File Download
Supplementary

postgraduate thesis: Texture and mid-level features of objects and scenes in images

TitleTexture and mid-level features of objects and scenes in images
Authors
Issue Date2015
PublisherThe University of Hong Kong (Pokfulam, Hong Kong)
Citation
Wu, R. [武若冰]. (2015). Texture and mid-level features of objects and scenes in images. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b5719463
AbstractFeatures of images have been widely explored in the literature to better represent and utilize images. The development of deep learning has brought new challenges to image feature representations that they shall be easy to build and captures as much as information with minimum space. In this thesis, multiple aspects of image features have been studied to give a better utilization of textures and mid-level representations of objects and scenes in images. First we investigate texture synthesis of art patterns and line drawings. Inspired by exemplar-based texture synthesis methods, we bring up a global energy function which considers both the appearance and curvilinear feature similarities between the input exemplar and the output image. An EM-like scheme is performed to optimize that energy function, which can be easily to extend to handle multi-layer textures. The remaining part of this thesis is about creating mid-level features that can be used to classify objects and scenes in images more effectively. We propose a multi-layer deep learning model, SCaLE, to achieve intermediate image representation that can be directly used by nearest neighbor classifier. We then propose to use meta-objects and build a novel scene classification pipeline. Both models work well and give state-of-the-art performance on benchmark datasets.
DegreeDoctor of Philosophy
SubjectImage processing - Digital techniques
Dept/ProgramComputer Science
Persistent Identifierhttp://hdl.handle.net/10722/223613

 

DC FieldValueLanguage
dc.contributor.authorWu, Ruobing-
dc.contributor.author武若冰-
dc.date.accessioned2016-03-03T23:16:49Z-
dc.date.available2016-03-03T23:16:49Z-
dc.date.issued2015-
dc.identifier.citationWu, R. [武若冰]. (2015). Texture and mid-level features of objects and scenes in images. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b5719463-
dc.identifier.urihttp://hdl.handle.net/10722/223613-
dc.description.abstractFeatures of images have been widely explored in the literature to better represent and utilize images. The development of deep learning has brought new challenges to image feature representations that they shall be easy to build and captures as much as information with minimum space. In this thesis, multiple aspects of image features have been studied to give a better utilization of textures and mid-level representations of objects and scenes in images. First we investigate texture synthesis of art patterns and line drawings. Inspired by exemplar-based texture synthesis methods, we bring up a global energy function which considers both the appearance and curvilinear feature similarities between the input exemplar and the output image. An EM-like scheme is performed to optimize that energy function, which can be easily to extend to handle multi-layer textures. The remaining part of this thesis is about creating mid-level features that can be used to classify objects and scenes in images more effectively. We propose a multi-layer deep learning model, SCaLE, to achieve intermediate image representation that can be directly used by nearest neighbor classifier. We then propose to use meta-objects and build a novel scene classification pipeline. Both models work well and give state-of-the-art performance on benchmark datasets.-
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.lcshImage processing - Digital techniques-
dc.titleTexture and mid-level features of objects and scenes in images-
dc.typePG_Thesis-
dc.identifier.hkulb5719463-
dc.description.thesisnameDoctor of Philosophy-
dc.description.thesislevelDoctoral-
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