Perceptual Annotation: Measuring Human Vision to Improve Computer Vision

DSpace/Manakin Repository

Perceptual Annotation: Measuring Human Vision to Improve Computer Vision

Show simple item record

dc.contributor.author Scheirer, Walter Jerome
dc.contributor.author Anthony, Samuel English
dc.contributor.author Nakayama, Ken
dc.contributor.author Cox, David Daniel
dc.date.accessioned 2014-04-25T16:46:06Z
dc.date.issued 2014
dc.identifier.citation Scheirer, Walter, Samuel Anthony, Ken Nakayama, and David Cox. 2014. Perceptual annotation: measuring human vision to improve computer vision. IEEE Transactions on Pattern Analysis and Machine Intelligence PP(99): 1–8. en_US
dc.identifier.issn 0162-8828 en_US
dc.identifier.uri http://nrs.harvard.edu/urn-3:HUL.InstRepos:12111387
dc.description.abstract For many problems in computer vision, human learners are considerably better than machines. Humans possess highly accurate internal recognition and learning mechanisms that are not yet understood, and they frequently have access to more extensive training data through a lifetime of unbiased experience with the visual world. We propose to use visual psychophysics to directly leverage the abilities of human subjects to build better machine learning systems. First, we use an advanced online psychometric testing platform to make new kinds of annotation data available for learning. Second, we develop a technique for harnessing these new kinds of information – “perceptual annotations” – for support vector machines. A key intuition for this approach is that while it may remain infeasible to dramatically increase the amount of data and high-quality labels available for the training of a given system, measuring the exemplar-by-exemplar difficulty and pattern of errors of human annotators can provide important information for regularizing the solution of the system at hand. A case study for the problem face detection demonstrates that this approach yields state-ofthe- art results on the challenging FDDB data set. en_US
dc.description.sponsorship Engineering and Applied Sciences en_US
dc.description.sponsorship Molecular and Cellular Biology en_US
dc.language.iso en_US en_US
dc.publisher Institute of Electrical & Electronics Engineers (IEEE) en_US
dc.relation.isversionof doi:10.1109/tpami.2013.2297711 en_US
dc.relation.hasversion http://www.coxlab.org/pdfs/2014_scheirer_tpami.pdf en_US
dash.license OAP
dc.subject machine learning en_US
dc.subject citizen science en_US
dc.subject face detection en_US
dc.subject psychology en_US
dc.subject psychometrics en_US
dc.subject psychophysics en_US
dc.subject regularization en_US
dc.subject support vector machines en_US
dc.subject visual recognition en_US
dc.title Perceptual Annotation: Measuring Human Vision to Improve Computer Vision en_US
dc.type Journal Article en_US
dc.description.version Accepted Manuscript en_US
dc.relation.journal IEEE Transactions on Pattern Analysis and Machine Intelligence en_US
dash.depositing.author Cox, David Daniel
dc.date.available 2014-04-25T16:46:06Z

Files in this item

Files Size Format View
Scheirer_PerceptualAnnotation.pdf 2.101Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

 
 

Search DASH


Advanced Search
 
 

Submitters