Title
Extracting Salient Contour Groups From Cluttered Solar Images Via Markov Random Fields
Abstract
We propose a method to extract salient contour group from cluttered regions using Markov Random Fields. Our technique delineates smooth, long, and elliptical curves out of clutter. To extract salient curves, we use the following perceptual rules: smoothness, proximity, co-circularity, co-elliptic, and length. Our method consists of following steps: obtaining individual smooth contours along their saliency measures; starting from the most salient contour search for possible grouping options for each contour; continuing the grouping until an optimum solution is reached. We introduce circularity and saliency measures for open curves. We applied our method to discern coronal loops from cluttered solar images, and were able to successfully obtain the entire set of desired coronal loops while eliminating any cluttered background.
Year
DOI
Venue
2011
10.1109/ICIP.2011.6116260
2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Keywords
Field
DocType
Contour Grouping, Salient Contours, Markov Random Fields, Solar Images, Saliency Measure, Circularity Measure
Computer vision,Markov process,Random field,Pattern recognition,Clutter,Salience (neuroscience),Computer science,Markov chain,Feature extraction,Image segmentation,Artificial intelligence,Salient
Conference
ISSN
Citations 
PageRank 
1522-4880
2
0.37
References 
Authors
8
2
Name
Order
Citations
PageRank
Nurcan Durak1435.33
Olfa Nasraoui21515164.53