US 11,776,164 B2 · Content-adaptive tiling solution via image similarity for efficient image compression

Abstract

Techniques are provided herein for more efficiently storing images that have a common subject, such as product images that share the same product in the image. Each image undergoes an adaptive tiling procedure to split the image into a plurality of tiles, with each tile identifying a region of the image having pixels with the same content. The tiles across multiple images can then be clustered together and those tiles having identical content are removed. Once all duplicate tiles have been removed from the set of all tiles across the images, the tiles are once again clustered based on their encoding scheme and certain encoding parameters. Tiles within each cluster are compressed using the best compression technique for the tiles in each corresponding cluster. By removing duplicative tile content between numerous images of the same subject, the total amount of data that needs to be stored is reduced.

Claims20

Dependent claims

A method for efficiently storing a set of image files, the method comprising:

generating a first plurality of tiles for a first image, wherein tiles of the first plurality of tiles include pixels that are within a threshold color intensity of one another;
generating a second plurality of tiles for a second image, wherein tiles of the second plurality of tiles include pixels that are within the threshold color intensity of one another;
generating a first tile cluster that includes at least one tile from the first image and at least one tile from the second image;
removing a duplicate tile from the first tile cluster, wherein pixels of the duplicate tile share a same color intensity as another tile in the first tile cluster, and wherein remaining tiles after removing the duplicate tile constitute a filtered first tile cluster;
generating a second tile cluster that includes tiles from the filtered first tile cluster that share a common encoding parameter;
and
compressing one or more tiles of the second tile cluster, thereby providing one or more compressed tiles.

4 more elements

A system configured to efficiently store an image file, the system comprising:

at least one processor;
a tile generation module, executable by the at least one processor, and configured to:
generate a first plurality of tiles for a first image, wherein tiles of the first plurality of tiles include pixels that are within a threshold color intensity of one another, and
generate a second plurality of tiles for a second image, wherein tiles of the second plurality of tiles include pixels that are within the threshold color intensity of one another;
a content clustering module, executable by the at least one processor, and configured to:
generate a first tile cluster that includes at least one tile from the first image and at least one tile from the second image, and
remove a duplicate tile from the first tile cluster, wherein pixels of the duplicate tile share a same color intensity as another tile in the first tile cluster, and wherein remaining tiles after removing the duplicate tile constitute a filtered first tile cluster;
and
a tile compression module, executable by the at least one processor, and configured to:
generate a second tile cluster that includes tiles from the filtered first tile cluster that share a common encoding parameter, and
compress one or more tiles of the second tile cluster, thereby providing one or more compressed tiles.

8 more elements

A computer program product including one or more non-transitory machine-readable mediums having instructions encoded thereon that, when executed by at least one processor, cause a process for efficiently storing a set of image files to be carried out, the process comprising:

generating a first plurality of tiles for a first image, wherein each tile of the first plurality of tiles includes pixels that are within a threshold color intensity of one another;
generating a second plurality of tiles for a second image, wherein each tile of the second plurality of tiles includes pixels that are within the threshold color intensity of one another;
generating a first tile cluster that includes at least one tile from the first image and at least one tile from the second image;
removing a duplicate tile from the first tile cluster, wherein pixels of the duplicate tile share a same color intensity as another tile in the first tile cluster, and wherein remaining tiles after removing the duplicate tile constitute a filtered first tile cluster;
and
compressing one or more tiles of the filtered first tile cluster, thereby providing one or more compressed tiles.

3 more elements

Dependencies are inferred from the claim text.

Content-adaptive tiling solution via image similarity for efficient image compression

Life of this patent

Content-adaptive tiling solution via image similarity for efficient image compression

Life of this patent

Abstract

Claims20