Local Similarity Search for Content-based Image Retrieval
This event took place on Wednesday 29 November 2006 at 11:30
Peter Howarth Imperial College London, and KMi, The Open University
The goal of content-based image retrieval (CBIR) is to provide the user with a way to browse or retrieve images from large collections based on visual similarity. At the heart of any CBIR system are visual features that have been extracted from images and (dis)similarity functions that are used to quantify the similarity between these features. The combination of these two components will drive the overall performance of a system.
Two frequently studied research areas in CBIR are maximising retrieval performance using similarity measures and improving the efficiency and speed of search by applying indexing methods. Often these are mutually exclusive. The best performing similarity measures are usually computationally expensive and the optimal indexing approaches can place many restrictions on what features and similarity functions can be used.
In this talk we investigate how to localise the measurement of similarity. That is, emphasise points that are close to the query in some subspace of the full feature space. We show that this has dual benefits for CBIR, both improving retrieval performance and speeding up the search of high-dimensional features.
This event took place on Wednesday 29 November 2006 at 11:30
The goal of content-based image retrieval (CBIR) is to provide the user with a way to browse or retrieve images from large collections based on visual similarity. At the heart of any CBIR system are visual features that have been extracted from images and (dis)similarity functions that are used to quantify the similarity between these features. The combination of these two components will drive the overall performance of a system.
Two frequently studied research areas in CBIR are maximising retrieval performance using similarity measures and improving the efficiency and speed of search by applying indexing methods. Often these are mutually exclusive. The best performing similarity measures are usually computationally expensive and the optimal indexing approaches can place many restrictions on what features and similarity functions can be used.
In this talk we investigate how to localise the measurement of similarity. That is, emphasise points that are close to the query in some subspace of the full feature space. We show that this has dual benefits for CBIR, both improving retrieval performance and speeding up the search of high-dimensional features.
Future Internet
KnowledgeManagementMultimedia &
Information SystemsNarrative
HypermediaNew Media SystemsSemantic Web &
Knowledge ServicesSocial Software
New Media Systems is...
Our New Media Systems research theme aims to show how new media devices, standards, architectures and concepts can change the nature of learning.
Our work involves the development of short life-cycle working prototypes of innovative technologies or concepts that we believe will influence the future of open learning within a 3-5 year timescale. Each new media concept is built into a working prototype of how the innovation may change a target community. The working prototypes are all available (in some form) from this website.
Our prototypes themselves are not designed solely for traditional Open Learning, but include a remit to show how that innovation can and will change learning at all levels and in all forms; in education, at work and play.
List all New Media Systems Projects
Check out these Hot New Media Systems Technologies:
List all New Media Systems Technologies
