Share Email Print

Journal of Electronic Imaging

Clustering techniques for personal photo album management
Author(s): Edoardo Ardizzone; Marco La Cascia; Marco Morana; Filippo Vella
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We propose a novel approach for the automatic representation of pictures achieving a more effective organization of personal photo albums. Images are analyzed and described in multiple representation spaces, namely, faces, background, and time of capture. Faces are automatically detected, rectified, and represented, projecting the face itself in a common low-dimensional eigenspace. Backgrounds are represented with low-level visual features based on an RGB histogram and Gabor filter bank. Faces, time, and background information of each image in the collection is automatically organized using a mean-shift clustering technique. Given the particular domain of personal photo libraries, where most of the pictures contain faces of a relatively small number of different individuals, clusters tend to be semantically significant besides containing visually similar data. We report experimental results based on a data set of about 1000 images where automatic detection and rectification of faces lead to approximately 400 faces. Significance of clustering has been evaluated, and results are very encouraging.

Paper Details

Date Published: 1 October 2009
J. Electron. Imag. 18(4) 043014 doi: 10.1117/1.3274617
Published in: Journal of Electronic Imaging Volume 18, Issue 4
Show Author Affiliations
Edoardo Ardizzone, Univ. degli Studi di Palermo (Italy)
Marco La Cascia, Univ. degli Studi di Palermo (Italy)
Marco Morana, Univ. degli Studi di Palermo (Italy)
Filippo Vella, Consiglio Nazionale delle Ricerche (Italy)

© SPIE. Terms of Use
Back to Top