Paper Info
Title
Hierarchical region-based representation for segmentation and filtering with depth in single images
Abstract
This paper presents an algorithm for tree-based representation of single images and its applications to segmentation and filtering with depth. In a our recent work, we have addressed the problem of segmentation with depth by incorporating depth ordering information into a region merging algorithm and by reasoning about depth relations through a graph model. In this paper, we extend this previous work giving a two-fold contribution. First, we propose to model each pixel statistically by its probability distribution instead of deterministically by its color value. Second, we propose a depth-oriented filter, which allows to remove foreground regions and to replace them with a plausible background. Experimental results are satisfactory.
Year
DOI
Venue
2009
10.1109/ICIP.2009.5414079
Image Processing
Keywords
Field
DocType
plausible background,depth-oriented filter,hierarchical region-based representation,graph model,depth relation,color value,recent work,previous work,single image,probability distribution,foreground region,filtering,statistical distributions,merging,indexing terms,image segmentation,pixel
Computer vision,Pattern recognition,Range segmentation,Segmentation,Computer science,Filter (signal processing),Image segmentation,Probability distribution,Pixel,Artificial intelligence,Lightness,Merge (version control)
Conference
ISSN
ISBN
Citations 
1522-4880 E-ISBN : 978-1-4244-5655-0
978-1-4244-5655-0
12
PageRank 
References 
Authors
1.04
12
2
Name
Order
Citations
PageRank
Mariella Dimiccoli18918.29
Philippe Salembier260387.65