Proximity-based Order-respecting Intersection for Searching in Image Databases

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.

Authors

HOMOLA Tomáš DOHNAL Vlastislav ZEZULA Pavel

Type Article in Proceedings
Conference 8th International Workshop on Adaptive Multimedia Retrieval, AMR'2010
MU Faculty or unit

Faculty of Informatics

Citation
Doi http://dx.doi.org/10.1007/978-3-642-27169-4_13
Field Informatics
Keywords proximity based order respecting intersection; sub image search; image database; experimental trials
Description As the volume of non-textual data, such images and other multimedia data, available on Internet is increasing. The issue of identifying data items based on query containment rather than query equality is more and more important. In this paper, we propose a solution to this problem. We assume the local descriptors are extracted from data item, so the aforementioned problem reduces to finding data items of a collection that share as many as possible local descriptors with the query. In particular, we defined a new e-intersection that identifies close (similar) descriptors. Local descriptors usually contain the location of the descriptors in the original data, so the proposed solution takes into account them to increase effectiveness of searching. We evaluate the e-intersection on two real-life image collections using SIFT and SURF local descriptors.
Related projects: