| Titre : | Segmentation d’images par coopération entre régions contours : Image segmentation by region-contour cooperation. |
| Auteurs : | Aek Djaker Elhadi, Auteur ; Hayat Meddeber, Directeur de thèse |
| Type de document : | texte manuscrit |
| Editeur : | Université mustapha stambouli de Mascara:Faculté des sciences exactes, 2019 |
| ISBN/ISSN/EAN : | SE00701T |
| Format : | 70P. / couv. / . 29 cm. |
| Accompagnement : | disque optique numérique (CD-ROM) |
| Langues: | Français |
| Résumé : |
Active Contour Model is a very efficient technique of image Segmentation. But there are also some drawbacks of this model as any other technique. In this work, watershed segmentation model and GVF snake are introduced and combined to segment images. This proposed method is tested with different images including noisy gray level images. The experimental results show that the final segmentation combining watershed and GVF-snake has a large capture range and is able to move into boundary concavities. . Future work includes by treating the image as a 3D time-dependent surface and selectively deforming this surface based on variational approaches in conjunction with the anisotropic filter. This effectively removes most of the non-significant image extrema, which will remove the added parameter and allow the technique to be used with less tuning and interaction by the user. As we shall add some features to break down the medical images that have multiple object and apply successfully the watershed segmentation combined by the GVF Snake. |
Exemplaires (2)
| Code-barres | Cote | Support | Localisation | Section | Disponibilité |
|---|---|---|---|---|---|
| SE00701T | INF232 | Livre audio | Bibliothèque des Sciences Exactes | 7-Mémoires Master | Libre accès Disponible |
| SE00926T | INF232 | Livre audio | Bibliothèque des Sciences Exactes | 7-Mémoires Master | Libre accès Disponible |
Aucun avis, veuillez vous identifier pour ajouter le vôtre !
Accueil
