Skip to Main content Skip to Navigation
Conference papers

A Concentration-Based Adaptive Approach to Region Merging of Optimal Time and Space Complexities

Christophe Fiorio 1 Andre Mas 2
1 ICAR - Image & Interaction
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : In this paper, we investigate image segmentation as a statistical and computa- tional problem. The observed image is sampled from a theoretical, unknown image, in which pixels are represented by distributions. Our objective is to approximate as best as possible the region segmentation in the ideal image, where each region has pixels with identical expectations, but adjacent regions have different pixel’s expectations. From that model, a concentration-based statistical test for deciding region merging is built, limiting the risk of wrong merges. The analysis is carried out without any assumption on the distribu- tions: we avoid in particular the classics of variance analysis, normality and homocedasticity. A practical approximation of the test is given, of constant time and space computation, which leads in turn to a segmentation algorithm of optimal complexity, easy to implement. Some experiments on various types of images shed light on the quality of the segmentations obtained.
Complete list of metadatas

Cited literature [6 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01168062
Contributor : Christophe Fiorio <>
Submitted on : Thursday, June 25, 2015 - 11:17:34 AM
Last modification on : Friday, December 7, 2018 - 11:59:09 AM
Document(s) archivé(s) le : Friday, October 9, 2015 - 5:25:35 PM

File

FioNocBMVC00_A Concentration-B...
Files produced by the author(s)

Identifiers

Citation

Christophe Fiorio, Andre Mas. A Concentration-Based Adaptive Approach to Region Merging of Optimal Time and Space Complexities . Proceedings of the British Machine Vision Conference, Sep 2000, Bristol, United Kingdom. ⟨10.5244/C.14.78⟩. ⟨lirmm-01168062⟩

Share

Metrics

Record views

178

Files downloads

386