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

Title: A Locally Adapting Technique for Edge Detection using Image Segmentation

Journal Article · · SIAM Journal on Scientific Computing
DOI:https://doi.org/10.1137/17M1155363· OSTI ID:1512357
 [1];  [2];  [1];  [3]
  1. Nevada National Security Site, Las Vegas, NV (United States). Signal Processing and Applied Mathematics
  2. Univ. of Alabama, Huntsville, AL (United States). Dept. of Mathematical Sciences
  3. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Dept. of Physical Chemistry, Inst. for Soldier Nanotechnology
+ Show Author Affiliations

Rapid growth in the field of quantitative digital image analysis is paving the way for scientific researchers to make precise measurements about objects in an image. To compute quantities from an image such as the density of compressed materials or the velocity of a shockwave, object boundaries must first be determined. Images containing regions that each have a spatial trend in intensity are of particular interest here. For edge detection, we present a supervised, statistical image segmentation method that incorporates spatial information to locate boundaries between regions with overlapping intensity histograms, specifically for images where the regions are known but precise boundary locations are unknown. The segmentation of a pixel is determined by comparing its intensity to distributions from nearby pixel intensities, and a gradient of the segmented image indicates edge locations. Because of the statistical nature of the algorithm, we use maximum likelihood estimation to quantify uncertainty about each boundary. We demonstrate the success of this algorithm at locating boundaries and providing uncertainty bands on a radiograph of a multicomponent cylinder and on an optical image of a laser-induced shockwave.

Research Organization:
Nevada National Security Site, Las Vegas, NV (United States).
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC52-06NA25946; N00014-16-1-2090; N00014-15-1-2694
OSTI ID:
1512357
Report Number(s):
DOE/NV/-25946-3282
Journal Information:
SIAM Journal on Scientific Computing, Vol. 40, Issue 4; ISSN 1064-8275
Publisher:
SIAMCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 8 works
Citation information provided by
Web of Science

References (17)

Impact of Semiautomated versus Manual Image Segmentation Errors on Myocardial Strain Calculation by Magnetic Resonance Tagging journal January 1994
Symmetry of projection in the quantitative analysis of mammographic images journal January 1996
A Neural Network Method for Efficient Vegetation Mapping journal December 1999
Classifier Technology and the Illusion of Progress journal February 2006
An Approach Toward Fast Gradient-Based Image Segmentation journal September 2015
Bayesian Abel Inversion in Quantitative X-Ray Radiography journal January 2016
Mapping per-pixel predicted accuracy of classified remote sensing images journal March 2017
On the accuracy of the Sobel edge detector journal February 1983
Real-time implementation of order-statistics-based directional filters journal February 2009
Segmentation and Image Analysis of Abnormal Lungs at CT: Current Approaches, Challenges, and Future Trends journal July 2015
Estimating pixel-scale land cover classification confidence using nonparametric machine learning methods journal January 2001
Edge-Detection Method for Image Processing Based on Generalized Type-2 Fuzzy Logic journal December 2014
Visualization and Quantification of Vascular Structure of Fruit Using Magnetic Resonance Microimaging journal April 2014
A review on image segmentation techniques journal September 1993
Direct Visualization of Laser-Driven Focusing Shock Waves journal May 2011
Minimizing Manual Image Segmentation Turn-Around Time for Neuronal Reconstruction by Embracing Uncertainty journal September 2012
Use of normalized difference built-up index in automatically mapping urban areas from TM imagery journal January 2003

Cited By (1)

Advances on pancreas segmentation: a review journal December 2019

Figures / Tables (13)

Figure-2.1(p. 4)figure Figure-2.1
Fig. 2.2(p. 5)figure Fig. 2.2
Algorithm 1(p. 6)figure Algorithm 1
Fig. 3.1(p. 7)figure Fig. 3.1
Fig. 4.1(p. 9)figure Fig. 4.1
Fig. 4.2(p. 10)figure Fig. 4.2
Fig. 4.3(p. 11)figure Fig. 4.3
Fig. 4.4(p. 12)figure Fig. 4.4
Fig. 4.5(p. 13)figure Fig. 4.5
Fig. 4.6(p. 14)figure Fig. 4.6
Fig. 4.7(p. 15)figure Fig. 4.7
Fig. 4.8(p. 16)figure Fig. 4.8
Fig. 4.9(p. 16)figure Fig. 4.9

Similar Records

Machine learning to analyze images of shocked materials for precise and accurate measurements
Journal Article · Thu Sep 14 00:00:00 EDT 2017 · Journal of Applied Physics · OSTI ID:1512357
+5 more
A Locally Adaptive Method for Boundary Detection
Conference · Wed Mar 07 00:00:00 EST 2018 · OSTI ID:1512357
+1 more
ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather
Journal Article · Fri Jan 08 00:00:00 EST 2021 · Geoscientific Model Development (Online) · OSTI ID:1512357
+19 more

Related Subjects

97 MATHEMATICS AND COMPUTING
edge detection
image processing
statistical segmentation
discriminant analysis
maximum likelihood estimation