Show simple item record

dc.rights.licenseRestricted to current Rensselaer faculty, staff and students. Access inquiries may be directed to the Rensselaer Libraries.
dc.contributorCutler, Barbara M.
dc.contributorGray, Wayne D., 1950-
dc.contributorMagdon-Ismail, Malik
dc.contributor.authorHan, Tianning Steven
dc.date.accessioned2021-11-03T08:09:38Z
dc.date.available2021-11-03T08:09:38Z
dc.date.created2014-09-11T10:31:28Z
dc.date.issued2014-05
dc.identifier.urihttps://hdl.handle.net/20.500.13015/1107
dc.descriptionMay 2014
dc.descriptionSchool of Science
dc.description.abstractContributions of this thesis include an efficient implementation of OBVIS and SDA, guidelines for setting layer sizes in SDA from an implementation efficiency perspective, an analysis of the strength and weakness of OBVIS and SDA, and, finally, a system design that combines OBVIS and SDA to learn a good feature generation process using ground truth data from human studies.
dc.description.abstractThe complex nature of visual similarity makes it extremely difficult to hand code a set of good features that incorporate all of the important aspects for all images. This thesis work shows that machine learning techniques can be used to generate statistically optimal low dimensional features that work well with calculating similarity using Euclidean distance between feature representation of images. Specifically, a Stacked Denoising Autoencoder (SDA) was used to train a deep neural network to learn a set of important features from the Amsterdam Library of Object Images. Theses features generated by SDA were compared with those generated using OBVIS, a feature generation algorithm developed specifically for human visual similarity comparison. The results indicated that features learned by SDA, a generic representation learning approach, outperformed the features generated by OBVIS, a method coded with domain specific knowledge.
dc.language.isoENG
dc.publisherRensselaer Polytechnic Institute, Troy, NY
dc.relation.ispartofRensselaer Theses and Dissertations Online Collection
dc.subjectComputer science
dc.titleFeature generation for quantification of visual similarity
dc.typeElectronic thesis
dc.typeThesis
dc.digitool.pid172663
dc.digitool.pid172664
dc.digitool.pid172665
dc.rights.holderThis electronic version is a licensed copy owned by Rensselaer Polytechnic Institute, Troy, NY. Copyright of original work retained by author.
dc.description.degreeMS
dc.relation.departmentDept. of Computer Science


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record