Method and system for determining a characteristic of a keratinous surface and method and system for treating said keratinous surface
The present application is directed to a method and system for determining at least one physical and/or chemical characteristic of a keratinous surface of a user, the method comprising the steps of: —receiving data corresponding to at least one image of the keratinous surface, —processing the image by applying at least one machine learning model to said image, —returning at least one numerical value corresponding to a grade of the characteristic of the keratinous surface to be determined.
1. A computer-implemented method for determining hair tone of a keratinous surface of a user, the method comprising the steps of:
receiving data corresponding to at least one image of the keratinous surface encoded in a first color space, the at least one image picturing a scalp area of the user comprising hairs,
performing a pre-processing segmentation step configured to identify at least one hair segment,
processing the at least one image by transforming color values of the at least one identified hair segment from the first color space into a CIELAB color space including L* values by applying a first machine learning model to said at least one image,
applying a second machine learning model trained accordingly to evaluate the hair tone of the keratinous surface from median L* values of pixels of the at least one identified hair segment, and
returning at least one numerical value corresponding to a grade of the hair tone of the keratinous surface to be determined.
2. The computer-implemented method according to claim 1 , wherein the segmentation step is performed by contrast analysis.
3. The computer-implemented method according to claim 1 , wherein the segmentation step is performed by applying a classification model to the image.
4. The computer-implemented method according to claim 1 , wherein the at least one image is an RGB image.
5. The computer-implemented method according to claim 1 , wherein the method is repeated in order to determine a second characteristic of the keratinous surface.
6. The computer-implemented method according to claim 1 , wherein the method comprises a subsequent step of recommending a cosmetic product based on the at least one numerical value.
7. The computer-implemented method according to claim 1 , wherein the method comprises a subsequent step of determining a recommended cosmetic product composition based on the at least one numerical value.
8. The computer-implemented method according to claim 7 , wherein the method comprises the subsequent step of making and dispensing a cosmetic product according to the recommended composition.
9. The computer-implemented method according to claim 1 , wherein the area pictured in the at least one image is a hair-root region of the user.
10. The computer-implemented method according to claim 1 , wherein the pre-processing segmentation step is based on adaptive thresholding by applying a Gaussian filter to reduce the noise in the image and then ranking hair regions by size using connected components analysis.
11. A non-transitory computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform a method comprising:
receiving data corresponding to at least one image of a keratinous surface of a user, the at least one image encoded in a first color space, the at least one image picturing a scalp area of the user comprising hairs,
performing a pre-processing segmentation step configured to identify at least one hair segment,
processing the at least one image by transforming color values of the at least one identified hair segment from the first color space into a CIELAB color space including L* values by applying a first machine learning model to the at least one image,
applying a second machine learning model trained accordingly to evaluate hair tone of the keratinous surface from median L* values of pixels of the at least one identified hair segment, and
returning at least one numerical value corresponding to a grade of the hair tone of the keratinous surface to be determined.
12. A system for determining hair tone of a keratinous surface of a user, said system comprising an image sensor configured for acquiring an image of the keratinous surface and to transmit the image data to a processor, said processor being configured to process the image data by performing steps comprising:
receiving data corresponding to at least one image of the keratinous surface encoded in a first color space, the at least one image picturing a scalp area of the user comprising hairs,
performing a pre-processing segmentation step configured to identify at least one hair segment,
processing the at least one image by transforming color values of the at least one identified hair segment from the first color space into a CIELAB color space including L* values by applying a first machine learning model to said at least one image,
applying a second machine learning model trained accordingly to evaluate the hair tone of the keratinous surface from median L* values of pixels of the at least one identified hair segment, and
returning at least one numerical value corresponding to a grade of the hair tone of the keratinous surface to be determined.
13. The system according to claim 12 , wherein the system is at least partially integrated into a portable camera device.
14. The system according to claim 12 , wherein the system comprises a camera device including the image sensor, said camera device being configured to transmit the image data wirelessly to a distant processing device.
15. The system according to claim 12 further comprising a dispensing unit configured to deliver a cosmetic product based on the at least one numerical value.