The Use of Probabilistic Neural Network and UV Reflectance Spectroscopy as an Objective Cultured Pearl Quality Grading Method

Pearl quality and value are determined as a combination of different features, with mollusk species, nacre thickness, luster, surface, shape, color and pearl size, being the most important. A pearl grader has to quantify visual observations and to assign a grading level to a pearl. The aim of this work was to reduce subjectivity in the assessment of some aspects of pearl quality by using artificial neural networks to predict pearl quality parameters from UV reflectance spectra. Given the good predictability of our previous model that used multilayer perceptron ANN modeling of UVVisible spectra to predict the grade of pearls, we wanted to simplify and improve the model by reducing the spectral input to UV only and by using classifier neural network modelling. It is hypothesized that as UV light is of higher energy than visible light, it may penetrate further into the surface of the pearl, and hence the corresponding UV diffuse reflectance spectrum may provide more information that can be used to assess pearl quality. The developed models were successful in predicting mollusk pearl growing species, pearl and donor color, luster, and surface complexity. The simplified models have been built resulting in more accurate prediction of selected pearl quality parameters when compared with the previous reported model.

[1]  S. Elen.  Spectral Reflectance and Fluorescence Characteristics of Natural-Color and Heat-Treated "Golden" South Sea Cultured Pearls , 2001 .

[2]  M. Bos,et al.  Comparison of the training of neural networks for quantitative x-ray fluorescence spectrometry by a genetic algorithm and backward error propagation , 1991 .

[3]  C. Raman,et al.  On the chromatic diffusion halo and other optical effects exhibited by pearls , 1954 .

[4]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[5]  T. G. Truscott,et al.  The carotenoids as anti-oxidants--a review. , 1997, Journal of photochemistry and photobiology. B, Biology.

[6]  Rodolfo Zunino,et al.  Implementing probabilistic Neural Networks , 1997, Neural Computing & Applications.

[7]  Andreas Scholl,et al.  Gradual ordering in red abalone nacre. , 2008, Journal of the American Chemical Society.

[8]  S. Berets,et al.  Accessories and Sample Handling for Mid-Infrared Diffuse Reflection Spectroscopy , 2006 .

[9]  Michael F. Ashby,et al.  The mechanical efficiency of natural materials , 2004 .

[10]  H. Edwards,et al.  Carotenes and carotenoids in natural biological samples: a Raman spectroscopic analysis , 2009 .

[11]  J. Chalmers,et al.  Handbook of vibrational spectroscopy , 2002 .

[12]  I. Aksay,et al.  Biomimetics. Design and Processing of Materials. , 1995 .

[13]  Solid State Assay of Ranitidine HCl as a Bulk Drug and as Active Ingredient In Tablets Using DRIFT Spectroscopy with Artificial Neural Networks , 1999, Pharmaceutical Research.

[14]  David S. Touretzky,et al.  Optical Chinese character recognition using probabilistic neural networks , 1997, Pattern Recognit..

[15]  P. Southgate,et al.  A new approach to pearl oyster broodstock selection: can saibo donors be used as future broodstock? , 2004 .

[16]  Reza Shadmehr,et al.  Principal Component Analysis of Optical Emission Spectroscopy and Mass Spectrometry: Application to Reactive Ion Etch Process Parameter Estimation Using Neural Networks , 1992 .

[17]  Germà Garcia-Belmonte,et al.  A new approach to automatic radiation spectrum analysis , 1991 .

[18]  S. Amendolia,et al.  Classification and quantitation of 1H NMR spectra of alditols binary mixtures using artificial neural networks. , 1998, Analytical chemistry.

[19]  S. Agatonovic-Kustrin,et al.  The Use of UV-Visible Reflectance Spectroscopy as an Objective Tool to Evaluate Pearl Quality , 2012, Marine drugs.

[20]  Huang Yi-lan.  Colouration Attributes and UV-NIS Reflection Spectra of Various Golden Seawater Cultured Pearls , 2008 .

[21]  P. Southgate,et al.  Assessing Pearl Quality Using Reflectance UV-Vis Spectroscopy: Does the Same Donor Produce Consistent Pearl Quality? , 2010, Marine drugs.