Abstract
Three factors, including tenderness, juiciness and flavour, are found to have an impact on lamb eating quality, which determines the repurchase behaviour of customers. In addition to these factors, the surface colour of lamb can also influence the purchase decision of consumers. From a long time ago, meat industries have been looking for fast and non-invasive objective quality evaluation approaches, where near-infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) have shown great promises in assessing beef quality compared with conventional methods. However, rare research has been conducted for lamb samples. Therefore, in this paper the feasibility of the HSI system for evaluating lamb quality was tested. In total 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, noise was further removed from HSI spectra by singular spectrum analysis (SSA) for better performance. Considering support vector machine (SVM) is sensitive to high dimensional data, principal component analysis (PCA) was applied to reduce the dimensionality of HSI spectra before feeding into SVM for constructing prediction equations. The prediction results suggest that HSI is promising in predicting some lamb eating quality traits, which could be beneficial for lamb industries.
Zusammenfassung
Die drei Faktoren Zartheit, Saftigkeit und Geschmack beeinflussen die Qualität von Lammfleisch erheblich und sind damit entscheidende Kriterien dafür, ob ein Produkt vom Kunden nochmals gekauft werden wird oder nicht. Neben diesen Faktoren wird das Kaufverhalten des Kunden zusätzlich durch die äußerliche farbliche Erscheinung des Fleisches beeinflusst. Seit langer Zeit ist die Fleischindustrie auf der Suche nach schnellen, nicht invasiven und objektiven Verfahren zur Qualitätskontrolle. Verglichen mit konventionellen Methoden zeigten die Nahinfrarotspektroskopie (NIRS) und die hyperspektrale Bildgebung (HSI) vielversprechende Ergebnisse bezüglich der Bestimmung der Fleischqualität. Lammfleischproben wurden jedoch nur selten untersucht. Daher wurde im Rahmen dieses Beitrags die Eignung eines HSI-Systems zur Prüfung von Lammfleischqualität evaluiert. Insgesamt wurden mittels eines HSI-Systems von 80 Lammfleischproben Bilder im sichtbaren Spektralbereich aufgenommen und für die Bestimmung von mit der Fleischqualität verwandten Merkmalen verwendet. Zusätzlich wurde per Singular Spectrum Analysis (SSA) bei einigen Merkmalen vorhandenes Rauschen von den HSI-Spektren entfernt. Da die Support Vector Machine (SVM) empfindlich auf hochdimensionale Daten reagieren kann, wurde die Dimension der HSI-Spektren mittels einer Hauptkomponentenanalyse (PCA) reduziert, bevor die Daten zum Trainieren der SVM verwendet wurden. Die Klassifikationsergebnisse deuten darauf hin, dass HSI-Spektren für die Bestimmung einiger Qualitätsmerkmale von Lammfleisch durchaus geeignet sind. Für die Fleischindustrie könnten diese Ergebnisse von Vorteil sein.
Funding statement: T. Qiao, J. Ren and J. Zabalza would like to thank the support from University of Strathclyde and Quality Meat Scotland. Z. Yang would like to acknowledge support from National Natural Science Foundation of China (NSFC, #61471132). C. Qing would like to acknowledge the support from both NSFC (#61401163) and the Fundamental Research Funds for the Central Universities (No. 2015ZZ032).
About the authors
Tong Qiao received the B.Eng. degree (1st class) in Electrical and Electronic Engineering from University of Manchester in 2009, and the M.Sc. degree (distinction) in the same major from University of Strathclyde in 2010. She is currently working towards the Ph.D. degree in the Centre for excellence in Signal and Image Processing (CeSIP), Department of Electronic and Electrical Engineering, University of Strathclyde. Her research interests include hyperspectral imaging based applications and feature extraction for remote sensing image classification.
Centre for excellence in Signal and Image Processing (CeSIP), Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, UK
Jinchang Ren received his B. Eng. degree in computer software, MEng in image processing, DEng in computer vision, all from Northwestern Polytechnical University (NWPU), China. He was also awarded a PhD in Electronic Imaging and Media Communication from Bradford University, U.K. His research interests focus mainly on visual computing and multimedia signal processing, especially on semantic content extraction for video analysis and understanding and more recently hyperspectral imaging.
Centre for excellence in Signal and Image Processing (CeSIP), Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, UK
Zhijing Yang received the B.S. and Ph.D. degrees from the Faculty of Mathematics and Computing Science, Sun Yat-Sen University, Guangzhou, China, in 2003 and 2008, respectively. He was a Visiting Research Scholar in the School of Computing, Informatics and Media, University of Bradford, U.K., between July–Dec. 2009, and a Research Fellow in the School of Engineering, University of Lincoln, U.K., between Jan. 2011 to Jan. 2013. He is currently an Associate Professor in the Faculty of Information Engineering, Guangdong University of Technology, China. His research interests include time-frequency analysis, signal processing, machine learning, and pattern recognition.
School of Information Engineering, Guangdong University of Technology, Guangzhou, 510006, China
Chunmei Qing received her B.Sc. degree in Information and Computation Science from Sun Yat-sen University, China, in 2003, and Ph.D. degree in Electronic Imaging and Media Communications from University of Bradford, UK, in 2009. She was a postdoc researcher in the University of Lincoln, U.K. She is currently an Associate Professor in School of Electronic and Information Engineering, South China University of Technology, China. Her research interests include image/video processing, human-computer interaction, video surveillance and machine learning.
School of Electronics and Information Engineering, South China University of Technology, Guangzhou, 510641, China
Jaime Zabalza received the MEng in Industrial Engineering from the Universitat Jaume I (UJI), Spain, in 2006, the MAS in Electrical Technology at the Universitat Politecnica de Valencia, Spain, in 2010 and the MSc (distinction) in Electronic and Electrical Engineering from the University of Strathclyde, UK, in 2012. He has been recently awarded a PhD degree in CeSIP, University of Strathclyde. From 2006 to 2011, he was with UJI as a Research and Development Engineer and worked with the Energy Technological Institute, Valencia, Spain, in multidisciplinary fields including power electronics, automation, and computer science. His interests include synthetic aperture radar and remote sensing, hyperspectral imaging, and digital signal processing, including signal processing in a wide range of applications.
Centre for excellence in Signal and Image Processing (CeSIP), Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, UK
Stephen Marshall received the BSc degree in electrical and electronic engineering and the PhD degree in image processing respectively from the University of Nottingham and the University of Strathclyde, U.K. With over 150 papers published, his research activities focus in nonlinear image processing and hyperspectral imaging. Currently he is a Professor with the Department of Electronic and Electrical Engineering in Strathclyde, and a Fellow of the IET.
University of Strathclyde, Department of Electronic and Electrical Engineering, Glasgow, UK
Acknowledgement
Authors would like to thank Dr. Cameron Craigie and Scotland's Rural College (SRUC) for helping preparing the data. Also special thanks to the associate editor and the anonymous reviewers for their careful reading and helpful remarks to improve the paper quality. An earlier version of this paper was presented at the 2nd conference on Optical Characterization of Materials (OCM) in 2015.
©2015 Walter de Gruyter Berlin/Boston
