Image Registration Using A Fully Convolutional Network

Patent №

US 11,348,227

Granted

2022-05-31

Filed 2019

Owner

THE TRUSTEES OF THE UNIVERSITY OF PENNSYLVANIA

Lab

AI components

3

ml · vision · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16560235

Methods and systems for analyzing images are disclosed. An example method may comprise inputting one or more of a first image or a second image into a fully convolutional network, and determining an updated fully convolutional network by optimizing a similarity metric associated with spatially transforming the first image to match the second image. The one or more values of the fully convolutional network may be adjusted to optimize the similarity metric. The method may comprise registering one or more of the first image or the second image based on the updated fully convolutional network.

Machine learningVisionAI hardwareG06T 7/0014G06F 18/22G06N 3/045G06N 3/0464G06N 3/08G06N 3/084G06N 3/088G06N 3/0895+10 more

AI classification

Machine learning1.00
Vision1.00
AI hardware1.00
Natural language0.13
Speech0.03
Evolutionary computation0.00
Knowledge representation0.00
Planning0.00

Ownership

THE TRUSTEES OF THE UNIVERSITY OF PENNSYLVANIA

assignment · 527310537

Assignors

FAN, YONG, LI, HONGMING

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC