Back to results
US 10,254,938 B2Granted
Image processing device and method with user defined image subsets
AssigneeSony Corporation
InventorsYasutaka Fujii, Manabu Yasumi, Hideshi Yamada, Mitsuharu Ohki
Life of this patent
Estimating the term…
Abstract
An apparatus includes a mode determination circuit configured to determine an input mode from at least a first mode and a second mode; an input circuit configured to receive a signal based on a user input; and an image processing circuit configured to determine a subset of an image including a desired image area based on the user input of a first line in the first mode, and to determine the desired image area based on the user input of a second line on the subset of the image in the second mode.
Claims20
A system, comprising:
- an input circuit configured to receive a signal based on a user input;
- and
- an image processing circuit configured to:
- determine an input mode from at least one of a first mode or a second mode;
- determine a subset of an image based on the user input of a first line in the first model;
- determine a desired image area of the subset of the image based on the user input of a second line on the subset of the image in the second mode;
- generate an alpha mat image based on the subset of the image;
- determine an unknown region, within the alpha mat image, from a boundary that is in contact with each of a foreground region of the alpha mat image and a background region of the alpha mat image, wherein the unknown region includes a plurality of pixels, and wherein a pixel value of each of the plurality of pixels has a first pixel value;
- calculate a mixing ratio based on a shortest distance to the foreground region of the alpha mat image and the background region of the alpha mat image with respect to each of the plurality of pixels of the determined unknown region;
- change the first pixel value to a second pixel value based on the mixing ratio, wherein the second pixel value indicates a foreground of the image in one of the first mode or the second mode.
7 more elements
A method, comprising:
- receiving a signal based on a user input;
- determining an input mode from at least one of a first mode or a second mode;
- determining a subset of an image based on the user input of a first line in the first mode;
- determining a desired image area of the subset of the image based on the user input of a second line on the subset of the image in the second mode;
- generating an alpha mat image based on the subset of the image;
- determining an unknown region, within the alpha mat image, from a boundary that is in contact with each of a foreground region of the alpha mat image and a background region of the alpha mat image, wherein the unknown region includes a plurality of pixels, and wherein a pixel value of each of the plurality of pixels has a first pixel value;
- calculating a mixing ratio based on a shortest distance to the foreground region of the alpha mat image and the background region of the alpha mat image with respect to each of the plurality of pixels of the determined unknown region;
- and
- changing the first pixel value to a second pixel value based on the mixing ratio, wherein the second pixel value indicates a foreground of the image in one of the first mode or the second mode.
6 more elements
A non-transitory computer readable medium having stored thereon computer-readable instructions, which when executed by a computer, cause the computer to execute operations, the operations comprising:
- receiving a signal based on a user input;
- determining an input mode from at least one of a first mode or a second mode;
- determining a subset of an image based on the user input of a first line in the first mode;
- determining a desired image area of the subset of the image based on the user input of a second line on the subset of the image in the second mode;
- generating an alpha mat image based on the subset of the image;
- determining an unknown region, within the alpha mat image, from a boundary that is in contact with each of a foreground region of the alpha mat image and a background region of the alpha mat image, wherein the unknown region includes a plurality of pixels, and wherein a pixel value of each of the plurality of pixels has a first pixel value;
- calculating a mixing ratio based on a shortest distance to the foreground region of the alpha mat image and the background region of the alpha mat image with respect to each of the plurality of pixels of the determined unknown region;
- and
- changing the first pixel value to a second pixel value based on the mixing ratio, wherein the second pixel value indicates a foreground of the image in one of the first mode or the second mode.
6 more elements
An apparatus, comprising:
- a display device configured to display an image;
- an input circuit configured to receive a signal based on a user input;
- and
- an image processing circuit configured to:
- determine an input mode from at least one of a first mode or a second mode;
- determine a subset of the image based on the user input of a first line in the first mode;
- determine a desired image area of the subset of the image based on the user input of a second line on the subset of the image in the second mode;
- generate an alpha mat image based on the subset of the image;
- determine an unknown region, within the alpha mat image, from a boundary that is in contact with each of a foreground region of the alpha mat image and a background region of the alpha mat image, wherein the unknown region includes a plurality of pixels, and wherein a pixel value of each of the plurality of pixels has a first pixel value;
- calculate a mixing ratio based on a shortest distance to the foreground region of the alpha mat image and the background region of the alpha mat image with respect to each of the plurality of pixels of the determined unknown region;
- and
- change the first pixel value to a second pixel value based on the mixing ratio, wherein the second pixel value indicates a foreground of the image in one of the first mode or the second mode.
9 more elements
Dependencies are inferred from the claim text.