Canon Patent for Machine Learning Apparatus Processing Image Data
Summary
The USPTO has granted Canon Kabushiki Kaisha a patent (US12586342B2) for a machine learning apparatus that processes image data to improve the accuracy of dividing patterns. The patent, filed on March 31, 2021, details an apparatus that uses a weighted loss function for machine learning of a model.
What changed
The United States Patent and Trademark Office (USPTO) has granted patent US12586342B2 to Canon Kabushiki Kaisha for an "Information processing apparatus that performs machine learning of learning model, learning method, and storage medium." The patent, filed on March 31, 2021, describes an apparatus and method for machine learning of a model that processes image data to output a dividing pattern. The CPU of the apparatus determines a dividing pattern and a weight associated with similarity to teacher data, then performs machine learning using a loss function weighted by this determined weight, aiming to increase the rate of outputting a correct dividing pattern.
This patent grant is primarily an intellectual property event and does not impose new regulatory obligations on businesses. However, it signifies innovation in the field of AI and machine learning for image processing, potentially impacting companies developing or utilizing similar technologies. Companies in the technology and manufacturing sectors should be aware of this patent as it relates to their own intellectual property strategies and potential licensing considerations.
Source document (simplified)
Information processing apparatus that performs machine learning of learning model, learning method, and storage medium
Grant US12586342B2 Kind: B2 Mar 24, 2026
Assignee
Canon Kabushiki Kaisha
Inventors
Hayato Oura
Abstract
An apparatus that performs machine learning of a learning model that can increase a rate of outputting a block dividing pattern as a correct answer. A CPU of the apparatus determines a dividing pattern output from a learning model that outputs, using an image for learning as an input thereto, a dividing pattern obtained by dividing the image, and a weight associated with a similarity with teacher data when performing machine learning of the learning model. The CPU performs machine learning of the learning model using a loss function weighted by the determined weight.
CPC Classifications
G06V 10/50 G06V 10/765 G06V 10/82 G06V 10/764 G06N 3/08
Filing Date
2021-03-31
Application No.
17219582
Claims
18
Named provisions
Related changes
Source
Classification
Who this affects
Taxonomy
Browse Categories
Get Telecom & Technology alerts
Weekly digest. AI-summarized, no noise.
Free. Unsubscribe anytime.
Get alerts for this source
We'll email you when ChangeBridge: Patent Grants - AI & Computing (G06N) publishes new changes.