Patent · US Active

Deep learning architecture for automated image feature extraction

US10796221B2 · kind B2 · utility

36Cited by

6References

20Claims

0Family size

Assignee

General Electric Company · US

Inventors

Min Zhang · San Ramon, US
Gopal B. Avinash · San Ramon, US

Key dates

Filing date	Dec 27, 2017
Grant date	Oct 6, 2020
Priority date	—
Expiry date	Mar 30, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG06V2201/03
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Systems and techniques for facilitating a deep learning architecture for automated image feature extraction are presented. In one example, a system includes a machine learning component. The machine learning component generates learned imaging output regarding imaging data based on a convolutional neural network that receives the imaging data. The machine learning component also performs a plurality of sequential and/or parallel downsampling and upsampling of the imaging data associated with convolutional layers of the convolutional neural network.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.