging system to predict tenderness of 14-day aged, cooked beef from hyperspectral images of fresh ribeye steaks acquired at 14-day post-mortem. A pushbroom hyperspectral imaging system (wavelength range: 400-1000 nm) with a diffuse-flood lighting system was developed and calibrated. Hyperspectral images of beef-steak (n = 111) at 14-day post-mortem were acquired. After imaging, steaks were cooked and slice shear force (SSF) values were collected as a tenderness reference. All images were corrected for reflectance. After reflectance calibration, a region-of-interest (ROI) of 200 × 600 pixels at the center was selected and principal component analysis was carried out on the ROI images to reduce the dimension along the spectral axis. The first five principal components explained over 90% of the variance of all spectral bands in the image. Gray-level textural co-occurrence matrix analysis was conducted to extract second-order statistical textural features from the principal component images. These features were then used in a canonical discriminant model to predict three beef tenderness categories, namely tender (SSF ≤ 205.80 N), intermediate (205.80 N < SSF < 254.80 N), and tough (SSF ≥ 254.80 N). With a leave-one-out cross-validation procedure, the model predicted the three tenderness categories with a 96.4% accuracy. All of the tough samples were correctly identified. Our results indicate that hyperspectral imaging has considerable promise for predicting beef tenderness.

AB - Beef tenderness is an important quality attribute for consumer satisfaction. The current beef quality grading system does not incorporate a direct measure of tenderness because there is currently no accurate, rapid, nondestructive method for predicting tenderness available to the beef industry. The objective of this study was to develop and test a visible/near-infrared hyperspectral imaging system to predict tenderness of 14-day aged, cooked beef from hyperspectral images of fresh ribeye steaks acquired at 14-day post-mortem. A pushbroom hyperspectral imaging system (wavelength range: 400-1000 nm) with a diffuse-flood lighting system was developed and calibrated. Hyperspectral images of beef-steak (n = 111) at 14-day post-mortem were acquired. After imaging, steaks were cooked and slice shear force (SSF) values were collected as a tenderness reference. All images were corrected for reflectance. After reflectance calibration, a region-of-interest (ROI) of 200 × 600 pixels at the center was selected and principal component analysis was carried out on the ROI images to reduce the dimension along the spectral axis. The first five principal components explained over 90% of the variance of all spectral bands in the image. Gray-level textural co-occurrence matrix analysis was conducted to extract second-order statistical textural features from the principal component images. These features were then used in a canonical discriminant model to predict three beef tenderness categories, namely tender (SSF ≤ 205.80 N), intermediate (205.80 N < SSF < 254.80 N), and tough (SSF ≥ 254.80 N). With a leave-one-out cross-validation procedure, the model predicted the three tenderness categories with a 96.4% accuracy. All of the tough samples were correctly identified. Our results indicate that hyperspectral imaging has considerable promise for predicting beef tenderness.

KW - Beef tenderness

KW - Hyperspectral imaging

KW - Instrument grading

KW - Principal component analysis

KW - Textural co-occurrence matrices

UR - http://www.scopus.com/inward/record.url?scp=53549119943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=53549119943&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2008.05.020

DO - 10.1016/j.compag.2008.05.020

M3 - Article

AN - SCOPUS:53549119943

VL - 64

SP - 225

EP - 233

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

IS - 2

ER -