Title:
画像コンテンツ認識のための方法およびシステム
Document Type and Number:
Japanese Patent JP7457647
Kind Code:
B2
Abstract:
A method of recognizing image content, comprises applying to the image a neural network which comprises an input layer for receiving the image, a plurality of hidden layers for processing the image, and an output layer for generating output pertaining to an estimated image content based on outputs of the hidden layers. The method further comprises applying to an output of at least one of the hidden layers a neural network branch, which is independent of the neural network and which has an output layer for generating output pertaining to an estimated error level of the estimate. A combined output indicative of the estimated image content and the estimated error level is generated.
Inventors:
Wolf Riolu
More Gnome
More Gnome
Application Number:
JP2020515741A
Publication Date:
March 28, 2024
Filing Date:
September 17, 2018
Export Citation:
Assignee:
RAMOT AT TEL AVIV UNIVERSITY LTD.
International Classes:
G06V30/194; G06T7/00; G06V20/62; G06V30/28
Domestic Patent References:
| JP2000155803A | ||||
| JP2016139176A | ||||
| JP201710543A | ||||
| JP5101029A |
Foreign References:
| US20160189010 |
Attorney, Agent or Firm:
Patent Attorney Corporation Washida International Patent Office