DMCA
Tuner: Principled parameter finding for image segmentation algorithms using visual response surface exploration (2011)
| Venue: | IEEE Transactions on Visualization and Computer Graphics |
| Citations: | 22 - 6 self |
BibTeX
@INPROCEEDINGS{Torsney-weir11tuner:principled,
author = {Thomas Torsney-weir and Student Member and Ahmed Saad and Senior Member and Britta Weber and Hans-christian Hege and Jean-marc Verbavatz and Steven Bergner and Student Member},
title = {Tuner: Principled parameter finding for image segmentation algorithms using visual response surface exploration},
booktitle = {IEEE Transactions on Visualization and Computer Graphics},
year = {2011},
pages = {1892--1901}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—In this paper we address the difficult problem of parameter-finding in image segmentation. We replace a tedious manual process that is often based on guess-work and luck by a principled approach that systematically explores the parameter space. Our core idea is the following two-stage technique: We start with a sparse sampling of the parameter space and apply a statistical model to estimate the response of the segmentation algorithm. The statistical model incorporates a model of uncertainty of the estimation which we use in conjunction with the actual estimate in (visually) guiding the user towards areas that need refinement by placing additional sample points. In the second stage the user navigates through the parameter space in order to determine areas where the response value (goodness of segmentation) is high. In our exploration we rely on existing ground-truth images in order to evaluate the ”goodness ” of an image segmentation technique. We evaluate its usefulness by demonstrating this technique on two image segmentation algorithms: a three parameter model to detect microtubules in electron tomograms and an eight parameter model to identify functional regions in dynamic Positron Emission Tomography scans. Index Terms—Parameter exploration, Image segmentation, Gaussian Process Model. 1
Keyphrases
image segmentation visual response surface exploration parameter space parameter model statistical model electron tomograms tedious manual process ground-truth image response value image segmentation algorithm image segmentation technique index term parameter exploration difficult problem segmentation algorithm user towards area additional sample point functional region gaussian process model actual estimate core idea following two-stage technique second stage dynamic positron emission tomography scan principled approach sparse sampling
