skip to main content
DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Multi-scale deep learning system

Abstract

A system for identifying objects in an image is provided. The system identifies segments of an image that may contain objects. For each segment, the system generates a segment score by inputting to a multi-scale neural network windows of multiple scales that include the segment that have been resampled to a fixed window size. A multi-scale neural network includes a feature extracting convolutional neural network (“feCNN”) for each scale and a classifier that inputs each feature of each feCNN. The segment score indicates whether the segment contains an object. The system generates a pixel score for pixels of the image. The pixel score for a pixel indicates that that pixel is within an object based on the segment scores of segments that contain that pixel. The system then identifies the object based on the pixel scores of neighboring pixels.

Inventors:
; ;
Issue Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1600450
Patent Number(s):
10,521,699
Application Number:
15/782,771
Assignee:
Lawrence Livermore National Security, LLC (Livermore, CA)
DOE Contract Number:  
AC52-07NA27344
Resource Type:
Patent
Resource Relation:
Patent File Date: 10/12/2017
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Bremer, Peer-Timo, Kim, Hyojin, and Thiagarajan, Jayaraman J. Multi-scale deep learning system. United States: N. p., 2019. Web.
Bremer, Peer-Timo, Kim, Hyojin, & Thiagarajan, Jayaraman J. Multi-scale deep learning system. United States.
Bremer, Peer-Timo, Kim, Hyojin, and Thiagarajan, Jayaraman J. Tue . "Multi-scale deep learning system". United States. https://www.osti.gov/servlets/purl/1600450.
@article{osti_1600450,
title = {Multi-scale deep learning system},
author = {Bremer, Peer-Timo and Kim, Hyojin and Thiagarajan, Jayaraman J.},
abstractNote = {A system for identifying objects in an image is provided. The system identifies segments of an image that may contain objects. For each segment, the system generates a segment score by inputting to a multi-scale neural network windows of multiple scales that include the segment that have been resampled to a fixed window size. A multi-scale neural network includes a feature extracting convolutional neural network (“feCNN”) for each scale and a classifier that inputs each feature of each feCNN. The segment score indicates whether the segment contains an object. The system generates a pixel score for pixels of the image. The pixel score for a pixel indicates that that pixel is within an object based on the segment scores of segments that contain that pixel. The system then identifies the object based on the pixel scores of neighboring pixels.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {12}
}

Patent:

Save / Share: