Invention Grant
- Patent Title: Recurrent deep neural network system for detecting overlays in images
-
Application No.: US18071939Application Date: 2022-11-30
-
Publication No.: US11893782B2Publication Date: 2024-02-06
- Inventor: Wilson Harron , Irene Zhu
- Applicant: Gracenote, Inc.
- Applicant Address: US CA Emeryville
- Assignee: The Nielsen Company (US), LLC
- Current Assignee: The Nielsen Company (US), LLC
- Current Assignee Address: US NY New York
- Agency: McDonnell Boehnen Hulbert & Berghoff LLP
- Main IPC: G06V10/00
- IPC: G06V10/00 ; G06V10/82 ; G06N3/08 ; G06V30/148 ; G06N3/044 ; G06N3/045 ; G06N3/047 ; G06N3/048 ; G06V30/18 ; G06V10/44 ; G06V10/26 ; G06V30/10

Abstract:
In one aspect, an example method includes a processor (1) applying a feature map network to an image to create a feature map comprising a grid of vectors characterizing at least one feature in the image and (2) applying a probability map network to the feature map to create a probability map assigning a probability to the at least one feature in the image, where the assigned probability corresponds to a likelihood that the at least one feature is an overlay. The method further includes the processor determining that the probability exceeds a threshold, and responsive to the processor determining that the probability exceeds the threshold, performing a processing action associated with the at least one feature.
Public/Granted literature
- US20230087773A1 Recurrent Deep Neural Network System for Detecting Overlays in Images Public/Granted day:2023-03-23
Information query