Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
Fundamentals of digital image processing
Fundamentals of digital image processing
Keyblock: an approach for content-based image retrieval
MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
| Hi-index | 0.00 |
Content Based Image Retrieval (CBIR) is currently a very important area of research in multimedia technology. Plenty of research works had been undertaken in past decade to design efficient image retrieval techniques from image database. Although large numbers of indexing and retrieval techniques have been developed, there are still no universally accepted feature extraction, indexing and retrieval techniques available. The main problem of the common CBIR system faces is that when the system is serving as an interface to an image collection, which covers many different topics. The problem of missing semantically information about the images leads to great numbers of false matches because of misleading similarities in the visual primitives that are retrieved. Which is called as semantic gap. This paper introduces an approach that tries to reduce the number of false matches in query result sets. It relies heavily on user feedback on retrieval results. This can be used as an independent system or as an interface to already existing CBIR system.