Incorporating labeled features into image classification using generalized expectation Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/v118rh329

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been leveraged in text classification, through the incorporation of labeled features. Labeling features provides a much more informative form of feedback than existing vision feedback systems like active learning and relevance feedback. In this paper, I adapt the Generalized Expectation Criteria to incorporate labeled features into the more complex CRF model used for images. Experiments are performed using oracle selected features as a first step towards showing the potential benefits of this kind of user feedback for image classification.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2013-12-30T16:52:19Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) MooreTravisW2013.pdf: 346331 bytes, checksum: c4fcd5139936530b2092b7c3bf63e030 (MD5)
  • description.provenance : Made available in DSpace on 2013-12-30T22:10:21Z (GMT). No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) MooreTravisW2013.pdf: 346331 bytes, checksum: c4fcd5139936530b2092b7c3bf63e030 (MD5) Previous issue date: 2013-11-21
  • description.provenance : Submitted by Travis Moore (moortrav@onid.orst.edu) on 2013-12-27T20:13:03Z No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) MooreTravisW2013.pdf: 346331 bytes, checksum: c4fcd5139936530b2092b7c3bf63e030 (MD5)
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2013-12-30T22:10:21Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) MooreTravisW2013.pdf: 346331 bytes, checksum: c4fcd5139936530b2092b7c3bf63e030 (MD5)

Relationships

In Administrative Set:
Last modified: 08/14/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items