Show simple item record

dc.contributor.advisorMcCane, Brendan
dc.contributor.advisorBenuskova, Lubica
dc.contributor.authorFu, Jie
dc.date.available2012-07-18T04:06:10Z
dc.date.copyright2012
dc.identifier.citationFu, J. (2012). Learning Hierarchical Sparse Filters for Feature Matching (Thesis, Master of Science). University of Otago. Retrieved from http://hdl.handle.net/10523/2360en
dc.identifier.urihttp://hdl.handle.net/10523/2360
dc.description.abstractA common problem in computer vision is to match corresponding points between images. The success of computer vision has usually relied on having good feature representations, which are usually hand-crafted and thus require huge amounts of prior knowledge and human labor. To the best of my knowledge, feature learning algorithms have not been used for feature matching in the literature. In this thesis, I will present how to use feature learning algorithms to build useful feature representations from aerial images in a biologically-inspired and unsupervised manner. These learned feature representations can then be used to do feature matching tasks. Specifically, I will present two algorithms, Sparse Filtering and convolutional Networks for generating hierarchical representations, in which the information from the lower levels is grouped to establish complex features. These complex and hierarchical representations often lead to performance approaching highly hand-designed computer vision algorithms in feature matching tasks.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherUniversity of Otago
dc.rightsAll items in OUR Archive are provided for private study and research purposes and are protected by copyright with all rights reserved unless otherwise indicated.
dc.subjectFeature Learning
dc.subjectFeature Matching
dc.subjectComputer Vision
dc.titleLearning Hierarchical Sparse Filters for Feature Matching
dc.typeThesis
dc.date.updated2012-07-18T03:44:30Z
dc.language.rfc3066en
thesis.degree.disciplineComputer Science
thesis.degree.nameMaster of Science
thesis.degree.grantorUniversity of Otago
thesis.degree.levelMasters
otago.openaccessOpen
 Find in your library

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record