Differences between revisions 13 and 14
Revision 13 as of 2015-08-26 13:12:01
Size: 1912
Comment:
Revision 14 as of 2015-09-03 22:03:30
Size: 4513
Comment:
Deletions are marked like this. Additions are marked like this.
Line 6: Line 6:

## page was renamed from Presentations/2015-06-22_HDR
#acl All:read
= Sparse Coding Of Natural Images Using A Prior On Edge Co-Occurrences =

||<tablestyle="width: 35%; float: right; margin-left:20px; margin-right:20px; border-style: 0px; font-size: 8pt;"> [[Publications/PerrinetBednar15|{{attachment:Figures/PerrinetBednar15/FigureModel/figure_model.jpg|Architecture of the model|width=100%,align="left"}}]] <<BR>> ''[[Figures/PerrinetBednar15/FigureModel| Figure 1]]'': '''Edge co-occurrences''' ''(A)'' An example image with the list of extracted edges overlaid. Each edge is represented by a red line segment which represents its position (center of segment), orientation, and scale (length of segment). . ''(B)'' The relationship between a reference edge "A" and another edge "B" can be quantified in terms of the difference between their orientations, ratio of scale, distance between their centers, and difference of azimuth. This is used to compute the chevron map in [[Figures/PerrinetBednar15/FigureChevrons| Figure 2]]. Go back to [[Publications/PerrinetBednar15|manuscript page]]. ||

  Titre:: Sparse Coding Of Natural Images Using A Prior On Edge Co-Occurrences

  Résumé:: Oriented edges in images commonly occur in co-linear and co-circular
  arrangements, obeying the ``good continuation law'' of Gestalt
  psychology. The human visual system appears to exploit this
  property of images, with contour detection, line completion, and
  grouping performance well predicted by such an ``association field''
  between edge elements \citep{Field93,Geisler01}. In this paper, we
  show that an association field of this type can be used to enhance
  the sparse representation of natural images. First, we define the
  SparseLets framework as an efficient representation of images based
  on a discrete wavelet transform. Second, we extract second-order
  information about edge co-occurrences from a set of images of natural
  scenes. Finally, we incorporate this prior information into our
  framework and show that it allows for the extraction of features
  relevant to natural scenes, like a round shape. This novel approach
  points the way to practical computer vision algorithms with
  human-like performance.

 Slides:: [[attachment:perrinet15eusipco_talk.pdf|slides]], [[attachment:perrinet15eusipco_handout.pdf|slides with notes]]

 Code:: For more information on Matching Pursuit on natural images, follow [[http://blog.invibe.net/posts/2015-05-22-a-hitchhiker-guide-to-matching-pursuit.html|The hitchhiker guide to Matching Pursuit]].

Sparse coding of natural images using a prior on edge co-occurences

#acl All:read

Sparse Coding Of Natural Images Using A Prior On Edge Co-Occurrences

Architecture of the model
Figure 1: Edge co-occurrences (A) An example image with the list of extracted edges overlaid. Each edge is represented by a red line segment which represents its position (center of segment), orientation, and scale (length of segment). . (B) The relationship between a reference edge "A" and another edge "B" can be quantified in terms of the difference between their orientations, ratio of scale, distance between their centers, and difference of azimuth. This is used to compute the chevron map in Figure 2. Go back to manuscript page.

Titre
Sparse Coding Of Natural Images Using A Prior On Edge Co-Occurrences
Résumé
Oriented edges in images commonly occur in co-linear and co-circular

arrangements, obeying the good continuation law of Gestalt psychology. The human visual system appears to exploit this property of images, with contour detection, line completion, and grouping performance well predicted by such an association field between edge elements \citep{Field93,Geisler01}. In this paper, we show that an association field of this type can be used to enhance the sparse representation of natural images. First, we define the SparseLets framework as an efficient representation of images based on a discrete wavelet transform. Second, we extract second-order information about edge co-occurrences from a set of images of natural scenes. Finally, we incorporate this prior information into our framework and show that it allows for the extraction of features relevant to natural scenes, like a round shape. This novel approach points the way to practical computer vision algorithms with human-like performance.

Slides

slides, slides with notes

Code

For more information on Matching Pursuit on natural images, follow The hitchhiker guide to Matching Pursuit.

reference

  • Laurent U. Perrinet, James A. Bednar. Sparse Coding Of Natural Images Using A Prior On Edge Co-Occurences. In European Signal Processing Conference 2015 (EUSIPCO 2015), Nice, France, 2015 abstract.


All material (c) L. Perrinet. Please check the copyright notice.


This work was supported by European Union project Number FP7-269921, "BrainScales".
BrainScaleS logoFET logoFP7 logoEU logo


TagYear15 TagBrainScales TagPublicationsArticles TagTalks

welcome: please sign in