Change search
ReferencesLink to record
Permanent link

Direct link
Unbiased decoding of biologically motivated visual feature descriptors
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-6096-3648
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. (Computer Graphics and Image Processing)ORCID iD: 0000-0001-7557-4904
2015 (English)In: Frontiers in Robotics and AI, ISSN 2296-9144, Vol. 2, no 20Article in journal (Refereed) Published
Abstract [en]

Visual feature descriptors are essential elements in most computer and robot vision systems. They typically lead to an abstraction of the input data, images, or video, for further processing, such as clustering and machine learning. In clustering applications, the cluster center represents the prototypical descriptor of the cluster and estimates the corresponding signal value, such as color value or dominating flow orientation, by decoding the prototypical descriptor. Machine learning applications determine the relevance of respective descriptors and a visualization of the corresponding decoded information is very useful for the analysis of the learning algorithm. Thus decoding of feature descriptors is a relevant problem, frequently addressed in recent work. Also, the human brain represents sensorimotor information at a suitable abstraction level through varying activation of neuron populations. In previous work, computational models have been derived that agree with findings of neurophysiological experiments on the represen-tation of visual information by decoding the underlying signals. However, the represented variables have a bias toward centers or boundaries of the tuning curves. Despite the fact that feature descriptors in computer vision are motivated from neuroscience, the respec-tive decoding methods have been derived largely independent. From first principles, we derive unbiased decoding schemes for biologically motivated feature descriptors with a minimum amount of redundancy and suitable invariance properties. These descriptors establish a non-parametric density estimation of the underlying stochastic process with a particular algebraic structure. Based on the resulting algebraic constraints, we show formally how the decoding problem is formulated as an unbiased maximum likelihood estimator and we derive a recurrent inverse diffusion scheme to infer the dominating mode of the distribution. These methods are evaluated in experiments, where stationary points and bias from noisy image data are compared to existing methods.

Place, publisher, year, edition, pages
Lausanne, Switzerland: Frontiers Research Foundation , 2015. Vol. 2, no 20
Keyword [en]
feature descriptors, population codes, channel representations, decoding, estimation, visualization
National Category
Computer Vision and Robotics (Autonomous Systems)
URN: urn:nbn:se:liu:diva-120973DOI: 10.3389/frobt.2015.00020OAI: diva2:850261
Available from: 2015-09-01 Created: 2015-09-01 Last updated: 2016-08-31Bibliographically approved

Open Access in DiVA

fulltext(8807 kB)174 downloads
File information
File name FULLTEXT01.pdfFile size 8807 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Felsberg, MichaelÖfjäll, KristofferLenz, Reiner
By organisation
Computer VisionFaculty of Science & EngineeringMedia and Information Technology
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 174 downloads
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: 1533 hits
ReferencesLink to record
Permanent link

Direct link