28 January 2008 Evaluation of content-based features for user-centered image retrieval in small media collections
Author Affiliations +
Abstract
The experiments described in this paper indicate that under certain conditions content-based features are not required for efficient user-centred image retrieval in small media collections. The importance of feature selection drops dramatically if classification is used for retrieval (e.g. if Support Vector Machines are used) and only little user feedback is available. In this situation simple image features and even random features perform equally well as sophisticated signal processing-based features (e.g. the content-based MPEG-7 image descriptors). Practically relevant applications for these findings are retrieval on mobile devices and in heterogeneous (e.g. ad hoc generated) media collections.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Horst Eidenberger, Horst Eidenberger, Maia Zaharieva, Maia Zaharieva, } "Evaluation of content-based features for user-centered image retrieval in small media collections", Proc. SPIE 6820, Multimedia Content Access: Algorithms and Systems II, 68200J (28 January 2008); doi: 10.1117/12.753725; https://doi.org/10.1117/12.753725
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Using browsing to improve content-based image retrieval
Proceedings of SPIE (October 05 1998)
Novel image retrieval technique using salient edges
Proceedings of SPIE (December 19 2001)
Image indexing using a texture dictionary
Proceedings of SPIE (November 21 1995)

Back to Top