Rapid discrimination of main red meat species based on near-infrared hyperspectral imaging technology

Meat is the necessary source of essential nutrients for people including protein, fat, and so on. The discrimination of meat species and the determination of meat authenticity have been an important issue in the meat industry. The objective of this study is to realize the fast and accurate identification of three main red meats containing beef, lamb and pork by using near-infrared hyperspectral imaging (HSI) technology. After acquiring the hyperspectral images of meat samples, the calibration of acquired images and selection of the region of interest (ROI) were carried out. Then spectral preprocessing method of standard normal variate correction (SNV) was used to reduce the light scattering and random noise before the spectral analysis. Finally, characteristic wavelengths were extracted by principal component analysis (PCA), and the Fisher linear discriminant method was applied to establish Fisher discriminant functions to identify the meat species. All the samples were collected from different batches in order to improve the coverage of the models. In addition to the validation of sample itself in train set and cross validation, three different meat samples were sliced at the size of 2cm×2cm×2 cm approximately and were spliced together in one interface to be scanned by HSI system. The acquired hyperspectral data was applied to further validate the discriminant model. The results demonstrated that the near-infrared hyperspectral imaging technology could be applied as an effective, rapid and non-destructive discrimination method for main red meats.

[1]  Kurt C. Lawrence,et al.  Reflectance calibration of focal plane array hyperspectral imaging system for agricultural and food safety applications , 2003, SPIE Remote Sensing.

[2]  Gamal ElMasry,et al.  Chemical-free assessment and mapping of major constituents in beef using hyperspectral imaging , 2013 .

[3]  Nuria Aleixos,et al.  Selection of Optimal Wavelength Features for Decay Detection in Citrus Fruit Using the ROC Curve and Neural Networks , 2013, Food and Bioprocess Technology.

[4]  Gamal ElMasry,et al.  Application of NIR hyperspectral imaging for discrimination of lamb muscles , 2011 .

[5]  Ashok Samal,et al.  Visible/near-infrared hyperspectral imaging for beef tenderness prediction , 2008 .

[6]  A. S. Mohamed,et al.  Rapid identification of pork for halal authentication using the electronic nose and gas chromatography mass spectrometer with headspace analyzer. , 2011, Meat science.

[7]  Da-Wen Sun,et al.  Recent developments of hyperspectral imaging systems and their applications in detecting quality attributes of red meats: A review , 2014 .

[8]  Moon S. Kim,et al.  Analysis of hyperspectral fluorescence images for poultry skin tumor inspection. , 2004, Applied optics.

[9]  Gamal ElMasry,et al.  Non-destructive determination of water-holding capacity in fresh beef by using NIR hyperspectral imaging , 2011 .

[10]  Gamal ElMasry,et al.  Quality classification of cooked, sliced turkey hams using NIR hyperspectral imaging system , 2011 .

[11]  Shaoqing Cui,et al.  Analysis of pork adulteration in minced mutton using electronic nose of metal oxide sensors , 2013 .

[12]  Silvia Serranti,et al.  Classification of polyolefins from building and construction waste using NIR hyperspectral imaging system , 2012 .

[13]  Gamal ElMasry,et al.  Predicting quality and sensory attributes of pork using near-infrared hyperspectral imaging. , 2012, Analytica chimica acta.

[14]  N. Z. Ballin Authentication of meat and meat products. , 2010, Meat science.

[15]  Thomas W Vickroy,et al.  Fast differentiation of meats from fifteen animal species by liquid chromatography with electrochemical detection using copper nanoparticle plated electrodes. , 2007, Journal of chromatography. B, Analytical technologies in the biomedical and life sciences.

[16]  Dejan Škorjanc,et al.  Predicting pork water-holding capacity with NIR spectroscopy in relation to different reference methods , 2010 .

[17]  D L Massart,et al.  The effect of preprocessing methods in reducing interfering variability from near-infrared measurements of creams. , 2004, Journal of pharmaceutical and biomedical analysis.

[18]  Gamal ElMasry,et al.  Fast detection and visualization of minced lamb meat adulteration using NIR hyperspectral imaging and multivariate image analysis. , 2013, Talanta.

[19]  A. Moussavi,et al.  Fraud identification in industrial meat products by multiplex PCR assay. , 2009 .

[20]  Daniel Cozzolino,et al.  Identification of animal meat muscles by visible and near infrared reflectance spectroscopy , 2004 .

[21]  María Jesús Lerma-García,et al.  Classification of extra virgin olive oils according to their genetic variety using linear discriminant analysis of sterol profiles established by ultra-performance liquid chromatography with mass spectrometry detection , 2011 .

[22]  Da-Wen Sun,et al.  NIR hyperspectral imaging as non-destructive evaluation tool for the recognition of fresh and frozen–thawed porcine longissimus dorsi muscles , 2013 .

[23]  Gamal ElMasry,et al.  Non-destructive prediction and visualization of chemical composition in lamb meat using NIR hyperspectral imaging and multivariate regression , 2012 .

[24]  M. S. Brewer,et al.  Reducing the fat content in ground beef without sacrificing quality: a review. , 2012, Meat science.

[25]  Paul J. Williams,et al.  Near-infrared (NIR) hyperspectral imaging and multivariate image analysis to study growth characteristics and differences between species and strains of members of the genus Fusarium , 2012, Analytical and Bioanalytical Chemistry.

[26]  Yankun Peng,et al.  Prediction of beef quality attributes using VIS/NIR hyperspectral scattering imaging technique , 2012 .

[27]  Teresa García,et al.  TaqMan real-time PCR for the detection and quantitation of pork in meat mixtures. , 2005, Meat science.