US 12,008,734 B2 · Generating image masks from digital images via color density estimation and deep learning models

Abstract

This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize color density estimation in a blended boundary region of a digital image to generate an image mask. For example, the disclosed system extracts a foreground region, a background region, and a blended boundary region from a digital image. The disclosed system determines a color histogram—within a color space selected utilizing the foreground region and the background region—for a portion of the background region along an edge of the blended boundary region. Additionally, the disclosed system generates a color density map for the blended boundary region by comparing colors in the blended boundary region to colors in the color histogram of the background band. The disclosed system then generates a final mask for the digital image based on the color density map.

Claims20

Dependent claims

A method comprising:

extracting, from a digital image, a foreground region, a background region, and a blended boundary region that comprises a combination of foreground elements and background elements of the digital image;
determining a background band within the background region at a first edge of the blended boundary region and a foreground band within the foreground region at a second edge of the blended boundary region;
selecting a color space from a plurality of color spaces in response to comparing colors of the background band to colors of the foreground band in each of the plurality of color spaces;
determining a color histogram for the background band according to the color space selected based on the colors of the foreground band and the colors of the background band;
generating a color density map for the blended boundary region utilizing the color histogram for the background band;
and
generating a final mask for the digital image based on the color density map for the blended boundary region.

4 more elements

A system comprising:

at least one computer memory device comprising a digital image;
and
one or more servers configured to cause the system to:
extract, from the digital image, a foreground region, a background region, and a blended boundary region that comprises a combination of foreground elements and background elements of the digital image;
determine a background band within the background region at a first edge of the blended boundary region and a foreground band within the foreground region at a second edge of the blended boundary region;
select a color space from a plurality of color spaces in response to comparing colors of the foreground band and colors of the background band in each of the plurality of color spaces;
determine a color histogram for the background band according to the color space selected based on the colors of the foreground band and the colors of the background band;
generate a color density map for the blended boundary region utilizing the color histogram for the background band;
and
generate a final mask for the digital image based on the color density map for the blended boundary region.

7 more elements

A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause a computing device to:

extract, from a digital image, a foreground region, a background region, and a blended boundary region that comprises a combination of foreground elements and background elements of the digital image;
determine a background band within the background region at a first edge of the blended boundary region and a foreground band within the foreground region at a second edge of the blended boundary region;
select a color space from a plurality of color spaces in response to comparing colors of the background band to colors of the foreground band in each of the plurality of color spaces;
determine a color histogram for the background band according to the color space selected based on the colors of the foreground band and the colors of the background band;
generate a color density map for the blended boundary region utilizing the color histogram for the background band;
and
generate a final mask for the digital image based on the color density map for the blended boundary region.

4 more elements

Dependencies are inferred from the claim text.

Generating image masks from digital images via color density estimation and deep learning models

Life of this patent

Generating image masks from digital images via color density estimation and deep learning models

Life of this patent

Abstract

Claims20