Computational object recognition: a biologically motivated approach

DC FieldValueLanguage
dc.contributor.authorKietzmann, Tim C.
dc.contributor.authorLange, Sascha
dc.contributor.authorRiedmiller, Martin
dc.date.accessioned2021-12-23T16:00:12Z-
dc.date.available2021-12-23T16:00:12Z-
dc.date.issued2009
dc.identifier.issn03401200
dc.identifier.urihttps://osnascholar.ub.uni-osnabrueck.de/handle/unios/4285-
dc.description.abstractWe propose a conceptual framework for artificial object recognition systems based on findings from neurophysiological and neuropsychological research on the visual system in primate cortex. We identify some essential questions, which have to be addressed in the course of designing object recognition systems. As answers, we review some major aspects of biological object recognition, which are then translated into the technical field of computer vision. The key suggestions are the use of incremental and view-based approaches together with the ability of online feature selection and the interconnection of object-views to form an overall object representation. The effectiveness of the computational approach is estimated by testing a possible realization in various tasks and conditions explicitly designed to allow for a direct comparison with the biological counterpart. The results exhibit excellent performance with regard to recognition accuracy, the creation of sparse models and the selection of appropriate features.
dc.description.sponsorship[DFG-SPP1125]; This work was partly granted by DFG-SPP1125. We would like to thank the anonymous reviewers for the helpful comments, suggestions and discussions.
dc.language.isoen
dc.publisherSPRINGER
dc.relation.ispartofBIOLOGICAL CYBERNETICS
dc.subjectBiologically inspired computer vision
dc.subjectComputer Science
dc.subjectComputer Science, Cybernetics
dc.subjectFACES
dc.subjectFeature selection
dc.subjectFEATURES
dc.subjectIncremental learning
dc.subjectINFERIOR TEMPORAL CORTEX
dc.subjectINFEROTEMPORAL CORTEX
dc.subjectLONG-TERM-MEMORY
dc.subjectNEURONS
dc.subjectNeurosciences
dc.subjectNeurosciences & Neurology
dc.subjectObject recognition
dc.subjectORGANIZATION
dc.subjectREPRESENTATION
dc.subjectSELECTIVITY
dc.subjectSHAPE
dc.subjectView-based object representations
dc.titleComputational object recognition: a biologically motivated approach
dc.typejournal article
dc.identifier.doi10.1007/s00422-008-0281-6
dc.identifier.isiISI:000263486700007
dc.description.volume100
dc.description.issue1
dc.description.startpage59
dc.description.endpage79
dc.contributor.orcid0000-0001-8076-6062
dc.contributor.researcheridAAA-5771-2019
dc.identifier.eissn14320770
dc.publisher.placeONE NEW YORK PLAZA, SUITE 4600, NEW YORK, NY, UNITED STATES
dcterms.isPartOf.abbreviationBiol. Cybern.
Show simple item record

Google ScholarTM

Check

Altmetric