Abstract
The aim of this study was to investigate the capacity of Artificial Neural Networks (ANNs) to model and classify UV reflectance spectra of 28 different pearls in order to assess their quality. Spectral data (inputs) were smoothed to reduce the noise and fed into ANNs and correlated to the pearls' quality/grading criteria (outputs). The developed ANNs were successful in predicting mollusk pearl growing species, pearl and donor color, luster, possible luster and color enhancing treatments, and surface complexity. The results of this study indicate that the developed UV-spectroscopy-ANN method may be used as a more objective method of assessing pearl quality (grading) and may become a valuable tool for the pearl grading industry.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
