Efficient Image Matching using Regions of Interest
| atmire.migration.oldid | 2487 | |
| dc.contributor.advisor | Gavrilova, Marina | |
| dc.contributor.author | Bhattacharya, Priyadarshi | |
| dc.date.accessioned | 2014-09-12T22:14:26Z | |
| dc.date.available | 2014-11-17T08:00:45Z | |
| dc.date.issued | 2014-09-12 | |
| dc.date.submitted | 2014 | en |
| dc.description.abstract | This thesis tackles the challenging problem of producing a ranked list of images, based on similarity to a query image in a large, unordered image collection. The application domain considered spans from landmarks and scenes to general objects. Existing state-of-the-art methodology for object retrieval in large image collections [SZ03] [PCI+07], based on the bag-of-words approach, has its limitations. Discarding spatial information about features in the image representation stage results in false matches. Spatial verification, used as a post-processing step to improve retrieval accuracy, is computationally expensive. Being based on a global model of the image, the method is susceptible to noise and background clutter. In this thesis, I propose a novel image modelling methodology, that is driven by attention to interesting regions of an image and representing these regions at a high level of detail. Rich spatial information about features is injected in the image modelling stage. This eliminates the need for computationally expensive spatial verification as a post-processing step. A novel image matching methodology is proposed that matches localized regions in images, instead of matching images at a global level using a histogram-based approach. The motivation is that, despite large changes in their global appearance, some of the regions in the images will still match well. The proposed methodology is observed to be highly robust to viewpoint changes, occlusion and background clutter and suitable for sub-image retrieval. It allows real-time search and is scalable to large image corpuses. An added advantage is that object localization is possible simultaneously with search, with minimal computing effort. Experiments reveal the superior performance of the proposed methodology over state-of-the-art methods that utilize spatial information. It is also several orders of magnitude faster than the bag-of-words approach with spatial verification. | en_US |
| dc.identifier.citation | Bhattacharya, P. (2014). Efficient Image Matching using Regions of Interest (Doctoral thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/25845 | en_US |
| dc.identifier.doi | http://dx.doi.org/10.11575/PRISM/25845 | |
| dc.identifier.uri | http://hdl.handle.net/11023/1752 | |
| dc.language.iso | eng | |
| dc.publisher.faculty | Graduate Studies | |
| dc.publisher.institution | University of Calgary | en |
| dc.publisher.place | Calgary | en |
| dc.rights | University of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission. | |
| dc.subject | Computer Science | |
| dc.subject.classification | regions of interest | en_US |
| dc.subject.classification | dense features | en_US |
| dc.subject.classification | part-based image matching | en_US |
| dc.subject.classification | finding similar images | en_US |
| dc.subject.classification | Image Matching | en_US |
| dc.title | Efficient Image Matching using Regions of Interest | |
| dc.type | doctoral thesis | |
| thesis.degree.discipline | Computer Science | |
| thesis.degree.grantor | University of Calgary | |
| thesis.degree.name | Doctor of Philosophy (PhD) | |
| ucalgary.item.requestcopy | true |