Back to results
US 11,776,161 B2Granted
Methods for identifying pore color
AssigneeThe Procter & Gamble Company
InventorsDissanayake Mudiyanselage Mahathma Bandara Dissanayake, Akira Matsubara, Naoki Miyamoto, Ankur Purwar
Life of this patent
Estimating the term…
Abstract
A method for identifying a pore color of at least one skin pore. The method includes obtaining at least one image of a subject, extracting a pore image from the obtained image, in which the extracted pore image identifies a boundary of the at least one skin pore, and superimposing the obtained image and the extracted pore image to identify the pore color within the identified boundary of the at least one skin pore.
Claims11
A method for identifying a pore color of at least one skin pore, comprising:
- a. obtaining only one image of a subject, optionally cropping the obtained image to obtain a portion of the image;
- and performing a histogram equalization to the obtained image or the portion of the image to obtain a histogram-equalized image;
- b. filtering the histogram-equalized image to remove one or more skin features that are not a skin pore to obtain a filtered image;
- wherein the one or more skin features are chosen from shine, line, spot, hair, mole, pimple, acne, blackhead, and/or whitehead;
- c. segmenting a pore image from the filtered image, wherein the extracted pore image identifies a boundary of each of the skin pores;
- wherein the segmenting is performed by one or more of an adaptive thresholding method, color-based segmentation method, transform method, and texture method;
- d. superimposing the obtained image and the extracted pore image to identify the pore color within the identified boundary of each skin pore;
- e. defining an adjacency area radially from the identified boundary of each of the skin pores;
- f. superimposing the obtained image and the defined adjacency area to identify an adjacency area color of each of the skin pores;
- and
- g. comparing the identified pore color to the identified adjacency area color to determine a pore color contrast value of each of the skin pores.
8 more elements
A method for determining a skin feature color contrast value of at least one skin feature, comprising:
- a. obtaining only one image of a subject, optionally cropping the obtained image to obtain a portion of the image;
- and performing a histogram equalization to the obtained image or the portion of the image to obtain a histogram-equalized image;
- b. filtering the histogram-equalized image to remove one or more skin features that are not a skin pore to obtain a filtered image;
- wherein the one or more skin features are chosen from shine, line, spot, hair, mole, pimple, acne, blackhead, and/or whitehead;
- c. segmenting a skin feature image from the filtered image, wherein the extracted skin feature image identifies a boundary of the at least one skin feature;
- wherein the segmenting is performed by one or more of an adaptive thresholding method, color-based segmentation method, transform method, and texture method;
- d. defining an adjacency area radially from the identified boundary of the at least one skin feature;
- e. superimposing the obtained image and the extracted skin feature image to identify a skin feature color within the identified boundary of the at least one skin feature;
- f. superimposing the obtained image and the defined adjacency area to identify an adjacency area color;
- and
- g. comparing the identified skin feature color to the identified adjacency area color to determine the skin feature color contrast value.
8 more elements
A method for determining a skin feature intensity contrast value of at least one skin feature, comprising:
- a. obtaining only one image of a subject, optionally cropping the obtained image to obtain a portion of the image;
- and performing a histogram equalization to the obtained image or the portion of the image to obtain a histogram-equalized image;
- b. filtering the histogram-equalized image to remove one or more skin features that are not a skin pore to obtain a filtered image;
- wherein the one or more skin features are chosen from shine, line, spot, hair, mole, pimple, acne, blackhead, and/or whitehead;
- c. segmenting a skin feature image from the filtered image, wherein the segmenting is performed by one or more of an adaptive thresholding method, color-based segmentation method, transform method, and texture method;
- wherein the extracted skin feature image identifies a boundary of the at least one skin feature;
- d. defining an adjacency area radially from the identified boundary of the at least one skin feature;
- e. superimposing the obtained image and the extracted skin feature image to identify an intensity within the identified boundary of the at least one skin feature;
- f. superimposing the obtained image and the defined adjacency area to identify an intensity of the adjacency area;
- and
- g. comparing the identified intensity within the identified boundary of the at least one skin feature to the identified intensity of the adjacency area to determine the skin feature intensity contrast value.
8 more elements
Dependencies are inferred from the claim text.