Multi-scale spot segmentation with selection of image scales

Abstract : Detecting spot-like objects of different sizes in images is needed in many applications. Multiple image scales must then be handled for reliable spot segmentation. We define an original criterion based on the a contrario approach and the LoG scale-space framework to automatically select the meaningful scales. We then design a coarse-to-fine multi-scale spot segmentation scheme involving a locally adaptive thresholding across scales, to come up with the final map of segmented spots. We report experimental results on simu-lated and real images of different types, and we demonstrate that our method outperforms other existing methods.
Type de document :
Communication dans un congrès
ICASSP 2017 - The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2017, New Orleans, United States. International Conference on Acoustics, Speech and Signal Processing, pp.5, 〈http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7943262〉. 〈10.1109/ICASSP.2017.7952489〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01561164
Contributeur : Patrick Bouthemy <>
Soumis le : mercredi 12 juillet 2017 - 14:17:46
Dernière modification le : jeudi 13 juillet 2017 - 09:39:25

Identifiants

Collections

Citation

Bertha Mayela Toledo Acosta, Antoine Basset, Patrick Bouthemy, Charles Kervrann. Multi-scale spot segmentation with selection of image scales. ICASSP 2017 - The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2017, New Orleans, United States. International Conference on Acoustics, Speech and Signal Processing, pp.5, 〈http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7943262〉. 〈10.1109/ICASSP.2017.7952489〉. 〈hal-01561164〉

Partager

Métriques

Consultations de la notice

109