Detection of expired vacuum-packed smoked salmon based on PLS-DA method using hyperspectral images

Abstract Consumers want fresh food with a long shelf-life, which in 2010, resulted in an important increase in packaged and processed food. This is especially important for fishery products due to their highly perishable nature. One problem is that it is not possible to measure freshness in packaged food only using the visible spectrum. Moreover, the detection of freshness is a complex problem as fish has different tissues with different biodegradation processes. Therefore, it would be especially interesting to have a non-destructive method to evaluate the shelf-life of packed processed fish. This paper proposes a method for detecting expired packaged salmon. Firstly, this method uses hyperspectral imaging spectroscopy (HIS) using visible and SW-NIR wavelengths. Secondly, a classification of different salmon tissues is carried out by image segmentation. Finally, classifications of expired or non expired salmon are performed with the PLS-DA statistical multivariate method due to the large amount of captured data. In a similar way, spectral data and the physicochemical, biochemical and microbiological properties of salmon are correlated using partial least squares (PLSs). The result obtained has a classification success rate of 82.7% in cross-validation from real commercial samples of salmon. Therefore, this is a promising technique for the non-destructive detection of expired packaged smoked salmon.

[1]  Fredrik Manne,et al.  Rapid estimation of fat content in salmon fillets by colour image analysis , 2007 .

[2]  Karsten Heia,et al.  Automatic freshness assessment of cod (Gadus morhua) fillets by Vis/Nir spectroscopy , 2011 .

[3]  M. Cardinal,et al.  Study of the microbial ecology of cold-smoked salmon during storage at 8°C , 1998 .

[4]  Colm P. O'Donnell,et al.  Hyperspectral imaging – an emerging process analytical tool for food quality and safety control , 2007 .

[5]  Clifton E. Meloan,et al.  Determination of Moisture , 1994 .

[6]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  J. Barat,et al.  Nondestructive assessment of freshness in packaged sliced chicken breasts using SW-NIR spectroscopy , 2011 .

[8]  Teri Hiltunen,et al.  Multivariate modelling of fish freshness index based on ion mobility spectrometry measurements , 2005 .

[9]  Baozong Yuan,et al.  A new algorithm for texture segmentation based on edge detection , 1991, Pattern Recognit..

[10]  John Reidar Mathiassen,et al.  Trends in application of imaging technologies to inspection of fish and fish products , 2011 .

[11]  Josse De Baerdemaeker,et al.  Hyperspectral waveband selection for on-line measurement of grain cleanness , 2009 .

[12]  M. Thomassen,et al.  Starvation prior to slaughter in Atlantic salmon (Salmo salar): II. White muscle composition and evaluation of freshness, texture and colour characteristics in raw and cooked fillets , 1998 .

[13]  H. Allan Bremner,et al.  A Critical Look at Whether ‘Freshness’ Can Be Determined , 2000 .

[14]  M. Al-Bachir,et al.  Effect of gamma irradiation on microbial load and quality characteristics of minced camel meat. , 2009, Meat science.

[15]  Angela Trocino,et al.  Prediction of chemical composition and origin identification of European sea bass (Dicentrarchus labrax L.) by near infrared reflectance spectroscopy (NIRS) , 2004 .

[16]  Paolo Menesatti,et al.  Quality Evaluation of Fish by Hyperspectral Imaging , 2010 .

[17]  Cláudio Rosito Jung,et al.  Unsupervised multiscale segmentation of color images , 2007, Pattern Recognit. Lett..

[18]  Edward,et al.  Quality assurance systems in food industry and health security of food , 2007 .

[19]  Paw Dalgaard,et al.  Methods to evaluate fish freshness in research and industry , 1997 .

[20]  Karsten Heia,et al.  Visible/Near‐Infrared Spectroscopy: A New Tool for the Evaluation of Fish Freshness? , 2002 .

[21]  F. Toldrá,et al.  Freshness monitoring of sea bream (Sparus aurata) with a potentiometric sensor. , 2008, Food chemistry.

[22]  B. Jørgensen,et al.  Rapid Assessment of Quality Parameters for Frozen Cod Using Near Infrared Spectroscopy , 1998 .

[23]  P. Malle,et al.  Rapid Quantitative Determination of Trimethylamine using Steam Distillation. , 1987, Journal of food protection.

[24]  Javier Carballo,et al.  Biochemical characteristics of dry-cured lacón (a Spanish traditional meat product) throughout the manufacture, and sensorial properties of the final product. Effect of some additives , 2008 .

[25]  Daniel Nyström.  Colorimetric and Multispectral Image Acquisition Using Model-Based and Empirical Device Characterization , 2007, SCIA.

[26]  Antonella Macagnano,et al.  Multisensor for fish quality determination , 2004 .

[27]  Gamal ElMasry,et al.  Principles of Hyperspectral Imaging Technology , 2010 .

[28]  A. Cavinato,et al.  Detection of sodium chloride in cured salmon roe by SW-NIR spectroscopy. , 2001, Journal of agricultural and food chemistry.

[29]  Manish H. Bharati,et al.  Using near-infrared multivariate image regression to predict pulp properties , 2004 .

[30]  D. Bravo,et al.  Effect of high pressure treatments on smoked cod quality during refrigerated storage , 2012 .

[31]  Manuela O’Connell,et al.  A practical approach for fish freshness determinations using a portable electronic nose , 2001 .

[32]  Isabel Escriche,et al.  Influence of storage conditions on some physical and chemical properties of smoked salmon (Salmo salar) processed by vacuum impregnation techniques , 2003 .

[33]  Paul Scheunders,et al.  A multivalued image wavelet representation based on multiscale fundamental forms , 2002, IEEE Trans. Image Process..

[34]  Antanas Verikas,et al.  Colour image segmentation by modular neural network , 1997, Pattern Recognit. Lett..

[35]  Eric Dufour,et al.  Development of a rapid method based on front-face fluorescence spectroscopy for the monitoring of fish freshness , 2003 .

[36]  José M. Barat,et al.  Control of ham salting by using image segmentation , 2008 .

[37]  M. Barker,et al.  Partial least squares for discrimination , 2003 .

[38]  J. Barat,et al.  Study of sea bass (Dicentrarchus labrax L.) salting process: Kinetic and thermodynamic control , 2008 .

[39]  Michael S. Brown,et al.  Visual enhancement of old documents with hyperspectral imaging , 2011, Pattern Recognit..

[40]  Achim Kohler,et al.  Noncontact salt and fat distributional analysis in salted and smoked salmon fillets using X-ray computed tomography and NIR interactance imaging. , 2009, Journal of agricultural and food chemistry.

[41]  Da-Wen Sun,et al.  Prediction of beef eating qualities from colour, marbling and wavelet surface texture features using homogenous carcass treatment , 2009, Pattern Recognit..

[42]  M. Hubert,et al.  Robust methods for partial least squares regression , 2003 .

[43]  Giorgio Manganelli,et al.  A y B , 1986 .