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

Title: Image registration via optimization over disjoint image regions

Abstract

Technologies pertaining to registering a target image with a base image are described. In a general embodiment, the base image is selected from a set of images, and the target image is an image in the set of images that is to be registered to the base image. A set of disjoint regions of the target image is selected, and a transform to be applied to the target image is computed based on the optimization of a metric over the selected set of disjoint regions. The transform is applied to the target image so as to register the target image with the base image.

Inventors:
; ; ; ;
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1419767
Patent Number(s):
9,886,645
Application Number:
14/270,129
Assignee:
National Technology & Engineering Solutions of Sandia, LLC (Albuquerque, NM) SNL-A
DOE Contract Number:
AC04-94AL85000
Resource Type:
Patent
Resource Relation:
Patent File Date: 2014 May 05
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Pitts, Todd, Hathaway, Simon, Karelitz, David B., Sandusky, John, and Laine, Mark Richard. Image registration via optimization over disjoint image regions. United States: N. p., 2018. Web.
Pitts, Todd, Hathaway, Simon, Karelitz, David B., Sandusky, John, & Laine, Mark Richard. Image registration via optimization over disjoint image regions. United States.
Pitts, Todd, Hathaway, Simon, Karelitz, David B., Sandusky, John, and Laine, Mark Richard. 2018. "Image registration via optimization over disjoint image regions". United States. doi:. https://www.osti.gov/servlets/purl/1419767.
@article{osti_1419767,
title = {Image registration via optimization over disjoint image regions},
author = {Pitts, Todd and Hathaway, Simon and Karelitz, David B. and Sandusky, John and Laine, Mark Richard},
abstractNote = {Technologies pertaining to registering a target image with a base image are described. In a general embodiment, the base image is selected from a set of images, and the target image is an image in the set of images that is to be registered to the base image. A set of disjoint regions of the target image is selected, and a transform to be applied to the target image is computed based on the optimization of a metric over the selected set of disjoint regions. The transform is applied to the target image so as to register the target image with the base image.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2018,
month = 2
}

Patent:

Save / Share:
  • Image registration of low contrast image sequences is provided. In one aspect, a desired region of an image is automatically segmented and only the desired region is registered. Active contours and adaptive thresholding of intensity or edge information may be used to segment the desired regions. A transform function is defined to register the segmented region, and sub-pixel information may be determined using one or more interpolation methods.
  • Image registration of low contrast image sequences is provided. In one aspect, a desired region of an image is automatically segmented and only the desired region is registered. Active contours and adaptive thresholding of intensity or edge information may be used to segment the desired regions. A transform function is defined to register the segmented region, and sub-pixel information may be determined using one or more interpolation methods.
  • Registration information for images of a common target obtained from a plurality of different spectral bands can be obtained by combining edge detection and phase correlation. The images are edge-filtered, and pairs of the edge-filtered images are then phase correlated to produce phase correlation images. The registration information can be determined based on these phase correlation images.
  • In an image registration method, edges are detected in a first image and a second image. A percentage of edge pixels in a subset of the second image that are also edges in the first image shifted by a translation is calculated. A best registration point is calculated based on a maximum percentage of edges matched. In a predefined search region, all registration points other than the best registration point are identified that are not significantly worse than the best registration point according to a predetermined statistical criterion.
  • Provided herein are methods and systems for image registration from multiple sources. A method for image registration includes rendering a common field of interest that reflects a presence of a plurality of elements, wherein at least one of the elements is a remote element located remotely from another of the elements and updating the common field of interest such that the presence of the at least one of the elements is registered relative to another of the elements.