|Candidate||Completion Date University||Title (N) = Thesis in Norwegian|
|Christian Hartvedt||2011, UiB||Interactivity in context-based image retrieval|
|Margrete Allern Brose||2010, UiTø||Context-aware Image Retrieval|
|Lars-Jacob Hove||2009, UiB||Visual Queries for Image Retrieval|
|Roe Fyllingsnes||2008, UiB||Mobile image retrieval|
|Jan-Erik Bråthen||2008, UiB||Folksonomies|
|Siv Hansen||2008, UiB||Multi Modal IR|
|Kawaljeet Singh Puri||2008, UiB||A Global Image Retrieval System using the CIDOC CRM|
|Anne Staurland Aarbakke||June 2007, UiTø||M2S and CAIR: Image based information retrieval in mobile environments|
|Christian Hartvedt||March 2007, UiB||Utilizing context in ranking results from distributed image retrieval – the CAIRANK Prototyp|
|Silje Alfheim||Dec.2006, UiTø||Image Contexts and the Semantic Web|
|Kai Arne Bjørnenak||Dec.2006, UiTø||Images and Location data (N)|
|Arne Tøndersen||June 2006, UiTø||Image retrieval based on location and time|
|Kurt Jøran Nyland||June 2006, UiTø||Image Collections and Context (N)|
|Per Thomas Bakken||June 2007, UiTø||Context detection on mobile units|
The table below presents some suggested master thesis projects based on the UiB project goals.
|CAIM sub-project/thesis topics|
UiB project areas
|UiB focus & perspective||Thesis topic proposals
|1||Dynamic context capture and management|
|1.a||Image context model||Definition of the concept of image context, context modeling including development of context descriptors for relationships among image objects||1. Evaluation/development of metadata models for capturing image context data in various application domains.
2. How can ontologies be used to make classification, information retrieval and collection updates more effective?
|1.b||Image description management||Dynamic update of context descriptors from user feedback. Development of techniques for the construction and use of ‘folksonomies’ and ontologies.||1. How can user input (feedback) be utilized for object identification and inter-object relationship specifications?
- How do user defined 'folksonomies' relate to/effect application/domain ontologies?
- Will a constantly updated folksonomy for an image collection improve image retrieval?
- Can a game-based approach to identifying objects within an image improve identification of image components?
|2||Multimodal information retrieval|
|2.a||Context-based Image retrieval||Focus on internal image contexts, e.g. relationships between image objects||1. Develop/extend algorithms for image retrieval using context data as defined in 1a and 1b
|2.b||Image retrieval using visual queries||Development of a visual query language (VQL) for image retrieval||1. How can current VQLs be improved?
|2.c||Multi-modal information retrieval||Text/audio retrieval from image input||1. Given visual input, how can image context data be utilized to retrieve related, multiple modal (text, audio) information?
|2.d||Multi-DB information retrieval||Focus on retrieval from multiple image collections.||1. How can current information retrieval algorithms from multiple DB systems be adapted for a multiple media DB environment?
(related to 2c)
|3.a||Context-based ranking||Focus on image component context||1. Develop and evaluate algorithms for "component-based" ranking (Related to 1b)
|3.b||Result ranking for image retrieval||Focus on ranking/integration of image result sets from multiple image DBs||1. Develop/improve algorithms for merging/ranking result sets from multiple image DBs (re. 2d)
|3.c||Multi-modal result presentation||Mixed media presentation.||1. Develop/improve current multi-modal result presentation
- potential case: VED prototypes; Flamenco http://flamenco.berkeley.edu/
- Are these algorithms domain dependent?