Learning Mid-Level Features from Object Hierarchy for Image Classification
| dc.contributor.author | Albaradei, Somayah | |
| dc.contributor.examiningcommittee | Neil Bruce (Computer Science) Carson Leung (Computer Science) Ekram Hossain (Electrical and Computer Engineering) | en_US |
| dc.contributor.supervisor | Yang Wang (Computer Science) | en_US |
| dc.date.accessioned | 2014-11-13T16:32:58Z | |
| dc.date.available | 2014-11-13T16:32:58Z | |
| dc.date.issued | 2014 | en_US |
| dc.degree.discipline | Computer Science | en_US |
| dc.degree.level | Master of Science (M.Sc.) | en_US |
| dc.description.abstract | One of the most active research areas in computer vision is image classification. Although there have been many research efforts in this area, it remains a difficult problem, especially when the number of categories is large. Most of the previous work in image classification uses low-level image features. We believe low-level features ignore a lot of the semantic structures of the image classes. In this thesis, we go beyond simple low-level features and propose new approaches for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representations implicitly capture the hierarchical structure in object classes. We show that our proposed approach outperforms other baseline methods in image classification. | en_US |
| dc.description.note | February 2015 | en_US |
| dc.identifier.citation | @inproceedings{albaradei2014, title = {Learning Mid-Level Features from Object Hierarchy for Image Classification}, author= {Albaradei, Somayah and Wang, Yang and Cao,Liangliang and Li,Jia}, booktitle = {Proceedings of IEEE Winter Conference on Applications of Computer Vision}, year = {2014} } | en_US |
| dc.identifier.uri | http://hdl.handle.net/1993/28540 | |
| dc.language.iso | eng | en_US |
| dc.publisher | IEEE | en_US |
| dc.rights | open access | en_US |
| dc.subject | Image Classification | en_US |
| dc.subject | Mid-Level Features | en_US |
| dc.title | Learning Mid-Level Features from Object Hierarchy for Image Classification | en_US |
| dc.type | master thesis | en_US |