Process for evaluation of at least one facial clinical sign

Patent metadata

Field	Value
Publication number	US-9955909-B2
Application number	US-201415104011-A
Country	US
Kind code	B2
Filing date	Dec 11, 2014
Priority date	Dec 12, 2013
Publication date	May 1, 2018
Grant date	May 1, 2018

Abstract

The present invention relates to a process without a therapeutic target that evaluates at least one facial clinical sign and/or evaluates make-up, in particular evaluates wrinkles or fine lines from a portion of the face, including steps consisting in: —from a sequence of facial images of a person filmed while emitting at least one sound, extract from the sequence one or more images coinciding with the emission of at least one predefined sound, —from the resulting image or images extracted, evaluate at least one facial clinical sign appearing on the image or images extracted and/or evaluate at least one characteristic related to make-up.

First claim

The invention claimed is:

1. A method to evaluate at least one facial clinical sign, comprising:
from a digitized sequence of facial images of a person filmed while emitting at least one sound, extract, with a device with a processor, one or more images coinciding with the emission of at least one predefined sound, the image extraction being performed automatically based on an analysis by the device of the sound emitted;
from the resulting image or images extracted, evaluate, with the device with the processor, at least one facial clinical sign appearing on the image or images extracted, the evaluation comprising comparing automatically by the device the images extracted with reference images.

2. The method according to claim 1 , wherein the image extraction comprises selecting image by voice recognition applied to a soundtrack of the sequence and/or by spectral analysis of the sounds collected, or selecting images for which a specific frequency exceeds a predefined amplitude.

3. The method according to claim 1 , wherein at least one sound to reproduce is displayed in front of the person filmed.

4. The method according to claim 1 , wherein the images extracted are compared with reference images.

5. The method according to claim 1 , wherein the sequence includes images concerning the presence of wrinkles or fine lines at the corners of the lips, under the eye, the upper lip, crow's feet, and/or the nasolabial fold.

6. The method according to claim 5 , the sequence including images of the entire face.

7. The method according to claim 1 , wherein the evaluation of the clinical sign or signs from the image or images extracted occurs automatically, by comparison with reference data.

8. The method according to claim 1 , wherein the image or images extracted are, at least for some, automatically cropped as a function of the clinical sign or signs to be evaluated.

9. The method according to claim 1 , wherein the sequence of images includes several different sounds emitted successively by the person and in which the images corresponding respectively to several predefined sounds are extracted.

10. The method according to claim 1 , including at least five different sounds.

11. The method according to claim 9 , the sound being selected from “A”, “E”, “O”, “OUI”, “STI”, “ART” and “TO”.

12. The method according to claim 1 , wherein the sound or the sounds of the sequence include phonemes.

13. The method according to claim 1 , wherein the selection of the image or images to be extracted occurs by voice recognition applied to the soundtrack of the sequence and/or by spectral analysis of the sounds collected.

14. The method according to claim 1 , wherein a score associated with each of the at least one clinical sign is automatically generated as a result of the evaluation of this clinical sign.

15. The method according to claim 1 , wherein the images are acquired by a device held by the person being evaluated or placed in front of said person.

16. The method according to claim 1 , wherein the acquisition of the images of the sequence occurs at an acquisition frequency greater than or equal to 50, images per second.

17. The method according to claim 14 , wherein several curves of how the score progresses for a given clinical sign of the at least one clinical sign are generated as a function of the order in which the sounds are emitted.

18. The method according to claim 1 , wherein, in parallel with the automatic evaluation of the clinical sign or signs, a self-assessment score is collected by the person for said clinical sign or signs and/or an evaluation score is collected by a panel of experts for said clinical sign or signs.

19. A method to demonstrate the effect of a cosmetic treatment on the face, comprising:
make a first evaluation of at least one facial clinical sign, using the method as defined in claim 1 ,
make a new evaluation, after a facial cosmetic treatment,
compare the evaluations,
generate representative information about treatment efficacy from comparison of evaluations.

20. A method to evaluate make-up, comprising:
extract, with a device with a processor, from a digitized sequence of facial images of a person filmed while emitting at least one sound, one or more images coinciding with the emission of at least one predefined sound, the image extraction being performed automatically based on an analysis by the device of the sound emitted;
from the resulting image or images extracted, evaluate, with the device with the processor, the hold of a make-up and its effect on facial appearance to be evaluated during facial deformations, and/or make-up visibility as a function of facial deformations, the evaluation comprising comparing automatically by the device the images extracted with reference images.

Assignees

• Oreal

Inventors

• Flament Frédéric

Classifications

• A61B5/442 Primary

  Evaluating skin mechanical properties, e.g. elasticity, hardness, texture, wrinkle assessment · CPC title

• A61B5/0077

  Devices for viewing the surface of the body, e.g. camera, magnifying lens · CPC title

• A61B5/4803

  Speech analysis specially adapted for diagnostic purposes · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06K9/00281

  Physics · mapped topic