Matches in SemOpenAlex for { <https://semopenalex.org/work/W115351601> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W115351601 abstract "We live in the midst of the information era, during which organising and indexing information more effectively is a matter of essential importance. With the fast development of digital imagery, how to search images - a rich form of information - more efficiently by their content has become one of the biggest challenges. Content-based image retrieval (CBIR) has been the traditional and dominant technique for searching images for decades. However, not until recently have researchers started to realise some vital problems existing in CBIR systems. One of the most important is perhaps what people call the textit{semantic gap}, which refers to the gap between the information that can be extracted from images and the interpretation of the images for humans. As an attempt to bridge the semantic gap, automatic image annotation has been gaining more and more attentions in recent years. This thesis aims to explore a number of different approaches to automatic image annotation and some related issues. It begins with an introduction into different techniques for image description, which forms the foundation of the research on image auto-annotation. The thesis then goes on to give an in-depth examination of some of the quality issues of the data-set used for evaluating auto-annotation systems. A series of approaches to auto-annotation are presented in the follow-up chapters. Firstly, we describe an approach that incorporates the salient based image representation into a statistical model for better annotation performance. Secondly, we explore the use of non-negative matrix factorisation (NMF), a matrix decomposition tehcnique, for two tasks; object class detection and automatic annotation of images. The results imply that NMF is a promising sub-space technique for these purposes. Finally, we propose a model named the image based feature space (IBFS) model for linking image regions and keywords, and for image auto-annotation. Both image regions and keywords are mapped into the same space in which their relationships can be measured. The idea of multiple segmentations is then implemented in the model, and better results are achieved than using a single segmentation." @default.
- W115351601 created "2016-06-24" @default.
- W115351601 creator A5048587578 @default.
- W115351601 date "2008-05-01" @default.
- W115351601 modified "2023-09-24" @default.
- W115351601 title "Automatic image annotation and object detection" @default.
- W115351601 hasPublicationYear "2008" @default.
- W115351601 type Work @default.
- W115351601 sameAs 115351601 @default.
- W115351601 citedByCount "9" @default.
- W115351601 countsByYear W1153516012012 @default.
- W115351601 countsByYear W1153516012013 @default.
- W115351601 countsByYear W1153516012014 @default.
- W115351601 countsByYear W1153516012015 @default.
- W115351601 crossrefType "dissertation" @default.
- W115351601 hasAuthorship W115351601A5048587578 @default.
- W115351601 hasConcept C115961682 @default.
- W115351601 hasConcept C154945302 @default.
- W115351601 hasConcept C1667742 @default.
- W115351601 hasConcept C177264268 @default.
- W115351601 hasConcept C17744445 @default.
- W115351601 hasConcept C199360897 @default.
- W115351601 hasConcept C199539241 @default.
- W115351601 hasConcept C199579030 @default.
- W115351601 hasConcept C23123220 @default.
- W115351601 hasConcept C2776321320 @default.
- W115351601 hasConcept C2776359362 @default.
- W115351601 hasConcept C2780719617 @default.
- W115351601 hasConcept C41008148 @default.
- W115351601 hasConcept C75165309 @default.
- W115351601 hasConcept C86034646 @default.
- W115351601 hasConcept C94625758 @default.
- W115351601 hasConceptScore W115351601C115961682 @default.
- W115351601 hasConceptScore W115351601C154945302 @default.
- W115351601 hasConceptScore W115351601C1667742 @default.
- W115351601 hasConceptScore W115351601C177264268 @default.
- W115351601 hasConceptScore W115351601C17744445 @default.
- W115351601 hasConceptScore W115351601C199360897 @default.
- W115351601 hasConceptScore W115351601C199539241 @default.
- W115351601 hasConceptScore W115351601C199579030 @default.
- W115351601 hasConceptScore W115351601C23123220 @default.
- W115351601 hasConceptScore W115351601C2776321320 @default.
- W115351601 hasConceptScore W115351601C2776359362 @default.
- W115351601 hasConceptScore W115351601C2780719617 @default.
- W115351601 hasConceptScore W115351601C41008148 @default.
- W115351601 hasConceptScore W115351601C75165309 @default.
- W115351601 hasConceptScore W115351601C86034646 @default.
- W115351601 hasConceptScore W115351601C94625758 @default.
- W115351601 hasLocation W1153516011 @default.
- W115351601 hasOpenAccess W115351601 @default.
- W115351601 hasPrimaryLocation W1153516011 @default.
- W115351601 hasRelatedWork W1666447063 @default.
- W115351601 hasRelatedWork W1750831471 @default.
- W115351601 hasRelatedWork W1779423191 @default.
- W115351601 hasRelatedWork W1794758617 @default.
- W115351601 hasRelatedWork W1877469910 @default.
- W115351601 hasRelatedWork W1900395391 @default.
- W115351601 hasRelatedWork W2029109699 @default.
- W115351601 hasRelatedWork W2068070764 @default.
- W115351601 hasRelatedWork W2127411609 @default.
- W115351601 hasRelatedWork W2137918516 @default.
- W115351601 hasRelatedWork W2156336347 @default.
- W115351601 hasRelatedWork W2170872123 @default.
- W115351601 hasRelatedWork W2172231696 @default.
- W115351601 hasRelatedWork W2314891720 @default.
- W115351601 hasRelatedWork W2355349688 @default.
- W115351601 hasRelatedWork W2359571297 @default.
- W115351601 hasRelatedWork W2775421587 @default.
- W115351601 hasRelatedWork W2810155558 @default.
- W115351601 hasRelatedWork W71124072 @default.
- W115351601 hasRelatedWork W2188082841 @default.
- W115351601 isParatext "false" @default.
- W115351601 isRetracted "false" @default.
- W115351601 magId "115351601" @default.
- W115351601 workType "dissertation" @default.