Method and apparatus for generating graphical chromophore maps
A method, non-transitory computer readable medium and apparatus for generating graphical chromophore maps are disclosed. For example, the method includes receiving an image of a customer from a mobile endpoint device of the customer, wherein the image is taken via the mobile endpoint device of the customer, converting RGB values of the image into a spectral representation, performing a constrained independent component analysis (ICA) on the spectral representation to obtain three or more independent components that are ordered, generating a first graphical chromophore map of a first independent component of the three or more independent components that are ordered and a second graphical chromophore map of a second independent component of the three or more independent components that are ordered and transmitting the first graphical chromophore map and the second graphical chromophore map to the mobile endpoint device of the customer for display.
1. A method, comprising:
receiving, by a processor, an image of a customer from a mobile endpoint device of the customer, wherein the image is taken via the mobile endpoint device of the customer;
converting, by the processor, red, green and blue (RGB) values of the image into a spectral representation;
performing, by the processor, a constrained independent component analysis (ICA) on the spectral representation to obtain three independent components that are ordered, wherein the three independent components are ordered by the constrained ICA by adding a distance component to the constrained ICA, wherein the distance component minimizes a distance between a spectral vector associated with one of the three independent components and a vector of a mixing matrix associated with the one of the three independent components, wherein the spectral vector is calculated during a training phase;
generating, by the processor, a first graphical chromophore map of a first independent component of the three independent components that are ordered and a second graphical chromophore map of a second independent component of the three independent components that are ordered; and
transmitting, by the processor, the first graphical chromophore map and the second graphical chromophore map to the mobile endpoint device of the customer for display.
2. The method of claim 1 , wherein the image is of a face of the customer.
3. The method of claim 2 , further comprising:
extracting, by the processor, one or more facial regions of the face.
4. The method of claim 3 , wherein the first graphical chromophore map displays the first independent component in the one or more facial regions and the second graphical chromophore map displays the second independent component in the one or more facial regions.
5. The method of claim 1 , wherein the three independent components that are ordered comprise a melanin component, a hemoglobin component and a shading component.
6. The method of claim 1 , wherein the constrained ICA analysis provides a mixing matrix, wherein each row of the mixing matrix comprises a plurality of wavelengths and each column of the mixing matrix comprises one of the three independent components and a weight vector of the three independent components.
7. The method of claim 6 , wherein the generating the first graphical chromophore map, comprises:
setting, by the processor, weight values for all independent components except the first independent component to zero; and
inverting, by the processor, the weight values of the first independent component for the plurality of wavelengths into corresponding RGB values.
8. The method of claim 6 , wherein the generating the second graphical chromophore map, comprises:
setting, by the processor, weight values for all independent components except the second independent component to zero; and
inverting, by the processor, the weight values of the second independent component for the plurality of wavelengths into corresponding RGB values.
9. A non-transitory computer-readable medium storing a plurality of instructions, which when executed by a processor, cause the processor to perform operations, the operations comprising:
receiving an image of a customer from a mobile endpoint device of the customer, wherein the image is taken via the mobile endpoint device of the customer;
converting red, green and blue (RGB) values of the image into a spectral representation;
performing a constrained independent component analysis (ICA) on the spectral representation to obtain three independent components that are ordered, wherein the three independent components are ordered by the constrained ICA by adding a distance component to the constrained ICA, wherein the distance component minimizes a distance between a spectral vector associated with one of the three independent components and a vector of a mixing matrix associated with the one of the three independent components, wherein the spectral vector is calculated during a training phase;
generating a first graphical chromophore map of a first independent component of the three independent components that are ordered and a second graphical chromophore map of a second independent component of the three independent components that are ordered; and
transmitting the first graphical chromophore map and the second graphical chromophore map to the mobile endpoint device of the customer for display.
10. The non-transitory computer-readable medium of claim 9 , wherein the image is of a face of the customer.
11. The non-transitory computer-readable medium of claim 10 , further comprising:
extracting one or more facial regions of the face.
12. The non-transitory computer-readable medium of claim 11 , wherein the first graphical chromophore map displays the first independent component in the one or more facial regions and the second graphical chromophore map displays the second independent component in the one or more facial regions.
13. The non-transitory computer-readable medium of claim 9 , wherein the three independent components that are ordered comprise a melanin component, a hemoglobin component and a shading component.
14. The non-transitory computer-readable medium of claim 9 , wherein the constrained ICA analysis provides a mixing matrix, wherein each row of the mixing matrix comprises a plurality of wavelengths and each column of the mixing matrix comprises one of the three independent components and a weight vector of the three independent components.
15. The non-transitory computer-readable medium of claim 14 , wherein the generating the first graphical chromophore map, comprises:
setting weight values for all independent components except the first independent component to zero; and
inverting the weight values of the first independent component for the plurality of wavelengths into corresponding RGB values; and
wherein generating the second graphical chromophore map, comprises:
setting weight values for all independent components except the second independent component to zero; and
inverting the weight values of the second independent component for the plurality of wavelengths into corresponding RGB values.
16. A method, comprising:
receiving, by a processor, a mobile selfie image of a face of a customer from a mobile endpoint device of the customer, wherein the mobile selfie image is taken via the mobile endpoint device of the customer;
extracting, by the processor, facial features from the mobile selfie image, the facial features comprising a mouth, cheeks, a nose and a forehead of the customer;
converting, by the processor, red, green and blue (RGB) values of the facial features into a spectral representation;
performing, by the processor, a constrained independent component analysis (ICA) on the spectral representation to obtain a shading component, a melanin component, and a hemoglobin component, wherein the constrained ICA is performed using an additional distance component that orders the shading component, the melanin component and the hemoglobin component, wherein the additional distance component minimizes a distance between a spectral vector associated with one of the shading component, the melanin component and the hemoglobin component and a vector of a mixing matrix associated with the one of the shading component, the melanin component and the hemoglobin component, wherein the spectral vector is calculated during a training phase;
generating, by the processor, a melanin graphical chromophore map based on a first inversion of only the melanin component into corresponding RGB values for each pixel that comprise the facial features from the mobile selfie image;
generating, by the processor, a hemoglobin graphical chromophore map based on a second inversion of only the hemoglobin component into corresponding RGB values for the each pixel that comprise the facial features from the mobile selfie image; and
transmitting, by the processor, the melanin graphical chromophore map and the hemoglobin graphical chromophore map to the mobile endpoint device of the customer for display.