Identification and validation of key wavelengths for on-line beef tenderness forecasting

G. Konda Naganathan, K. Cluff, A. Samal, C. R. Calkins, D. D. Jones, R. L. Wehling, J. Subbiah

Research output: Contribution to journalArticle

Abstract

The objective of this study was to identify and validate key wavelengths in the visible/near-infrared (VNIR) spectral region for beef tenderness assessment using hyperspectral images of beef carcasses acquired on-line in a commercial beef packing plant. A prototype on-line spectrograph hyperspectral imaging (HSI) system was developed and used to acquire images of exposed ribeye muscle on hanging beef carcasses (n = 274) at 2 days post-mortem. After image acquisition, a strip steak was cut from each carcass and vacuum packaged. After aging for 14 days, the steaks were cooked and Warner-Bratzler shear force values were collected as a measure of tenderness. Hyperspectral and multispectral image analysis approaches were conducted and compared to each other in terms of accuracy and speed of implementation. In the hyperspectral approach, principal component analysis (PCA) was conducted to reduce the spectral dimension of the hyperspectral images and create principal component (PC) bands. Image textural features were extracted from the PC bands and modeled to classify samples into two tenderness categories (tender or tough). In the multispectral approach, the loading vectors obtained from the PCA procedure were used to identify five key wavelengths (584, 619, 739, 832, and 950 nm). Image textural features were then extracted from these key wavelength images and modeled. In both approaches, the image features were extracted from the images acquired at 2 days post-mortem and used to forecast 14-day beef tenderness. Using a true validation procedure involving 101 beef samples, the hyperspectral approach had a tender certification accuracy, tender identification accuracy, tough identification accuracy, and accuracy index value of 86.7%, 65.8%, 63.6, and 66.8%, respectively. The corresponding metrics for the multispectral approach were 87.5%, 62%, 68.2%, and 67.8%, respectively. The tenderness prediction results for these two analysis methods were not considerably different; however, multispectral image analysis took far less time (about 8 s compared to 105 s on a quad-core computer with 8 GB of memory) to classify a beef sample into one of the two tenderness categories (tender or tough). Therefore, the multispectral approach shows great potential for real-time beef tenderness assessment in commercial beef packing plants.

Original languageEnglish (US)
Pages (from-to)769-783
Number of pages15
JournalTransactions of the ASABE
Volume59
Issue number3
DOIs
StatePublished - Jan 1 2016

Fingerprint

Beef
wavelengths
beef
wavelength
Wavelength
hyperspectral imagery
Packing plants
packing houses
beef carcasses
steaks
image analysis
multispectral image
principal component analysis
Principal Component Analysis
Principal component analysis
Image analysis
certification
Red Meat
prototypes
sampling

Keywords

  • Band selection
  • Hyperspectral imaging
  • Instrument grading
  • Multispectral imaging
  • Principal component analysis

ASJC Scopus subject areas

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

Cite this

Naganathan, G. K., Cluff, K., Samal, A., Calkins, C. R., Jones, D. D., Wehling, R. L., & Subbiah, J. (2016). Identification and validation of key wavelengths for on-line beef tenderness forecasting. Transactions of the ASABE, 59(3), 769-783. https://doi.org/10.13031/trans.59.11034

Identification and validation of key wavelengths for on-line beef tenderness forecasting. / Naganathan, G. Konda; Cluff, K.; Samal, A.; Calkins, C. R.; Jones, D. D.; Wehling, R. L.; Subbiah, J.

In: Transactions of the ASABE, Vol. 59, No. 3, 01.01.2016, p. 769-783.

Research output: Contribution to journalArticle

Naganathan, GK, Cluff, K, Samal, A, Calkins, CR, Jones, DD, Wehling, RL & Subbiah, J 2016, 'Identification and validation of key wavelengths for on-line beef tenderness forecasting', Transactions of the ASABE, vol. 59, no. 3, pp. 769-783. https://doi.org/10.13031/trans.59.11034
Naganathan, G. Konda ; Cluff, K. ; Samal, A. ; Calkins, C. R. ; Jones, D. D. ; Wehling, R. L. ; Subbiah, J. / Identification and validation of key wavelengths for on-line beef tenderness forecasting. In: Transactions of the ASABE. 2016 ; Vol. 59, No. 3. pp. 769-783.
@article{e2a8a4689a4d41efb53274f5cf428c13,
title = "Identification and validation of key wavelengths for on-line beef tenderness forecasting",
abstract = "The objective of this study was to identify and validate key wavelengths in the visible/near-infrared (VNIR) spectral region for beef tenderness assessment using hyperspectral images of beef carcasses acquired on-line in a commercial beef packing plant. A prototype on-line spectrograph hyperspectral imaging (HSI) system was developed and used to acquire images of exposed ribeye muscle on hanging beef carcasses (n = 274) at 2 days post-mortem. After image acquisition, a strip steak was cut from each carcass and vacuum packaged. After aging for 14 days, the steaks were cooked and Warner-Bratzler shear force values were collected as a measure of tenderness. Hyperspectral and multispectral image analysis approaches were conducted and compared to each other in terms of accuracy and speed of implementation. In the hyperspectral approach, principal component analysis (PCA) was conducted to reduce the spectral dimension of the hyperspectral images and create principal component (PC) bands. Image textural features were extracted from the PC bands and modeled to classify samples into two tenderness categories (tender or tough). In the multispectral approach, the loading vectors obtained from the PCA procedure were used to identify five key wavelengths (584, 619, 739, 832, and 950 nm). Image textural features were then extracted from these key wavelength images and modeled. In both approaches, the image features were extracted from the images acquired at 2 days post-mortem and used to forecast 14-day beef tenderness. Using a true validation procedure involving 101 beef samples, the hyperspectral approach had a tender certification accuracy, tender identification accuracy, tough identification accuracy, and accuracy index value of 86.7{\%}, 65.8{\%}, 63.6, and 66.8{\%}, respectively. The corresponding metrics for the multispectral approach were 87.5{\%}, 62{\%}, 68.2{\%}, and 67.8{\%}, respectively. The tenderness prediction results for these two analysis methods were not considerably different; however, multispectral image analysis took far less time (about 8 s compared to 105 s on a quad-core computer with 8 GB of memory) to classify a beef sample into one of the two tenderness categories (tender or tough). Therefore, the multispectral approach shows great potential for real-time beef tenderness assessment in commercial beef packing plants.",
keywords = "Band selection, Hyperspectral imaging, Instrument grading, Multispectral imaging, Principal component analysis",
author = "Naganathan, {G. Konda} and K. Cluff and A. Samal and Calkins, {C. R.} and Jones, {D. D.} and Wehling, {R. L.} and J. Subbiah",
year = "2016",
month = "1",
day = "1",
doi = "10.13031/trans.59.11034",
language = "English (US)",
volume = "59",
pages = "769--783",
journal = "Transactions of the ASABE",
issn = "2151-0032",
publisher = "American Society of Agricultural and Biological Engineers",
number = "3",

}

TY - JOUR

T1 - Identification and validation of key wavelengths for on-line beef tenderness forecasting

AU - Naganathan, G. Konda

AU - Cluff, K.

AU - Samal, A.

AU - Calkins, C. R.

AU - Jones, D. D.

AU - Wehling, R. L.

AU - Subbiah, J.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - The objective of this study was to identify and validate key wavelengths in the visible/near-infrared (VNIR) spectral region for beef tenderness assessment using hyperspectral images of beef carcasses acquired on-line in a commercial beef packing plant. A prototype on-line spectrograph hyperspectral imaging (HSI) system was developed and used to acquire images of exposed ribeye muscle on hanging beef carcasses (n = 274) at 2 days post-mortem. After image acquisition, a strip steak was cut from each carcass and vacuum packaged. After aging for 14 days, the steaks were cooked and Warner-Bratzler shear force values were collected as a measure of tenderness. Hyperspectral and multispectral image analysis approaches were conducted and compared to each other in terms of accuracy and speed of implementation. In the hyperspectral approach, principal component analysis (PCA) was conducted to reduce the spectral dimension of the hyperspectral images and create principal component (PC) bands. Image textural features were extracted from the PC bands and modeled to classify samples into two tenderness categories (tender or tough). In the multispectral approach, the loading vectors obtained from the PCA procedure were used to identify five key wavelengths (584, 619, 739, 832, and 950 nm). Image textural features were then extracted from these key wavelength images and modeled. In both approaches, the image features were extracted from the images acquired at 2 days post-mortem and used to forecast 14-day beef tenderness. Using a true validation procedure involving 101 beef samples, the hyperspectral approach had a tender certification accuracy, tender identification accuracy, tough identification accuracy, and accuracy index value of 86.7%, 65.8%, 63.6, and 66.8%, respectively. The corresponding metrics for the multispectral approach were 87.5%, 62%, 68.2%, and 67.8%, respectively. The tenderness prediction results for these two analysis methods were not considerably different; however, multispectral image analysis took far less time (about 8 s compared to 105 s on a quad-core computer with 8 GB of memory) to classify a beef sample into one of the two tenderness categories (tender or tough). Therefore, the multispectral approach shows great potential for real-time beef tenderness assessment in commercial beef packing plants.

AB - The objective of this study was to identify and validate key wavelengths in the visible/near-infrared (VNIR) spectral region for beef tenderness assessment using hyperspectral images of beef carcasses acquired on-line in a commercial beef packing plant. A prototype on-line spectrograph hyperspectral imaging (HSI) system was developed and used to acquire images of exposed ribeye muscle on hanging beef carcasses (n = 274) at 2 days post-mortem. After image acquisition, a strip steak was cut from each carcass and vacuum packaged. After aging for 14 days, the steaks were cooked and Warner-Bratzler shear force values were collected as a measure of tenderness. Hyperspectral and multispectral image analysis approaches were conducted and compared to each other in terms of accuracy and speed of implementation. In the hyperspectral approach, principal component analysis (PCA) was conducted to reduce the spectral dimension of the hyperspectral images and create principal component (PC) bands. Image textural features were extracted from the PC bands and modeled to classify samples into two tenderness categories (tender or tough). In the multispectral approach, the loading vectors obtained from the PCA procedure were used to identify five key wavelengths (584, 619, 739, 832, and 950 nm). Image textural features were then extracted from these key wavelength images and modeled. In both approaches, the image features were extracted from the images acquired at 2 days post-mortem and used to forecast 14-day beef tenderness. Using a true validation procedure involving 101 beef samples, the hyperspectral approach had a tender certification accuracy, tender identification accuracy, tough identification accuracy, and accuracy index value of 86.7%, 65.8%, 63.6, and 66.8%, respectively. The corresponding metrics for the multispectral approach were 87.5%, 62%, 68.2%, and 67.8%, respectively. The tenderness prediction results for these two analysis methods were not considerably different; however, multispectral image analysis took far less time (about 8 s compared to 105 s on a quad-core computer with 8 GB of memory) to classify a beef sample into one of the two tenderness categories (tender or tough). Therefore, the multispectral approach shows great potential for real-time beef tenderness assessment in commercial beef packing plants.

KW - Band selection

KW - Hyperspectral imaging

KW - Instrument grading

KW - Multispectral imaging

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=84975728065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975728065&partnerID=8YFLogxK

U2 - 10.13031/trans.59.11034

DO - 10.13031/trans.59.11034

M3 - Article

AN - SCOPUS:84975728065

VL - 59

SP - 769

EP - 783

JO - Transactions of the ASABE

JF - Transactions of the ASABE

SN - 2151-0032

IS - 3

ER -