Sökning: onr:"swepub:oai:DiVA.org:uu-111261" >
Sub-pixel Segmentat...
Sub-pixel Segmentation with the Image Foresting Transform
-
- Malmberg, Filip, 1980- (författare)
- Swedish University of Agricultural Sciences,Sveriges lantbruksuniversitet,Uppsala universitet,Centrum för bildanalys,Datoriserad bildanalys,Centre for Image Analysis
-
- Lindblad, Joakim (författare)
- Swedish University of Agricultural Sciences,Sveriges lantbruksuniversitet,Uppsala universitet,Centrum för bildanalys,,Centre for Image Analysis
-
- Nyström, Ingela (författare)
- Swedish University of Agricultural Sciences,Sveriges lantbruksuniversitet,Uppsala universitet,Centrum för bildanalys,Centre for Image Analysis
-
(creator_code:org_t)
-
- ISBN 9783642102080
- Berlin, Heidelberg : Springer, 2009
- 2009
- Engelska.
-
Ingår i: Proceedings of International Workshop on Combinatorial Image Analysis. - Berlin, Heidelberg : Springer. - 9783642102080 ; 5852, s. 201-211
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
https://res.slu.se/i...
-
visa färre...
Innehållsförteckning
Abstract
Ämnesord
Stäng
No table of content available
- The Image Foresting Transform (IFT) is a framework forimage partitioning, commonly used for interactive segmentation. Givenan image where a subset of the image elements (seed-points) have beenassigned user-defined labels, the IFT completes the labeling by computingminimal cost paths from all image elements to the seed-points. Eachimage element is then given the same label as the closest seed-point. Inits original form, the IFT produces crisp segmentations, i.e., each imageelement is assigned the label of exactly one seed-point. Here, we proposea modified version of the IFT that computes region boundaries withsub-pixel precision by allowing mixed labels at region boundaries. Wedemonstrate that the proposed sub-pixel IFT allows properties of thesegmented object to be measured with higher precision.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Image foresting transform
- Interactive image segmentation
- Sub-pixel precision
- Image analysis
- Bildanalys
- Computerized Image Analysis
- Datoriserad bildanalys
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas