Dividing pattern determination device capable of reducing amount of computation, dividing pattern determination method, learning device, learning method, and storage medium
AssigneeCanon Kabushiki Kaisha
InventorDai Miyauchi
Life of this patent
Estimating the term…
Abstract
A dividing pattern determination device capable of reducing the amount of computation performed when determining a dividing pattern of an image. An image for which a dividing pattern is expressed by a hierarchical structure for each predetermined area is input to a feature extraction section, and the feature extraction section generates, based on the input image, for the predetermined area, a hierarchy map in which a value indicative of a block size is associated with each of a plurality of blocks in the predetermined area. A determination section determines a dividing pattern of the image based on the generated hierarchy map.
Claims15
A device comprising:
- at least one processor;
- and
- a memory coupled to the at least one processor, the memory having instructions that, when executed by the processor, perform the operations comprising:
- inputting a first image of 64×64 pixels to a learning model and causing the learning model to generate a dividing pattern map for the first image of 64×64 pixels, the learning model having been subjected to machine learning, using images as input data and dividing pattern maps as teacher data;
- and
- using the dividing pattern map generated for the first image to determine one or more sizes of sub-blocks to be used for dividing the first image,
- wherein the dividing pattern map includes pieces of data corresponding to 16 prediction areas given by dividing the first image of 64×64 pixels into 4×4 blocks, respectively, and each of the pieces of data includes information indicative of which of a sub-block of 64×64 pixels, 4-division sub-blocks of 32×32 pixels, 16-division sub-blocks of 16×16 pixels, or 32-division sub-blocks of 8×8 pixels are to be used in corresponding one of the 4×4 blocks, as the sub-blocks to be used for dividing the first image.
A control method for a device, comprising:
- inputting a first image of 64×64 pixels to a learning model and causing the learning model to generate a dividing pattern map for the first image of 64×64 pixels, the learning model having been subjected to machine learning using images as input data and dividing pattern maps as teacher data;
- and
- using the dividing pattern map generated for the first image to determine one or more sizes of sub-blocks to be used for dividing the first image,
- wherein the dividing pattern map includes pieces of data corresponding to 16 prediction areas given by dividing the first image of 64×64 pixels into 4×4 blocks, respectively, and each of the pieces of data includes information indicative of which of a sub-block of 64×64 pixels, 4-division sub-blocks of 32×32 pixels, 16-division sub-blocks of 16×16 pixels, or 32-division sub-blocks of 8×8 pixels are to be used in corresponding one of the 4×4 blocks, as the sub-blocks to be used for dividing the first image.
A non-transitory computer-readable storage medium which stores a program for causing a computer to execute a method, the method comprising:
- inputting a first image of 64×64 pixels to a learning model and causing the learning model to generate a dividing pattern map for the first image of 64×64 pixels, the learning model having been subjected to machine learning using images as input data and dividing pattern maps as teacher data;
- and
- using the dividing pattern map generated for the first image to determine one or more sizes of sub-blocks to be used for dividing the first image,
- wherein the dividing pattern map includes pieces of data corresponding to 16 prediction areas given by dividing the first image of 64×64 pixels into 4×4 blocks, respectively, and each of the pieces of data includes information indicative of which of a sub-block of 64×64 pixels, 4-division sub-blocks of 32×32 pixels, 16-division sub-blocks of 16×16 pixels, or 32-division sub-blocks of 8×8 pixels are to be used in corresponding one of the 4×4 blocks, as the sub-blocks to be used for dividing the first image.
Dependencies are inferred from the claim text.