Sony Patent for ML-Based Eyesight Test System Using Eye Image Analysis
Summary
The USPTO granted Patent US12599303B2 to Sony Group Corporation on April 14, 2026, covering a machine learning-based eyesight test system. The system uses a processor and ML algorithm to estimate eyesight characteristics including myopia, hyperopia, and astigmatism from eye images. The patent application was filed February 28, 2023 and contains 17 claims defining the scope of the invention.
What changed
USPTO granted Patent US12599303B2 to Sony Group Corporation on April 14, 2026. The patent covers an information processing device and eyesight test system using machine learning algorithms to estimate vision characteristics from eye images. The system analyzes eye relaxation states and micromovements to determine myopia, hyperopia, and astigmatism, providing objective automated eyesight assessment.
For technology companies and healthcare providers, this patent establishes Sony's intellectual property rights in ML-based vision testing. Parties developing similar automated eyesight assessment systems should review the claims to ensure freedom to operate or consider licensing. The patent enables deployment of objective vision testing in remote locations and consumer devices, potentially disrupting traditional manual eyesight testing methods.
What to do next
- Review patent claims to assess potential overlap with existing products or services
- Evaluate licensing opportunities if implementing ML-based vision assessment technology
Archived snapshot
Apr 14, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Information processing device, eyesight test system, information processing method
Grant US12599303B2 Kind: B2 Apr 14, 2026
Assignee
Sony Group Corporation
Inventors
Justinas Miseikis
Abstract
An information processing device for estimating eyesight of a person comprises a processor coupled to memory storing machine readable instructions. The processor obtains image data representing an image of an eye and inputs the data into a machine learning algorithm trained to estimate eyesight characteristics from eye images. The system estimates the person's eyesight by determining at least one of myopia, hyperopia, and astigmatism based on the image data and algorithm output. The invention addresses limitations of traditional manual eyesight tests that are prone to human error and subjective patient feedback. The machine learning algorithm analyzes eye relaxation states and micromovements that indicate optimal vision correction, enabling objective automated eyesight assessment deployable in remote locations or consumer devices.
CPC Classifications
A61B 3/14 A61B 3/0285 A61B 3/036 G06V 10/82 G06V 40/18
Filing Date
2023-02-28
Application No.
18175565
Claims
17
Related changes
Get daily alerts for USPTO Patent Grants - Diagnosis & Surgery (A61B)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - Diagnosis & Surgery (A61B) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.