Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Multi-scale deep learning system

Patent ·
OSTI ID:1600450

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.

Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC52-07NA27344
Assignee:
Lawrence Livermore National Security, LLC (Livermore, CA)
Patent Number(s):
10,521,699
Application Number:
15/782,771
OSTI ID:
1600450
Country of Publication:
United States
Language:
English

References (1)

Image segmentation using consensus from hierarchical segmentation ensembles conference October 2014

Similar Records

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments
Journal Article · 2016 · PLoS Computational Biology (Online) · OSTI ID:1425613

A comparison of deep-learning-based inpainting techniques for experimental X-ray scattering
Journal Article · 2022 · Journal of Applied Crystallography (Online) · OSTI ID:1890010

Related Subjects