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 Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1600450
- Patent Number(s):
- 10521699
- Application Number:
- 15/782,771
- Assignee:
- Lawrence Livermore National Security, LLC (Livermore, CA)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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}
}
Works referenced in this record:
Image segmentation using consensus from hierarchical segmentation ensembles
conference, October 2014
- Kim, Hyojin; Thiagarajan, Jayaraman J.; Bremer, Peer-Timo
- 2014 IEEE International Conference on Image Processing (ICIP)
Image Recording System
patent-application, July 2015
- Cho, SungBong; Lee, SungHoon; Chae, SeokHo
- US Patent Application 14/506806; 20150208021
Kernel Sparse Modules for Automated Tumor Segmentation
patent-application, January 2016
- Thiagarajan, Jayaraman Jayaraman; Ramamurthy, Karthikeyan; Spanias, Andreas
- US Patent Application 14/853617; 20160005183