Differentiation of deciduous-calyx and persistent-calyx pears using hyperspectral reflectance imaging and multivariate analysis

Abstract Deciduous-calyx pears of Korla fragrant pear ( Pyrus sinkiangensis Yu ) have a significant economic value in Xinjiang Uygur Autonomous Region, China. This study developed a non-destructive method based on hyperspectral imaging using a combination of existing analytical techniques to differentiate the deciduous-calyx pear (DCF) and persistent-calyx pear (PCF). The degrees of circularity of DCP and PCP were extracted according to its morphological characteristic; similarly, the reflectance spectra of DCP and PCP were obtained by hyperspectral imaging technology. Successive projections algorithm (SPA) combined with support vector machine (SVM) established a classification model. The DCF and PCF could be differentiated by SPA-SVM model with accuracy of 93.3% and 96.7% respectively. Our findings suggest that hyperspectral imaging can be applied to non-destructively differentiate pears, and meet the packaging standards.

[1]  M. C. U. Araújo,et al.  The successive projections algorithm for variable selection in spectroscopic multicomponent analysis , 2001 .

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

[3]  R. Cubeddu,et al.  Nondestructive quantification of chemical and physical properties of fruits by time-resolved reflectance spectroscopy in the wavelength range 650-1000 nm. , 2001, Applied optics.

[4]  Roman M. Balabin,et al.  Near-infrared (NIR) spectroscopy for motor oil classification: From discriminant analysis to support vector machines , 2011 .

[5]  Renfu Lu,et al.  Hyperspectral laser-induced fluorescence imaging for assessing apple fruit quality , 2007 .

[6]  R. Lu.  Multispectral imaging for predicting firmness and soluble solids content of apple fruit , 2004 .

[7]  J. Qin,et al.  Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence , 2009 .

[8]  Renfu Lu,et al.  Prediction of firmness and soluble solids content of blueberries using hyperspectral reflectance imaging , 2013 .

[9]  Benxue Ma,et al.  Fragrant pear sexuality recognition with machine vision , 2006, SPIE Optics East.

[10]  Maria Fernanda Pimentel,et al.  Aspects of the successive projections algorithm for variable selection in multivariate calibration applied to plasma emission spectrometry , 2001 .

[11]  Yankun Peng,et al.  Prediction of apple fruit firmness and soluble solids content using characteristics of multispectral scattering images , 2007 .

[12]  Chul E. Kim,et al.  Digital Disks , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  K. Tu,et al.  Detection of cold injury in peaches by hyperspectral reflectance imaging and artificial neural network. , 2016, Food chemistry.

[14]  P Jancsók,et al.  Stem-end/Calyx Identification on Apples using Contour Analysis in Multispectral Images , 2007 .

[15]  Rasmus Bro,et al.  Variable selection in regression—a tutorial , 2010 .

[16]  A. Gitelson,et al.  Reflectance spectral features and non-destructive estimation of chlorophyll, carotenoid and anthocyanin content in apple fruit , 2003 .

[17]  Roberto Kawakami Harrop Galvão,et al.  The successive projections algorithm for spectral variable selection in classification problems , 2005 .

[18]  M. S. Kim,et al.  Online screening of fruits and vegetables using hyperspectral line-scan imaging techniques , 2015 .

[19]  R. Lu,et al.  Hyperspectral Scattering for assessing Peach Fruit Firmness , 2006 .

[20]  Baohua Zhang,et al.  A comparative study for the quantitative determination of soluble solids content, pH and firmness of pears by Vis/NIR spectroscopy , 2013 .

[21]  Alan M. Lefcourt,et al.  A novel integrated PCA and FLD method on hyperspectral image feature extraction for cucumber chilling damage inspection , 2004 .

[22]  Hongbin Pu,et al.  Non-destructive prediction of salt contents and water activity of porcine meat slices by hyperspectral imaging in a salting process , 2013 .

[23]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[24]  Moon S. Kim,et al.  Development of hyperspectral imaging technique for the detection of apple surface defects and contaminations , 2004 .

[25]  Daniel E. Guyer,et al.  Near-infrared hyperspectral reflectance imaging for detection of bruises on pickling cucumbers , 2006, Computers and Electronics in Agriculture.

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

[27]  P. Baranowski,et al.  Detection of early bruises in apples using hyperspectral data and thermal imaging , 2012 .

[28]  Roberto Kawakami Harrop Galvão,et al.  A variable elimination method to improve the parsimony of MLR models using the successive projections algorithm , 2008 .