Abstract/Details

Image classification with bags of local features


2006 2006

Other formats: Order a copy

Abstract (summary)

Many classification techniques expect class instances to be represented as feature vectors, i.e. points in a feature space. In computer vision classification problems, it is often possible to generate an informative feature vector representation of an image, for example using global texture or shape descriptors. However, in other cases, it may be beneficial to treat images as variable size unordered sets or bags of features, in which each feature represents a localized salient image structure or patch. These local features do not require a segmentation, and can be useful for object recognition in the presence of occlusion and clutter.

The local features are often used to find point correspondences between images to be later used for 3D reconstruction, object recognition, detection, or image retrieval. However, there are many cases when exact correspondences are difficult or even impossible to compute. Furthermore, point correspondences may not be necessary, unless one is interested in recovering the 3D shape of an object. If the correspondences are not computed, then this representation indeed constitutes an unordered set of local features.

In this dissertation we present methods for object class recognition using bags of features without relying on point correspondences. We also show that using bags of features and more traditional feature vector representation of images together can improve classification accuracy. We then propose and evaluate several methods of combining the two representations. The proposed techniques are applied to a challenging marine science domain.

Indexing (details)


Subject
Computer science
Classification
0984: Computer science
Identifier / keyword
Applied sciences, Computer vision, Image classification, Local features, Machine learning, Object categorization
Title
Image classification with bags of local features
Author
Lisin, Dimitri A.
Number of pages
113
Publication year
2006
Degree date
2006
School code
0118
Source
DAI-B 67/04, Dissertation Abstracts International
Place of publication
Ann Arbor
Country of publication
United States
ISBN
9780542656811, 0542656817
Advisor
Learned-Miller, Erik G.
University/institution
University of Massachusetts Amherst
University location
United States -- Massachusetts
Degree
Ph.D.
Source type
Dissertations & Theses
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
3215776
ProQuest document ID
305306298
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Document URL
http://search.proquest.com/docview/305306298
Access the complete full text

You can get the full text of this document if it is part of your institution's ProQuest subscription.

Try one of the following:

  • Connect to ProQuest through your library network and search for the document from there.
  • Request the document from your library.
  • Go to the ProQuest login page and enter a ProQuest or My Research username / password.