File Download
Supplementary

postgraduate thesis: Discriminative parts in computer vision : discovery and application

TitleDiscriminative parts in computer vision : discovery and application
Authors
Issue Date2015
PublisherThe University of Hong Kong (Pokfulam, Hong Kong)
Citation
Lin, A. [林盎然]. (2015). Discriminative parts in computer vision : discovery and application. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b5610992
AbstractDiscriminative part-based approaches have become increasingly popular in the past few years. The reason of their popularity can be attributed to the fact that discriminative parts have the ability to accumulate low level features to form high level descriptors for objects and images. Unfortunately, state-of-the-art algorithms heavily rely on SVM related techniques, which consume a lot of computation resources in training. To overcome this shortage and apply discriminative part-based techniques to more complicated computer vision problems with larger datasets, a fast, simple and powerful algorithm named Fast Exemplar Clustering (FEC) is proposed in this dissertation. It can train part classifiers automatically in an extremely efficient manner with only class labels provided. To show the great power of FEC, experiments were carried out on two computer vision topics: scene classification and scene text recognition. On scene classification, a new dataset named Outdoor Sight 20 was created and used in combination with MIT Indoor 67 dataset to test FEC’s ability to classify indoor and outdoor scenes. On scene recognition, a concrete example of integrating FEC was presented. Comparisons were made to show that the parts discovered by FEC were more meaningful than the existing linear SVM based feature pooling method, which led to a better recognition result.
DegreeMaster of Philosophy
SubjectComputer vision
Dept/ProgramComputer Science
Persistent Identifierhttp://hdl.handle.net/10722/221188

 

DC FieldValueLanguage
dc.contributor.authorLin, Angran-
dc.contributor.author林盎然-
dc.date.accessioned2015-11-04T23:11:56Z-
dc.date.available2015-11-04T23:11:56Z-
dc.date.issued2015-
dc.identifier.citationLin, A. [林盎然]. (2015). Discriminative parts in computer vision : discovery and application. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b5610992-
dc.identifier.urihttp://hdl.handle.net/10722/221188-
dc.description.abstractDiscriminative part-based approaches have become increasingly popular in the past few years. The reason of their popularity can be attributed to the fact that discriminative parts have the ability to accumulate low level features to form high level descriptors for objects and images. Unfortunately, state-of-the-art algorithms heavily rely on SVM related techniques, which consume a lot of computation resources in training. To overcome this shortage and apply discriminative part-based techniques to more complicated computer vision problems with larger datasets, a fast, simple and powerful algorithm named Fast Exemplar Clustering (FEC) is proposed in this dissertation. It can train part classifiers automatically in an extremely efficient manner with only class labels provided. To show the great power of FEC, experiments were carried out on two computer vision topics: scene classification and scene text recognition. On scene classification, a new dataset named Outdoor Sight 20 was created and used in combination with MIT Indoor 67 dataset to test FEC’s ability to classify indoor and outdoor scenes. On scene recognition, a concrete example of integrating FEC was presented. Comparisons were made to show that the parts discovered by FEC were more meaningful than the existing linear SVM based feature pooling method, which led to a better recognition result.-
dc.languageeng-
dc.publisherThe University of Hong Kong (Pokfulam, Hong Kong)-
dc.relation.ispartofHKU Theses Online (HKUTO)-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rightsThe author retains all proprietary rights, (such as patent rights) and the right to use in future works.-
dc.subject.lcshComputer vision-
dc.titleDiscriminative parts in computer vision : discovery and application-
dc.typePG_Thesis-
dc.identifier.hkulb5610992-
dc.description.thesisnameMaster of Philosophy-
dc.description.thesislevelMaster-
dc.description.thesisdisciplineComputer Science-
dc.description.naturepublished_or_final_version-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats