Back to results
US 9,754,155 B2Granted
Method and system for generating intrinsic images using a single reflectance technique
AssigneeTandent Vision Science, Inc.
InventorCasey Arthur Smith
Life of this patent
Estimating the term…
Abstract
An automated, computerized method is provided for processing an image. The method includes the steps of providing an image file depicting an image, in a computer memory, identifying a dominant region of single reflectance in the image and segregating the image into intrinsic images as a function of the dominant region of single reflectance.
Claims2
An automated, computerized method for processing an image of a face, comprising the steps of:
- providing an image file depicting an image of a face, in a computer memory;
- identifying a dominant region of single reflectance in the image of the face wherein the step of identifying a dominant region of single reflectance in the image is carried out by performing a pixel stability analysis;
- performing the pixel stability analysis as a function of pixel stability values relative to a threshold;
- identifying a skin mask on the image of a face;
- identifying eyebrow regions in the skin mask;
- setting a first threshold for use in the pixel stability analysis as a function of pixel stability values relative to a threshold, for pixels in the skin mask;
- setting a second threshold for use in the pixel stability analysis as a function of pixel stability values relative to a threshold, for pixels in the eyebrow regions;
- and
- segregating the image into intrinsic images as a function of the dominant region of single reflectance.
6 more elements
A computer program product, disposed on a non-transitory computer readable media, the product including computer executable process steps operable to control a computer to:
- provide an image file depicting an image of a face, in a computer memory,
- identify a dominant region of single reflectance in the image wherein the process step to identify a dominant region of single reflectance in the image is carried out by performing a pixel stability analysis,
- perform the pixel stability analysis as a function of pixel stability values relative to a threshold;
- identify a skin mask on the image of a face;
- identify eyebrow regions in the skin mask;
- set a first threshold for use in the pixel stability analysis as a function of pixel stability values relative to a threshold, for pixels in the skin mask;
- set a second threshold for use in the pixel stability analysis as a function of pixel stability values relative to a threshold, for pixels in the eyebrow regions, and
- segregate the image into intrinsic images as a function of the dominant region of single reflectance.
5 more elements
Dependencies are inferred from the claim text.