Multi-scale spot segmentation with selection of image scales - Archive ouverte HAL Access content directly
Conference Papers Year :

Multi-scale spot segmentation with selection of image scales

(1) , (1) , (1) , (1)
1

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.
Not file

Dates and versions

hal-01561164 , version 1 (12-07-2017)

Identifiers

Cite

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. pp.5, ⟨10.1109/ICASSP.2017.7952489⟩. ⟨hal-01561164⟩

Collections

INRIA INRIA2
89 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More