Image database querying using a multi-scale localized color representation
- 20 January 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. spie 1908, 28-32
- https://doi.org/10.1109/ivl.1999.781119
Abstract
A computationally efficient method to encode the spatial concentration of colors in images based on local histogram intersection is introduced. The representation allows image matching at multiple resolutions and partial matching of image regions without requiring image segmentation or cluster approximations. The method has been tested on a heterogeneous database of 16,643 images and video frames. Results of objective evaluation using manually selected ground-truth image queries as well as ground-truth video keyframe queries are presented.Keywords
This publication has 9 references indexed in Scilit:
- Indexing flowers by color names using domain knowledge-driven segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Image retrieval evaluationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Percentile blobs for image similarityPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Image indexing using color correlogramsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- FOCUS: Searching for multi-colored objects in a diverse image databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Comparing images using color coherence vectorsPublished by Association for Computing Machinery (ACM) ,1996
- Retrieval of paintings using principal color informationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- An integrated color-spatial approach to content-based image retrievalPublished by Association for Computing Machinery (ACM) ,1995
- Interactive indexing into image databasesPublished by SPIE-Intl Soc Optical Eng ,1993