English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Segmentation of clusters by template rotation expectation maximization

Svensson, C.-M., Bondoc, K. G., Pohnert, G., & Figge, M. (2017). Segmentation of clusters by template rotation expectation maximization. Computer Vision and Image Understanding, 154, 64-72. doi:10.1016/j.cviu.2016.08.003.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-002C-7F35-A Version Permalink: https://hdl.handle.net/21.11116/0000-0009-3167-C
Genre: Journal Article

Files

show Files
hide Files
:
IMPRS079.pdf (Publisher version), 2MB
 
File Permalink:
-
Name:
IMPRS079.pdf
Description:
-
OA-Status:
Visibility:
Restricted (Max Planck Institute for Chemical Ecology, MJCO; )
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-
:
IMPRS079s1.pdf (Supplementary material), 175KB
 
File Permalink:
-
Name:
IMPRS079s1.pdf
Description:
-
OA-Status:
Visibility:
Restricted (Max Planck Institute for Chemical Ecology, MJCO; )
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Svensson, Carl-Magnus, Author
Bondoc, Karen Grace1, Author           
Pohnert, Georg2, Author           
Figge, MarcThilo, Author
Affiliations:
1IMPRS on Ecological Interactions, MPI for Chemical Ecology, Max Planck Society, ou_421900              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: To solve the task of segmenting clusters of nearly identical objects we here present the template ro- tation expectation maximization (TREM) approach which is based on a generative model. We explore both a general purpose optimization approach for maximizing the log-likelihood and a modification of the standard expectation maximization (EM) algorithm. The general purpose approach is strict template matching, while TREM allows for a more deformable model. As benchmarking we compare TREM with standard EM for a two dimensional Gaussian mixture model (GMM) as well as direct maximization of the log-likelihood using general purpose optimization. We find that the EM based algorithms, TREM and standard GMM, are faster than the general purpose optimizer algorithms without any loss of segmen- tation accuracy. When applying TREM and GMM to a synthetic data set consisting of pairs of almost parallel objects we find that the TREM is better at segmenting those than an unconstrained GMM. Finally we demonstrate that this advantage for TREM over GMM gives significant improvement in segmentation of microscopy images of the motile unicellular alga Seminavis robusta .

Details

show
hide
Language(s):
 Dates: 2016-08-102017-012017
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: Other: IMPRS079
DOI: 10.1016/j.cviu.2016.08.003
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computer Vision and Image Understanding
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Elsevier
Pages: - Volume / Issue: 154 Sequence Number: - Start / End Page: 64 - 72 Identifier: ISSN: 1077-3142
CoNE: https://pure.mpg.de/cone/journals/resource/1077-3142