An innovative multivariate strategy for HSI-NIR images to automatically detect defects in green coffee.

In the present study, an advanced and original multivariate strategy for the processing of hyperspectral images in the near-infrared region is proposed to automatically detect physico-chemical defects in green coffee, which are similar one to each other by naked eye. An object-based approach for the characterization of individual beans, rather than single pixels, was adopted, calculating a series of descriptive parameters characterizing the distribution of scores on the lowest-order principal components. On such parameters, the k-nearest neighbors (k-NN) classification algorithm was applied and the predictive results on the test samples indicate that this approach is able not only to distinguish defective beans from non-defective ones, but also to differentiate the various types of defects. Hyperspectral imaging is demonstrated to be a valid alternative for the sorting of green beans - a crucial phase for coffee import/export.

[1]  Sergey V. Kucheryavskiy,et al.  A new approach for discrimination of objects on hyperspectral images , 2013 .

[2]  Giovanni Mettivier,et al.  Digital Imaging Processing , 2010 .

[3]  E. J. N. Marques,et al.  Vitamin C distribution in acerola fruit by near infrared hyperspectral imaging , 2016 .

[4]  Paul J. Williams,et al.  Classification of maize kernels using NIR hyperspectral imaging. , 2016, Food chemistry.

[5]  Kim H. Esbensen,et al.  Monitoring of pellet coating process with image analysis—a feasibility study , 2010 .

[6]  C. Pizarro,et al.  Coffee varietal differentiation based on near infrared spectroscopy. , 2007, Talanta.

[7]  Ana Paula Craig,et al.  Evaluation of the potential of FTIR and chemometrics for separation between defective and non-defective coffees. , 2012, Food chemistry.

[8]  C. Yeretzian,et al.  Quantitative assessment of specific defects in roasted ground coffee via infrared-photoacoustic spectroscopy. , 2018, Food chemistry.

[9]  Giorgia Foca,et al.  Data dimensionality reduction and data fusion for fast characterization of green coffee samples using hyperspectral sensors , 2016, Analytical and Bioanalytical Chemistry.

[10]  J. Anderson,et al.  GlutoPeak profile analysis for wheat classification: Skipping the refinement process , 2018 .

[11]  João Rodrigo Santos,et al.  Evaluation of green coffee beans quality using near infrared spectroscopy: a quantitative approach. , 2012, Food chemistry.

[12]  I. Jolliffe.  Principal Component Analysis , 2002 .

[13]  R. Barnes,et al.  Standard Normal Variate Transformation and De-Trending of Near-Infrared Diffuse Reflectance Spectra , 1989 .

[14]  Roberto Beghi,et al.  Testing of a VIS-NIR System for the Monitoring of Long-Term Apple Storage , 2014, Food and Bioprocess Technology.

[15]  T. Leroy,et al.  Validation of near-infrared spectroscopy for the quantification of cafestol and kahweol in green coffee , 2014 .

[16]  Alessandro Ulrici,et al.  Transferring results from NIR-hyperspectral to NIR-multispectral imaging systems: A filter-based simulation applied to the classification of Arabica and Robusta green coffee. , 2017, Analytica chimica acta.

[17]  Simona Benedetti,et al.  E-nose, e-tongue and e-eye for edible olive oil characterization and shelf life assessment: A powerful data fusion approach. , 2018, Talanta.

[18]  Paul Geladi,et al.  The Importance of Balanced Data Sets for Partial Least Squares Discriminant Analysis: Classification Problems Using Hyperspectral Imaging Data , 2011 .

[19]  Riccardo Leardi,et al.  Detection of addition of barley to coffee using near infrared spectroscopy and chemometric techniques. , 2012, Talanta.

[20]  Theodora Kourti,et al.  Process analysis, monitoring and diagnosis, using multivariate projection methods , 1995 .

[21]  Melissa Maya Mesa.  Variabilidad en la respuesta espectral de especies forestales en un contexto urbano , 2020 .

[22]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[23]  Aoife A. Gowen,et al.  Tutorial: Time Series Hyperspectral Image Analysis , 2016 .

[24]  Paulo Mazzafera,et al.  Chemical composition of defective coffee beans , 1999 .

[25]  Thibaud Taillefumier.  Principal Component , 2020, Definitions.

[26]  Alessandro Ulrici,et al.  Practical comparison of sparse methods for classification of Arabica and Robusta coffee species using near infrared hyperspectral imaging , 2015 .

[27]  Ivanira Moreira,et al.  Chemometric discrimination of genetically modified Coffea arabica cultivars using spectroscopic and chromatographic fingerprints. , 2013, Talanta.