USPTO Patent Grant: Image Processing Apparatus

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted a patent (US12586352B2) to CANON KABUSHIKI KAISHA for an image processing apparatus, method, and storage medium. The patent describes a system that calculates similarity between image regions and infers high-frequency components using a learning model.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has issued patent US12586352B2 to CANON KABUSHIKI KAISHA for an invention related to image processing. The patent details an apparatus and method for processing images by dividing them into partial regions, calculating similarity, forming local regions, and inferring high-frequency components using a learning model. The patent was granted on March 24, 2026, with a filing date of January 31, 2023.

This is a grant of intellectual property and does not impose new regulatory obligations on businesses. Companies developing or utilizing similar image processing technologies may wish to review the patent details to understand the scope of the claims and ensure their own innovations do not infringe upon this granted patent. No compliance actions are required.

Source document (simplified)

← USPTO Patent Grants

Image processing apparatus, image processing method and storage medium

Grant US12586352B2 Kind: B2 Mar 24, 2026

Assignee

CANON KABUSHIKI KAISHA

Inventors

Ryuichi Ishikuri

Abstract

An image processing apparatus calculates a degree of similarity with a partial region corresponding to a previous image which is a high definition target previous to a current image selected as a high definition target for each one of a plurality of partial regions obtained by dividing the current image, determines a plurality of local regions form the current image by combining a collection of one or more partial regions with the degree of similarity equal to or greater than a threshold as one local region and treating a partial region with the degree of similarity less than the threshold as a separate local region. The image processing apparatus infers high frequency components for each one of the plurality of local regions using a learning model selected based on the current image.

CPC Classifications

G06V 10/771 G06V 10/26 G06V 10/443 G06V 10/761 G06V 10/25 G06V 10/764 G06V 10/82 H04N 7/0135 H04N 7/0117 H04N 7/014 G06N 20/00 G06T 3/4046 G06T 3/4053