Perceptual Annotation: Measuring Human Vision to Improve Computer Vision

DSpace/Manakin Repository

Perceptual Annotation: Measuring Human Vision to Improve Computer Vision

Citable link to this page

 

 
Title: Perceptual Annotation: Measuring Human Vision to Improve Computer Vision
Author: Scheirer, Walter Jerome; Anthony, Samuel English; Nakayama, Ken; Cox, David Daniel

Note: Order does not necessarily reflect citation order of authors.

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.
Full Text & Related Files:
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.
Published Version: doi:10.1109/tpami.2013.2297711
Other Sources: http://www.coxlab.org/pdfs/2014_scheirer_tpami.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#OAP
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:12111387
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)

 
 

Search DASH


Advanced Search
 
 

Submitters