Simulating progression of skin conditions based on machine learning
AssigneeInternational Business Machines Corporation
InventorsYuan Yuan DING, Yi Chen ZHONG, Jing ZHANG, Yang LIU, Ziyi JIANG, Ting Ting CAO
Life of this patent
Estimating the term…
Abstract
Techniques for skin-condition visualization using machine learning. A color image depicting facial skin of a subject is retrieved. A monochromatic version of the color image is generated. Candidate instances of one or more skin conditions are segmented from the monochromatic version based on a segmentation threshold and using a machine learning model. A polarized version of the color image is generated, and based on the polarized version, the candidate instances are filtered. One or more simulation images are generated based on the filtered candidate instances.
Claims20
A computer-implemented method of skin-condition visualization, the computer-implemented method comprising:
- retrieving a color image depicting facial skin of a subject;
- generating a monochromatic version of the color image;
- segmenting, based on a segmentation threshold and using a machine learning model, a plurality of candidate instances of one or more skin conditions from the monochromatic version;
- generating a polarized version of the color image, wherein based on the polarized version, the plurality of candidate instances is filtered to exclude at least one candidate instance such that one or more candidate instances remain as one or more finalized instances;
- and
- generating, based on the one or more finalized instances and by operation of one or more computer processors, one or more simulation images that simulate an improving or worsening of the one or more finalized instances over time relative to the color image.
A computer program product of skin-condition visualization, the computer program product comprising:
- a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation comprising:
- retrieving a color image depicting facial skin of a subject;
- generating a monochromatic version of the color image;
- segmenting, based on a segmentation threshold and using a machine learning model, a plurality of candidate instances of one or more skin conditions from the monochromatic version;
- generating a polarized version of the color image, wherein based on the polarized version, the plurality of candidate instances is filtered to exclude at least one candidate instance such that one or more candidate instances remain as one or more finalized instances;
- and
- generating, based on the one or more finalized instances, one or more simulation images that simulate an improving or worsening of the one or more finalized instances over time relative to the color image.
A system of skin-condition visualization, the system comprising:
- one or more computer processors;
- and
- a memory containing a program executable by the one or more computer processors to perform an operation comprising:
- retrieving a color image depicting facial skin of a subject;
- generating a monochromatic version of the color image;
- segmenting, based on a segmentation threshold and using a machine learning model, a plurality of candidate instances of one or more skin conditions from the monochromatic version;
- generating a polarized version of the color image, wherein based on the polarized version, the plurality of candidate instances is filtered to exclude at least one candidate instance such that one or more candidate instances remain as one or more finalized instances;
- and
- generating, based on the one or more finalized instances, one or more simulation images that simulate an improving or worsening of the one or more finalized instances over time relative to the color image.
Dependencies are inferred from the claim text.