Granted Patent B1

US 12,190,516 · App. 18/431,772 · Granted Jan 7, 2025

Inventors: Tien Dung Nguyen (Toulouse, FR); Thi Thu Hang Nguyen (Toulouse, FR); Pierre Gillibert (Toulouse, FR); Clément Lemeunier (Toulouse, FR); Jérôme Michel Auguste Bertrand (Toulouse, FR)

Assignee: BelleTorus Corporation

G06T7/0012A61B5/441G06T7/12G06T17/20G16H50/20G06T2207/20084G06T2207/30088

Abstract

Claims (39)

1. A method of operation of a compute system comprising:

generating a digital model from an input image;

segmenting a 3D-polygon from the input image by applying a triangular mesh;

assembling a 3D surface of a zone of interest from the 3D-polygon based on the digital model;

generating a restricted heat map by applying the zone of interest to a heat map of the digital model to zero pixel values outside the zone of interest;

calculating an average threshold value of pixels within the zone of interest and the restricted heat map for identifying a condition over the 3D surface; and

assembling a skin condition display from analyzing by a skin artificial intelligence (AI) of the 3D surface for displaying on a device.

2. The method as claimed in claim 1 wherein generating the digital model includes segmenting the input image for analysis by a previously trained convolutional neural network.

3. The method as claimed in claim 1 wherein segmenting the 3D-polygons from the input image includes averaging the pixels of the 3D-polygons segmented by applying the triangular mesh.

4. The method as claimed in claim 1 wherein assembling the skin condition display includes assembling an acne score, an area of an acne, an estimated count, a 3D image sequence, and an identifying marker of the condition for display on the device.

5. The method as claimed in claim 1 wherein identifying the condition over the 3D surface includes identifying an acne type of an acne pimple from among a white head, a black head, a pustule, a cyst, a nodule, a papule, a comedone, and a discoloration.

6. The method as claimed in claim 1 wherein assembling the 3D surface includes compiling the zone of interest by matching the pixels of the 3D-polygons in a left side image, a central image, a right side image, or a combination thereof, and the digital model.

7. The method as claimed in claim 1 wherein calculating the average threshold value of the pixels for identifying the condition further comprising integrating the average threshold value from each of the 3D-polygon for a 3D image sequence of a first hemisphere image and a second hemisphere image.

8. A compute system comprising:

a control circuit, including a processor, configured to:

generate a digital model from an input image;

segment 3D-polygons from the input image by a triangular mesh;

assemble a 3D surface of interest from the 3D-polygons to match the digital model;

generate a restricted heat map by applying the zone of interest to a heat map of the digital model to zero pixel values outside the zone of interest; and

calculate an average threshold value of pixels within the zone of interest and the restricted heat map to identify a condition over the 3D surface; and

a communication circuit, coupled to the control circuit, configured to transfer a skin condition display from a skin artificial intelligence (AI) analysis of the 3D surface for displaying on a device.

9. The system as claimed in claim 8 wherein the control circuit is further configured to generate the digital model includes segmenting the input image by a previously trained convolutional neural network.

10. The system as claimed in claim 8 wherein the control circuit is further configured to segment the 3D-polygons from the input image by averaging the pixels of the 3D-polygons segmented by applying the triangular mesh.

11. The system as claimed in claim 8 wherein the control circuit is further configured to assemble the skin condition display to include an acne score, an area of an acne, an estimated count, a 3D image sequence, and an identifying marker of the condition assembled for display on the device.

12. The system as claimed in claim 8 wherein the control circuit is further configured to identify the condition over the 3D surface includes identifying an acne type of an acne pimple from among a white head, a black head, a pustule, a cyst, a nodule, a papule, a comedone, and a discoloration.

13. The system as claimed in claim 8 wherein the control circuit is further configured to assemble the 3D surface, including compiling a zone of interest by matching the pixels of the 3D-polygons in a left side image, a central image, a right side image, or a combination thereof, and the digital model.

14. The system as claimed in claim 8 wherein the control circuit is further configured to calculate the average threshold value of the pixels for identifying the condition further comprising integrating the average threshold value from the 3D-polygon for a 3D image sequence of a first hemisphere image and a second hemisphere image.

15. A non-transitory computer readable medium including instructions executable by a control circuit for a compute system for performing functions comprising:

generating a digital model from an input image;

segmenting 3D-polygons from the input image by applying a triangular mesh;

assembling a 3D surface of a zone of interest from the 3D-polygon matching the digital model;

generating a restricted heat map by applying the zone of interest to a heat map of the digital model to zero pixel values outside the zone of interest;

calculating an average threshold value of pixels within the zone of interest and the restricted heat map for identifying a condition over the 3D surface; and

assembling a skin condition display from analyzing by a skin artificial intelligence (AI) of the 3D surface for displaying on a device.

16. The non-transitory computer readable medium as claimed in claim 15 wherein generating the digital model includes segmenting the input image for analysis by a previously trained convolutional neural network.

17. The non-transitory computer readable medium as claimed in claim 15 wherein segmenting the 3D-polygons from the input image includes averaging the pixels of the 3D-polygons segmented by applying the triangular mesh.

18. The non-transitory computer readable medium as claimed in claim 15 further comprising assembling the skin condition display includes assembling an acne score, an area of an acne, an estimated count, a 3D image sequence, and an identifying marker of the condition for display on the device.

19. The non-transitory computer readable medium as claimed in claim 15 wherein identifying the condition over the 3D surface includes identifying an acne type of an acne pimple from among a white head, a black head, a pustule, a cyst, a nodule, a papule, a comedone, and a discoloration.

20. The non-transitory computer readable medium as claimed in claim 15 assembling the 3D surface includes compiling a zone of interest by matching the pixels of the 3D-polygons in a left side image, a central image, a right side image, or a combination thereof, and the digital model.

Assignments (1)

References Cited (13)