Automated Internal Classification of Beadless Chinese ZhuJi Freshwater Pearls based on Optical Coherence Tomography Images

Using optical coherence tomography to assess luster of pearls: technique suitability and insights

Luster is one of the vital indexes in pearl grading. To find a fast, nondestructive, and low-cost grading method, optical coherence tomography (OCT) is introduced to predict the luster grade through the texture features. After background removal, flattening, and segmentation, the speckle pattern of the region of interest is described by seven kinds of feature textures, including center-symmetric auto-correlation (CSAC), fractal dimension (FD), Gabor, gray level co-occurrence matrix (GLCM), histogram of oriented gradients (HOG), laws texture energy (LAWS), and local binary patterns (LBP). To find the relations between speckle-derived texture features and luster grades, four Four groups of pearl samples were used in the experiment to detect texture differences based on support vector machines (SVMs) and random forest classifier (RFC)) for investigating the relations between speckle-derived texture features and luster grades. The precision, recall, F1-score, and accuracy are more significant than 0.9 in several simulations, even after dimension reduction. This demonstrates that the texture feature from OCT images can be applied to class the pearl luster based on speckle changes.

Rapid detection of color-treated pearls and separation of pearl types using fluorescence analysis

Pearl identification plays a key role to maintain transparency in the gem industry by disclosing potential color treatments and classifying pearl species. Current techniques for pearl identification have been limited by expensive instrumentations and long measurement time, severely restricting their use outside of major gemological laboratories. There is a strong demand for simple and inexpensive identification instruments designed for non-specialized users and small-scale gemological laboratories. For this purpose, we demonstrate a portable fluorescence spectroscopy for pearl treatment detection and species classification based on pearl's nacre fluorescence detection. This device can be used to rapidly separate naturally colored pearls from treated colored pearls, detect potential treatments applied to white colored pearls, and separate pearls between certain species in seconds, based on their differences in nacre fluorescence intensity. The system enables noninvasive testing of loose pearls, pearl strands, and mounted pearl jewelry under normal office lighting conditions. The experimental prototype demonstrates high accuracy for automatic pearl color treatment screening, referring 100% of the treated colored pearls. Furthermore, similar protocols can be applied to evaluate popular pearl enhancements such as bleaching and to extend its application to separate akoya pearls and their South Sea counterparts.