Internal damage inspection of almond nuts using optimal near-infrared waveband selection technique

Abstract This work presents a statistical method for internal damage inspection of almond nuts based on advanced waveband selection and supervised pattern recognition techniques using near-infrared spectral data. Our proposed method employs an optimal adaptive branch and bound algorithm to select a small set of wavebands for use in a support vector machine classifier. Our case study involves discriminating almond nuts with internal damage from normal ones. Experimental results demonstrate that our method gives significantly higher classification rates than prior algorithms. Our classification model is promising for commercial online processing, since only a few wavebands are used for classification and can thus be recorded by many fast sensor systems.

[1]  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 .

[2]  Songyot Nakariyakul,et al.  Classification of internally damaged almond nuts using hyperspectral imagery , 2011 .

[3]  Ronei J. Poppi,et al.  Fourier transform near-infrared spectroscopy (FT-NIRS) application to estimate Brazilian soybean [Glycine max (L.) Merril] composition , 2013 .

[4]  P. Williams,et al.  Prediction of pork quality with near infrared spectroscopy (NIRS) 2. Feasibility and robustness of NIRS measurements under production plant conditions. , 2012, Meat science.

[5]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[6]  David Casasent,et al.  Hyperspectral waveband selection for contaminant detection on poultry carcasses , 2008 .

[7]  Josef Kittler,et al.  Fast branch & bound algorithms for optimal feature selection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  N. Keshava,et al.  Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[10]  David Casasent,et al.  Waveband selection for hyperspectral data: optimal feature selection , 2003, SPIE Defense + Commercial Sensing.

[11]  K. Walsh,et al.  Short-Wavelength Near-Infrared Spectra of Sucrose, Glucose, and Fructose with Respect to Sugar Concentration and Temperature , 2003, Applied spectroscopy.

[12]  Kurt C. Lawrence,et al.  ALGORITHM DEVELOPMENT WITH VISIBLE/NEAR-INFRARED SPECTRA FOR DETECTION OF POULTRY FECES AND INGESTA , 2003 .

[13]  Tom C. Pearson,et al.  Spectral Properties and Effect of Drying Temperature on Almonds with Concealed Damage , 1999 .

[14]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Feature Subset Selection , 1977, IEEE Transactions on Computers.

[15]  Fang Cheng,et al.  On-line prediction of pH values in fresh pork using visible/near-infrared spectroscopy with wavelet de-noising and variable selection methods , 2012 .

[16]  David Casasent,et al.  Fusion algorithm for poultry skin tumor detection using hyperspectral data. , 2007, Applied optics.

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

[18]  Shyam Narayan Jha,et al.  Nondestructive prediction of maturity of mango using near infrared spectroscopy , 2014 .

[19]  Huirong Xu,et al.  Near infrared spectroscopy for on/in-line monitoring of quality in foods and beverages: A review , 2008 .

[20]  Seyed Ahmad Mireei,et al.  Detecting bunch withering disorder in date fruit by near infrared spectroscopy , 2013 .

[21]  Filiberto Pla,et al.  SmartSpectra: Applying multispectral imaging to industrial environments , 2005, Real Time Imaging.

[22]  Ricard Boqué,et al.  Rapid characterization of transgenic and non-transgenic soybean oils by chemometric methods using NIR spectroscopy. , 2013, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[23]  Karsten Heia,et al.  VIS/NIR spectroscopy for non-destructive freshness assessment of Atlantic salmon (Salmo salar L.) fillets , 2013 .

[24]  David Casasent,et al.  Adaptive branch and bound algorithm for selecting optimal features , 2007, Pattern Recognit. Lett..

[25]  Xue-wen Chen,et al.  Combating the Small Sample Class Imbalance Problem Using Feature Selection , 2010, IEEE Transactions on Knowledge and Data Engineering.