liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Adaptive sharpening of multimodal distributions
Heidelberg Collaboratory for Image Processing Heidelberg University Heidelberg, Germany.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).ORCID iD: 0000-0002-6096-3648
BG-2: Plant Sciences Forschungszentrum Jülich 52425, Jülich, Germany.
2015 (English)In: Colour and Visual Computing Symposium (CVCS), 2015 / [ed] Marius Pedersen and Jean-Baptiste Thomas, IEEE , 2015, 1-4 p.Conference paper (Refereed)Text
Abstract [en]

In this work we derive a novel framework rendering measured distributions into approximated distributions of their mean. This is achieved by exploiting constraints imposed by the Gauss-Markov theorem from estimation theory, being valid for mono-modal Gaussian distributions. It formulates the relation between the variance of measured samples and the so-called standard error, being the standard deviation of their mean. However, multi-modal distributions are present in numerous image processing scenarios, e.g. local gray value or color distributions at object edges, or orientation or displacement distributions at occlusion boundaries in motion estimation or stereo. Our method not only aims at estimating the modes of these distributions together with their standard error, but at describing the whole multi-modal distribution. We utilize the method of channel representation, a kind of soft histogram also known as population codes, to represent distributions in a non-parametric, generic fashion. Here we apply the proposed scheme to general mono- and multimodal Gaussian distributions to illustrate its effectiveness and compliance with the Gauss-Markov theorem.

Place, publisher, year, edition, pages
IEEE , 2015. 1-4 p.
Keyword [en]
Probability density function, Signal reconstruction, Signal restoration
National Category
Computer Vision and Robotics (Autonomous Systems) Medical Image Processing
Identifiers
URN: urn:nbn:se:liu:diva-125252DOI: 10.1109/CVCS.2015.7274890ISI: 000380410200013ISBN: 978-1-4799-1765-5OAI: oai:DiVA.org:liu-125252DiVA: diva2:904084
Conference
Colour and Visual Computing Symposium (CVCS), 2015, 25th and 26th August, 2015, Gjøvik, Norway
Available from: 2016-02-18 Created: 2016-02-18 Last updated: 2016-08-19Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Felsberg, Michael
By organisation
Computer VisionFaculty of Science & EngineeringCenter for Medical Image Science and Visualization (CMIV)
Computer Vision and Robotics (Autonomous Systems)Medical Image Processing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 172 hits
ReferencesLink to record
Permanent link

Direct link