Image masks generated from local color models
AssigneeAdobe Systems Incorporated
InventorGregg D. Wilensky
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer program products, feature receiving an image mask where the image mask identifies a first opacity value of pixels in a raster image. The first opacity value ranges between a value representing foreground and a value representing background. Each pixel in the image has a color. A first boundary pixel is identified in the image. A second opacity value for the first boundary pixel is determined using a first local color model of opacity. The first local color model of opacity is determined based on the colors of the pixels in the image within a local neighborhood of the first boundary pixel.
Claims16
A computer-implemented method comprising:
- receiving an image mask, the image mask identifying first opacity values for pixels in an image, each pixel in the image having a color;
- identifying a first boundary pixel based on the image mask;
- determining, by a computing system, a plurality of weights by minimizing an error function that is based on the colors and the first opacity values of pixels within a local neighborhood of the first boundary pixel in the image;
- determining, by the computing system, a second opacity value for the first boundary pixel using a weighted sum, wherein the weighted sum combines the weights with corresponding products of color components of the first boundary pixel;
- and
- updating the image mask based on the second opacity value for the first boundary pixel.
A computer program product, encoded on a non-transitory computer-readable medium, operable to cause data processing apparatus to perform operations comprising:
- receiving an image mask, the image mask identifying first opacity values for pixels in an image, each pixel in the image having a color;
- identifying a first boundary pixel based on the image mask;
- determining a plurality of weights by minimizing an error function that is based on the colors and the first opacity values of the pixels within a local neighborhood of the first boundary pixel in the image;
- determining a second opacity value for the first boundary pixel using a weighted sum, wherein the weighted sum combines the weights with corresponding products of color components of the first boundary pixel;
- and
- updating the image mask based on the second opacity value for the first boundary pixel.
A system comprising:
- a display device;
- a computer program product encoded on a computer-readable medium;
- and
- one or more processors operable to execute the program product and perform operations comprising:
- receiving an image mask, the image mask identifying first opacity values for pixels in an image, each pixel in the image having a color;
- identifying a first boundary pixel based on the image mask;
- determining a plurality of weights by minimizing an error function that is based on the colors and the first opacity values of pixels within a local neighborhood of the first boundary pixel in the image;
- determining a second opacity value for the first boundary pixel using a weighted sum, wherein the weighted sum combines the weights with corresponding products of color components of the first boundary pixel;
- and
- updating the image mask based on the second opacity value for the first boundary pixel.
Dependencies are inferred from the claim text.