Home // MMEDIA 2011, The Third International Conferences on Advances in Multimedia // View article

Representative Picture Selection from Albums

Authors:
Gábor Szücs
Tamás Leposa
Sándor Turbucz

Keywords: representative picture; k-means++ clustering; qualitative and quantitative features; content features; EXIF data;

Abstract:
The paper is concerned with managing image album, where the picture set (containing very similar or different images) in each album is given. The goal has been to select the most representative pictures from the album. Our solution is based on the clustering of the images. The developed clustering procedure takes the large variety of the pictures and different type of image features into account. We have solved the incomplete feature value problem as well. The central pictures of the largest clusters are selected for representing the album.

Pages: 114 to 117

Copyright: Copyright (c) IARIA, 2011

Publication date: April 17, 2011

Published in: conference

ISSN: 2308-4448

ISBN: 978-1-61208-129-8

Location: Budapest, Hungary

Dates: from April 17, 2011 to April 22, 2011