English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning an Interest Operator from Eye Movements

Kienzle, W., Franz, M., Wichmann, F., & Schölkopf, B. (2005). Learning an Interest Operator from Eye Movements. Poster presented at International Workshop on Bioinspired Information Processing (BIP 2005), Lübeck, Germany.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-D469-B Version Permalink: http://hdl.handle.net/21.11116/0000-0005-3C8A-D
Genre: Poster

Files

show Files

Creators

show
hide
 Creators:
Kienzle, W1, 2, Author              
Franz, MO1, 2, Author              
Wichmann, FA1, 2, Author              
Schölkopf, B1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: In the computer vision community, so-calledinterest operatorshave become verypopular in recent years. An interest operator is a function that, given an image, re-turns a set ofinterestingpoints that can then be used to e.g. categorize images or todetect objects within images. To our knowledge, all of the widely used interest opera-tors are based onheuristicmeasures of local interestingness (e.g. contrast, second orderstructure, entropy, etc.). While this works well in numerous image processing applica-tions, it seems natural to ask how (if at all) they relate to the visual system’s notion ofinterestingness. This has been explored by e.g. Privitera and Stark [1], who found sig-nificant correlations between fixation points and locations selected by existing heuristicinterest operators. Reinagel and Zador [2] took the opposite approach and reportedthat patches around fixation points tend to have higher contrast and that point-wisecorrelations decay with eccentricity.In this work, we want to find regularities in the image structure around fixationpoints. Thus, we follow the spirit of [2], but instead of verifyingheuristichypothesessuch as ”higher contrast” or ”correlations decay with eccentricity”, our goal is toinferhypothesesfrom the data, using methods from statistical learning. To this end, we traina non-linear classifier on fixated vs. randomly selected image patches, i.e. we learn aninterest operator from human eye movements.At present, we are exploring various ways to deal with two major problems inherentin our approach. First, when a fixation point is recorded a some particular position,the size of the attracting image region around that point is unknown. Second, fixationpositions are subject to ”inaccurate” gaze positioning and measurement noise, which issubstantial compared to pixel sizes. At the workshop, we will present first experimentalresults showing that statistical methods are capable of learning discriminative imagefeatures around fixation points.

Details

show
hide
Language(s):
 Dates: 2005-09
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: 3522
 Degree: -

Event

show
hide
Title: International Workshop on Bioinspired Information Processing (BIP 2005)
Place of Event: Lübeck, Germany
Start-/End Date: 2005-09-20 - 2005-09-22

Legal Case

show

Project information

show

Source 1

show
hide
Title: International Workshop on Bioinspired Information Processing (BIP 2005)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -