IP Library Granted Patent US 10,890,531
Granted Patent B2
US 10,890,531 · App. 16/666,375 · Granted Jan 12, 2021

Apparatus and method for fluorescence grading of gemstones

Inventor: Hiroshi Takahashi (Fort Lee, NJ)
Assignee: Gemological Institute of America, Inc. (GIA)
G01N21/6456G01N21/87G01N33/381G01N2021/6471G01N2201/062G01N2201/068G01N2201/0634G01N2201/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,890,531
App. No.
16/666,375
Granted
Jan 12, 2021
Kind
B2
Abstract

Provided herein is an apparatus for assessing a fluorescence characteristic of a gemstone. The apparatus comprises an optically opaque platform for supporting a gemstone to be assessed, one or more light source to provide uniform UV and non-UV illumination, an image capturing component, and a telecentric lens positioned to provide fluorescent images of the illuminated gemstone to the image capturing component. Also provided are methods of fluorescence analysis based on images collected using such an apparatus.

Claims (56)

1. A method of assessing a fluorescence characteristic of a sample gemstone, the method comprising:

by a computer with a processor and memory,

receiving a digital pixelated first color image of the sample gemstone at a first image rotation angle and a first image view angle,

wherein the first color image is taken under a daylight approximating non-UV light source;

receiving a digital pixelated first fluorescence image of the sample gemstone at the first image rotation angle and the first image view angle,

wherein the first fluorescence image is taken under a UV light source;

receiving a digital pixelated second color image of the sample gemstone at a second image rotation angle and the first image view angle,

wherein the second color image is taken under a daylight approximating non-UV light source;

receiving a digital pixelated second fluorescence image of the sample gemstone at the second image rotation angle and the first image view angle,

wherein the second fluorescence image is taken under a UV light source;

determining, by the computer, an outline mask from the first color image and the second color image,

wherein the outline mask excludes all background image outside of boundary lines of the sample gemstone in the images;

based on the outline mask, determining values of geometrical parameters;

determining an apparent fluorescence area of the sample gemstone, by the computer for the first fluorescence image and the second fluorescence image;

generating a fluorescence mask by overlaying, by the computer, the determined apparent fluorescence area on the outline mask;

determining, by the computer, if any part of the fluorescence area falls outside of the outline mask;

removing, by the computer, any part of the fluorescence area falls outside of the outline mask;

analyzing the remaining fluorescence area determined to be inside of the outline mask to assign a grade.

2. The method of claim 1 wherein the outline mask is determined using edge detection of the boundary lines of the sample gemstone.

3. The method of claim 2 wherein the edge detection is search-based by measuring an edge strength with a first-order derivative expression and searching for local directional maxima of gradient magnitude.

4. The method of claim 2 wherein the edge detection is zero-crossing based by searching for zero crossings in a second-order derivative expression computed from the first color image to find edges.

5. The method of claim 1 wherein the geometrical parameters include height and width.

6. The method of claim 1 wherein the analysis of the image inside the outline mask is an analysis of the pixels for quantitative analysis.

7. The method of claim 6 further comprising applying, by the computer, an algorithm to each pixel in the fluorescence image inside the outline mask to determine a color value for each corresponding pixel.

8. The method of claim 7 further comprising, converting the image pixels from CMYK to RGB values and using the RGB values to determine a color value for each corresponding pixel.

9. The method of claim 6 further comprising, determining, by the computer, converting the color values to parameters representing a color characteristic of each pixel.

10. The method of claim 9 further comprising, by the computer, calculating an average value for each parameter for all pixels inside the outline mask.

11. The method of claim 10 further comprising, by the computer, calculating a fluorescence score of the sample gemstone based on the average values of the parameters.

12. A non-transitory computer readable media with instructions for a method of assessing a fluorescence characteristic of a sample gemstone, the method comprising:

by a computer with a processor and memory,

receiving a digital pixelated first color image of the sample gemstone at a first image rotation angle and a first image view angle,

wherein the first color image is taken under a daylight approximating non-UV light source;

receiving a digital pixelated first fluorescence image of the sample gemstone at the first image rotation angle and the first image view angle,

wherein the first fluorescence image is taken under a UV light source;

receiving a digital pixelated second color image of the sample gemstone at a second image rotation angle and the first image view angle,

wherein the second color image is taken under a daylight approximating non-UV light source;

receiving a digital pixelated second fluorescence image of the sample gemstone at the second image rotation angle and the first image view angle,

wherein the second fluorescence image is taken under a UV light source;

determining, by the computer, an outline mask from the first color image and the second color image,

wherein the outline mask excludes all background image outside of boundary lines of the sample gemstone in the images;

based on the outline mask, determining values of geometrical parameters;

determining an apparent fluorescence area of the sample gemstone, by the computer for the first fluorescence image and the second fluorescence image;

generating a fluorescence mask by overlaying, by the computer, the determined apparent fluorescence area on the outline mask;

determining, by the computer, if any part of the fluorescence area falls outside of the outline mask;

removing, by the computer, any part of the fluorescence area falls outside of the outline mask;

analyzing the remaining fluorescence area determined to be inside of the outline mask to assign a grade.

13. The non-transitory computer readable media of claim 12 wherein the outline mask is determined using edge detection of the boundary lines of the sample gemstone.

14. The non-transitory computer readable media of claim 13 wherein the edge detection is search-based by measuring an edge strength with a first-order derivative expression and searching for local directional maxima of gradient magnitude.

15. The non-transitory computer readable media of claim 13 wherein the edge detection is zero-crossing based by searching for zero crossings in a second-order derivative expression computed from the first color image to find edges.

16. The non-transitory computer readable media of claim 12 wherein the geometrical parameters include height and width.

17. The non-transitory computer readable media of claim 12 wherein the analysis of the image inside the outline mask is an analysis of the pixels for quantitative analysis.

18. The non-transitory computer readable media of claim 17 further comprising applying, by the computer, an algorithm to each pixel in the fluorescence image inside the outline mask to determine a color value for each corresponding pixel.

19. The non-transitory computer readable media of claim 18 further comprising, converting the image pixels from CMYK to RGB values and using the RGB values to determine a color value for each corresponding pixel.

20. The non-transitory computer readable media of claim 17 further comprising, determining, by the computer, converting the color values to parameters representing a color characteristic of each pixel;

calculating an average value for each parameter for all pixels inside the outline mask; and

calculating a fluorescence score of the sample gemstone based on the average values of the parameters.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 27, 2020
From: TAKAHASHI, HIROSHI
To: GEMOLOGICAL INSTITUTE OF AMERICA INC. (GIA)
Reel/Frame 052250/0583 →
Continuity (3)
Continuation 16133454 · Sep 17, 2018
Continuation 14673780 · Mar 30, 2015
Related Publication 20200064267A1 · Feb 27, 2020
Cited By (1)
US 12,372,467