Color features comparison for retrieval in personal photo collections

Authors:
Daniele Borghesani;Costantino Grana;Rita Cucchiara
Affiliations:
Dipartimento di Ingegneria dell'Informazione, University of Modena and Reggio Emilia, Modena, Italy;Dipartimento di Ingegneria dell'Informazione, University of Modena and Reggio Emilia, Modena, Italy;Dipartimento di Ingegneria dell'Informazione, University of Modena and Reggio Emilia, Modena, Italy
Venue:
ACS'08 Proceedings of the 8th conference on Applied computer scince
Year:
2008

Citing 3
Cited 1

Image Indexing Using Color Correlograms

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Color-Based Image Retrieval Using Spatial-Chromatic Histograms

ICMCS '99 Proceedings of the IEEE International Conference on Multimedia Computing and Systems - Volume 2
Enhancing HSV histograms with achromatic points detection for video retrieval

Proceedings of the 6th ACM international conference on Image and video retrieval

Digital forgery estimation into DCT domain: a critical analysis

MiFor '09 Proceedings of the First ACM workshop on Multimedia in forensics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Search and retrieval based on perceptual similarity will be a key issue for photo manager tools, indeed the majority of the thousand of photos collected day by day by users are not annotated or are associated with few meaningful keywords, making ontology or keyword based search not always affordable. In this paper, a complete performance analysis on similarity retrieval with common color features is proposed, focusing on the specific application scenario of personal photo collections. The analysis includes an enhancement of the standard HSV color space (aHSV), that provides performance improvements at no cost in practice. Tests are carried out on 25 variations of the UCID v2 database.