Difference between revisions of "Publications/xu.15.prl"
From LRDE
Yongchao Xu (talk | contribs) |
Yongchao Xu (talk | contribs) (Blanked the page) |
||
| (11 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | {{Publication |
||
| − | | published = false |
||
| − | | date = 2015-09-16 |
||
| − | | authors = Yongchao Xu, Thierry Géraud, Laurent Najman |
||
| − | | title = Hierarchical image simplification and segmentation based on Mumford-Shah-salient levelline selection |
||
| − | | journal = Pattern Recognition Letters |
||
| − | | project = Image |
||
| − | | abstract = Hierarchies are popular representations for image simplification and segmentation thanks to their multiscale structures. An example is the tree of shapes. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the Mumford-Shah functional. In this paper, we propose an efficient approach of hierarchical image simplification and segmentation based on the minimization of some energy functional. This method conforms to the current trends that are to find hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and equivalent image representation. Whereas, the construction of the input hierarchy for the classical approaches is an interesting problem in itself. Simply put, we compute an attribute function for each level line that characterizes its resistance under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map using shape-space filtering framework. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the good performance of our method. |
||
| − | | note = Submitted |
||
| − | | urllrde = 201509-PRL |
||
| − | | lrdeinc = Publications/xu.15.prl.inc |
||
| − | | lrdekeywords = Image |
||
| − | | optlrdepaper = https://www.lrde.epita.fr/dload/papers/xu.2015.prl.pdf |
||
| − | | type = article |
||
| − | | id = xu.2015.prl |
||
| − | | bibtex = |
||
| − | @Article<nowiki>{</nowiki> xu.2015.prl, |
||
| − | author = <nowiki>{</nowiki>Yongchao Xu and Thierry G\'eraud<nowiki> and Laurent Najman<nowiki>}</nowiki>, |
||
| − | title = <nowiki>{</nowiki>Hierarchical image simplification and segmentation based on Mumford-Shah-salient levelline selection<nowiki>}</nowiki>, |
||
| − | journal = <nowiki>{</nowiki>Pattern Recognition Letters<nowiki>}</nowiki>, |
||
| − | year = 2015, |
||
| − | project = <nowiki>{</nowiki>Image<nowiki>}</nowiki>, |
||
| − | abstract = <nowiki>{</nowiki>Hierarchies are popular representations for image simplification and segmentation thanks to their multiscale structures. An example is the tree of shapes. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the Mumford-Shah functional. In this paper, we propose an efficient approach of hierarchical image simplification and segmentation based on the minimization of some energy functional. This method conforms to the current trends that are to find hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and equivalent image representation. Whereas, the construction of the input hierarchy for the classical approaches is an interesting problem in itself. Simply put, we compute an attribute function for each level line that characterizes its resistance under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map using shape-space filtering framework. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the good performance of our method.<nowiki>}</nowiki>, |
||
| − | note = <nowiki>{</nowiki>Submitted<nowiki>}</nowiki>, |
||
| − | optlrdepaper = <nowiki>{</nowiki>https://www.lrde.epita.fr/dload/papers/xu.2015.prl.pdf<nowiki>}</nowiki> |
||
| − | |||
| − | <nowiki>}</nowiki> |
||
| − | |||
| − | }} |
||