Loading...
Please wait, while we are loading the content...
Similar Documents
Les contours actifs, une méthode de ségmentation : application à l'imagerie médicale
| Content Provider | Semantic Scholar |
|---|---|
| Author | Rousselle, Jean-Jacques |
| Copyright Year | 2003 |
| Abstract | The segmentation methods of images are numerous ; all have advantages but do not give full satisfaction. All must be adapted according to the application which has to be carried out. Active contours or deformable models made it possible to avoid to chain the contour points but require the adjustment of many parameters. Active contours that we have studied are implemented using a greedy algorithm. First, we propose an alternative based on a minimization by genetic algorithm. Then we propose three approaches to regulate the parameters which control the evolution of contour. Design of experiments makes it possible from a set of images to very quickly choose a set of powerful parameters. The genetic algorithms can be used to optimize the parameters. Finally we propose an original approach where the parameters are local and randomly defined. These autonomous snake allow an evolution of contours without any adjustment. The applications use various images, but in particular medical images. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://helios.mi.parisdescartes.fr/~vincent/siten/Publications/theses/pdf/Rousselle.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
