SYSTEM AND METHOD FOR ANALYSIS OF LIGHT-MATTER INTERACTION BASED ON SPECTRAL CONVOLUTION

• US 20150287191A1
• Filed: 04/24/2015
• Published: 10/08/2015
• Est. Priority Date: 01/05/2007
• Status: Abandoned Application

• Current Assignee: mySkin Inc.
• Original Assignee: mySkin Inc.
• Inventors: Koruga, Djuro, Tomic, Alexandar
• Application Number:
  US14/695,990
• Publication Number:
  US 20150287191A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A45D 2044/007 Devices for determining the condition of hair or skin or for selecting the appropriate cosmetic or hair treatment
• CPC Class Codes: A45D 44/00 Other cosmetic or toiletry articles, e.g. for hairdressers' rooms
• CPC Class Codes: A61B 5/0088 for oral or dental tissue
• CPC Class Codes: A61B 5/0091 for mammography
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/415 the glands, e.g. tonsils, adenoids or thymus
• CPC Class Codes: A61B 5/442 Evaluating skin mechanical properties, e.g. elasticity, hardness, texture, wrinkle assessment
• CPC Class Codes: A61B 5/443 Evaluating skin constituents, e.g. elastin, melanin, water
• CPC Class Codes: A61B 5/444 Evaluating skin marks, e.g. mole, nevi, tumour, scar
• CPC Class Codes: A61B 5/445 Evaluating skin irritation or skin trauma, e.g. rash, eczema, wound, bed sore
• CPC Class Codes: G06F 18/245 relating to the decision surface
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

In embodiments of the present disclosure, systems and methods of a method and algorithm for creating a unique spectral fingerprint are based on the convolution of RGB color channel spectral plots generated from digital images that have captured single and/or multi-wavelength light-matter interaction.

Claims

1. A method for determining skin characteristics and cosmetic features using color analysis, comprising:

analyzing the color of skin images in a pixel by pixel manner in a Red-Green-Blue (RGB) color system for an acquired digital image;

converting colors obtained in a device-dependent RGB color system into a device-independent standard RGB color system (sRGB);

generating a sample of most frequent sRGB colors responsive to analyzing the color of skin images in a pixel by pixel manner in the sRGB color system for the acquired digital image;

modeling the standard red, green, and blue component color distribution with Gaussian probabilistic distribution with estimated parameters (expected value and standard deviation) on the generated sRGB color sample for the acquired digital image; and

generating a phototype of the skin through a decision tree unit responsive to the estimated distribution model parameters colors.

2. The method of claim 1, wherein the step of analyzing the color of skin images in a pixel by pixel manner in a sRGB color system for an acquired digital image comprises analyzing a digital image of a part of a person'"'"'s skin by generating a table of most frequent colors appearing in the digital image.

3. The method of claim 1, wherein the step of generating a sample of most frequent sRGB colors responsive to analyzing color of skin images in the sRGB color system for the acquired digital image comprises preserving a plurality of sRGB color values.

4. The method of claim 1, wherein the step of modeling the standard red, green, and blue component color distribution with Gaussian probabilistic distribution with estimated parameters (expected value and standard deviation) on the generated sRGB color sample for the acquired digital image comprises approximating colors on the generated sRGB color samples by a Gaussian normal distribution.

5. The method of claim 4, wherein the step of approximating colors on the generated sRGB color samples by a Gaussian normal distribution comprises approximating colors on the generated sRGB color samples by a superposition of a plurality of Gaussian normal distributions.

6. The method of claim 1, wherein the step of generating a phototype of the skin through a decision tree unit responsive to the estimated distribution parameters comprises generating a phototype of the skin according to a corrected Fitzpatrick classification.

7. The method of claim 6, wherein the step of generating a phototype of the skin according to a corrected Fitzpatrick classification comprises generating a phototype of the skin according to a skin type scale which ranges from very fair skin to very dark skin.

8. A system for skin phototype determination using photograph analysis, comprising:

an image capturing device for capturing digital images of a skin;

an analyzer coupled to the image capturing device for performing a pixel by pixel analysis of a digital image of a part of a person'"'"'s skin;

a convertor to convert from a device-dependent RGB to device-independent sRGB color system;

a sampling device coupled to the image capturing device for generating a standard Red Green Blue (RGB) color samples for the captured digital image of the skin;

an approximating device coupled to the sampling device for approximating the color distribution parameters on the generated sRGB color samples using the estimates of expected value and standard deviation for the captured digital image of the skin; and

a decision tree unit coupled to the approximating device for generating a phototype of the skin using standard Red and Blue components of the approximated colors.

9. The system of claim 8, wherein the image capturing device comprises a digital camera unit.

10. The system of claim 8, wherein the analyzer comprises a quantization device for generating a table of most frequent colors appearing on the picture of the part of the person'"'"'s skin.

11. The system of claim 8, wherein the approximating device comprises at least one Gaussian normal distribution unit.

12. The system of claim 8, wherein the decision tree unit comprises a Fitzpatrick scaling unit for categorizing a skin phototype in accordance with a skin type scale which ranges from very fair skin to very dark skin.

13. The system of claim 8, further comprising a scaled Gaussian normal distribution unit for approximating colors on the generated sRGB color samples using estimates of expected value and standard deviation for the captured digital image of the skin.

14. The system of claim 8, wherein the system is used in a cosmetics and surgical industry.

15. The system of claim 8 further comprising a subsystem for determination of cosmetic features for at least one of:

a human element; and

a veterinary element.

16. The system of claim 15, wherein the cosmetic features comprise at least one of features pertaining to hair, nail and skin.