Prediction of lamb eating quality using hyperspectral imaging

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

Lamb eating quality is related to 3 factors, which are tenderness, juiciness and flavour. In addition to these factors, the surface colour of lamb could influence the purchase decision of consumers. Objective quality evaluation approaches, like near infrared spectroscopy (NIRS) and hyperspectral imaging (HSI), have been proved fast and non-destructive in assessing beef quality, compared with conventional methods. However, rare research has been done for lamb samples. Therefore, in this paper the feasibility of HSI for evaluating lamb quality is tested. A total of 80 lamb samples were imaged using a visible range HSI system and the spectral profiles were used for predicting lamb quality related traits. For some traits, noises were removed from HSI spectra by singular spectrum analysis (SSA) for better performance. Support vector machine (SVM) was employed to construct prediction equations. Considering SVM is sensitive to high dimensional data, principal component analysis (PCA) was applied to reduce the dimensionality first. The prediction results suggest that HSI is promising in predicting lamb eating quality
LanguageEnglish
Title of host publicationOCM (Optical Characterization of Materials) 2015
Subtitle of host publication2nd International Conference on Optical Characterization of Materials
EditorsJürgen Beyerer, Fernando Puente León, Thomas Längle
Place of PublicationKarlsruhe, Germany
Pages15-25
Number of pages10
DOIs
Publication statusPublished - 15 Mar 2015
EventOCM (Optical Characterization of Materials) 2015 - Karlsruhe, Germany
Duration: 18 Mar 201519 Mar 2015

Conference

ConferenceOCM (Optical Characterization of Materials) 2015
Abbreviated titleOCM 2015
CountryGermany
CityKarlsruhe
Period18/03/1519/03/15

Fingerprint

eating
predictions
Support vector machines
Beef
Near infrared spectroscopy
Flavors
Imaging systems
Principal component analysis
Spectrum analysis
principal components analysis
spectrum analysis
Hyperspectral imaging
Color
infrared spectroscopy
color
evaluation
profiles

Keywords

  • hyperspectral imaging (HSI)
  • singular spectrum analysis (SSA)
  • principal component analysis (PCA)
  • lamb eating quality
  • tenderness
  • juiciness
  • flavour

Cite this

Qiao, T., Ren, J., Zabalza, J., & Marshall, S. (2015). Prediction of lamb eating quality using hyperspectral imaging. In J. Beyerer, F. Puente León, & T. Längle (Eds.), OCM (Optical Characterization of Materials) 2015: 2nd International Conference on Optical Characterization of Materials (pp. 15-25). Karlsruhe, Germany. https://doi.org/10.5445/KSP/1000044906
Qiao, Tong ; Ren, Jinchang ; Zabalza, Jaime ; Marshall, Stephen. / Prediction of lamb eating quality using hyperspectral imaging. OCM (Optical Characterization of Materials) 2015: 2nd International Conference on Optical Characterization of Materials. editor / Jürgen Beyerer ; Fernando Puente León ; Thomas Längle. Karlsruhe, Germany, 2015. pp. 15-25
@inproceedings{65c8b1d6c6d54031abdfbf8795072916,
title = "Prediction of lamb eating quality using hyperspectral imaging",
abstract = "Lamb eating quality is related to 3 factors, which are tenderness, juiciness and flavour. In addition to these factors, the surface colour of lamb could influence the purchase decision of consumers. Objective quality evaluation approaches, like near infrared spectroscopy (NIRS) and hyperspectral imaging (HSI), have been proved fast and non-destructive in assessing beef quality, compared with conventional methods. However, rare research has been done for lamb samples. Therefore, in this paper the feasibility of HSI for evaluating lamb quality is tested. A total of 80 lamb samples were imaged using a visible range HSI system and the spectral profiles were used for predicting lamb quality related traits. For some traits, noises were removed from HSI spectra by singular spectrum analysis (SSA) for better performance. Support vector machine (SVM) was employed to construct prediction equations. Considering SVM is sensitive to high dimensional data, principal component analysis (PCA) was applied to reduce the dimensionality first. The prediction results suggest that HSI is promising in predicting lamb eating quality",
keywords = "hyperspectral imaging (HSI), singular spectrum analysis (SSA), principal component analysis (PCA), lamb eating quality, tenderness, juiciness, flavour",
author = "Tong Qiao and Jinchang Ren and Jaime Zabalza and Stephen Marshall",
year = "2015",
month = "3",
day = "15",
doi = "10.5445/KSP/1000044906",
language = "English",
isbn = "978-3-7315-0318-7",
pages = "15--25",
editor = "J{\"u}rgen Beyerer and {Puente Le{\'o}n}, Fernando and Thomas L{\"a}ngle",
booktitle = "OCM (Optical Characterization of Materials) 2015",

}

Qiao, T, Ren, J, Zabalza, J & Marshall, S 2015, Prediction of lamb eating quality using hyperspectral imaging. in J Beyerer, F Puente León & T Längle (eds), OCM (Optical Characterization of Materials) 2015: 2nd International Conference on Optical Characterization of Materials. Karlsruhe, Germany, pp. 15-25, OCM (Optical Characterization of Materials) 2015, Karlsruhe, Germany, 18/03/15. https://doi.org/10.5445/KSP/1000044906

Prediction of lamb eating quality using hyperspectral imaging. / Qiao, Tong; Ren, Jinchang; Zabalza, Jaime; Marshall, Stephen.

OCM (Optical Characterization of Materials) 2015: 2nd International Conference on Optical Characterization of Materials. ed. / Jürgen Beyerer; Fernando Puente León; Thomas Längle. Karlsruhe, Germany, 2015. p. 15-25.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Prediction of lamb eating quality using hyperspectral imaging

AU - Qiao, Tong

AU - Ren, Jinchang

AU - Zabalza, Jaime

AU - Marshall, Stephen

PY - 2015/3/15

Y1 - 2015/3/15

N2 - Lamb eating quality is related to 3 factors, which are tenderness, juiciness and flavour. In addition to these factors, the surface colour of lamb could influence the purchase decision of consumers. Objective quality evaluation approaches, like near infrared spectroscopy (NIRS) and hyperspectral imaging (HSI), have been proved fast and non-destructive in assessing beef quality, compared with conventional methods. However, rare research has been done for lamb samples. Therefore, in this paper the feasibility of HSI for evaluating lamb quality is tested. A total of 80 lamb samples were imaged using a visible range HSI system and the spectral profiles were used for predicting lamb quality related traits. For some traits, noises were removed from HSI spectra by singular spectrum analysis (SSA) for better performance. Support vector machine (SVM) was employed to construct prediction equations. Considering SVM is sensitive to high dimensional data, principal component analysis (PCA) was applied to reduce the dimensionality first. The prediction results suggest that HSI is promising in predicting lamb eating quality

AB - Lamb eating quality is related to 3 factors, which are tenderness, juiciness and flavour. In addition to these factors, the surface colour of lamb could influence the purchase decision of consumers. Objective quality evaluation approaches, like near infrared spectroscopy (NIRS) and hyperspectral imaging (HSI), have been proved fast and non-destructive in assessing beef quality, compared with conventional methods. However, rare research has been done for lamb samples. Therefore, in this paper the feasibility of HSI for evaluating lamb quality is tested. A total of 80 lamb samples were imaged using a visible range HSI system and the spectral profiles were used for predicting lamb quality related traits. For some traits, noises were removed from HSI spectra by singular spectrum analysis (SSA) for better performance. Support vector machine (SVM) was employed to construct prediction equations. Considering SVM is sensitive to high dimensional data, principal component analysis (PCA) was applied to reduce the dimensionality first. The prediction results suggest that HSI is promising in predicting lamb eating quality

KW - hyperspectral imaging (HSI)

KW - singular spectrum analysis (SSA)

KW - principal component analysis (PCA)

KW - lamb eating quality

KW - tenderness

KW - juiciness

KW - flavour

UR - http://digbib.ubka.uni-karlsruhe.de/volltexte/1000044906

UR - http://www.ocm-2013.eu/

U2 - 10.5445/KSP/1000044906

DO - 10.5445/KSP/1000044906

M3 - Conference contribution book

SN - 978-3-7315-0318-7

SP - 15

EP - 25

BT - OCM (Optical Characterization of Materials) 2015

A2 - Beyerer, Jürgen

A2 - Puente León, Fernando

A2 - Längle, Thomas

CY - Karlsruhe, Germany

ER -

Qiao T, Ren J, Zabalza J, Marshall S. Prediction of lamb eating quality using hyperspectral imaging. In Beyerer J, Puente León F, Längle T, editors, OCM (Optical Characterization of Materials) 2015: 2nd International Conference on Optical Characterization of Materials. Karlsruhe, Germany. 2015. p. 15-25 https://doi.org/10.5445/KSP/1000044906