Modèles statistiques avancés pour la segmentation non supervisée des images dégradées de l'iris

Autor: Yahiaoui, Meriem

L'iris est considérée comme une des modalités les plus robustes et les plus performantes en biométrie à cause de ses faibles taux d'erreurs. Ces performances ont été observées dans des situations contrôlées, qui imposent des contraintes lor

Externí odkaz: http://www.theses.fr/2017SACLL006/document

Advanced statistical models for unsupervised segmentation of degraded iris images

Autor: Yahiaoui, Meriem

Publikováno v: Traitement du signal et de l'image [eess.SP]. Université Paris-Saclay, 2017. Français. ⟨NNT : 2017SACLL006⟩

Iris is considered as one of the most robust and efficient modalities in biometrics because of its low error rates. These performances were observed in controlled situations, which impose constraints during the acquisition in order to have good quali

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5c64a90d74575c81156aff4478880816
https://theses.hal.science/tel-01591556

Towards a logic-based method to infer provenance-aware molecular networks

Autor: Aslaoui-Errafi, Zahira, Cohen-Boulakia, Sarah, Froidevaux, Christine, Gloaguen, Pauline, Poupon, Anne, Rougny, Adrien, Yahiaoui, Meriem

Publikováno v: Proc. of the 1st ECML/PKDD International workshop on Learning and Discovery in Symbolic Systems Biology (LDSSB)
Proc. of the 1st ECML/PKDD International workshop on Learning and Discovery in Symbolic Systems Biology (LDSSB), Sep 2012, Bristol, United Kingdom. pp.103-110
1. ECML/PKDD International workshop on Learning and Discovery in Symbolic Systems Biology (LDSSB)
1. ECML/PKDD International workshop on Learning and Discovery in Symbolic Systems Biology (LDSSB), European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML/PKDD). Bristol, GBR., Sep 2012, Bristol, United Kingdom

International audience; Providing techniques to automatically infer molecular networks is particularly important to understand complex relationships between biological objects. We present a logic-based method to infer such networks and show how it al

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c3e94df1d385521f73983c0736987e9c
https://hal.inria.fr/hal-00748041/file/SignPathways_final.pdf