Numerous research works about the extraction of low-level features from images and videos have been published. However, only recently the focus has shifted to exploiting low-level features to classify images and videos automatically into semantically meaningful and broad categories. In this paper, novel classification algorithms are presented for three broad and general-purpose categories. In detail, we present algorithms for distinguishing photo-like images from graphical images, true photos from only photo-like, but artificial images and presentation slides from comics. On a large image database, our classification algorithm achieved an accuracy of 97.3% in separating photo-like images from graphical images. In the subset of photo-like images, true photos could be separated from ray-traced/rendered image with an accuracy of 87.3%, while with an accuracy of 93.2% the subset of graphical images was successfully partitioned into presentation slides and comics.

Date Published: 19 December 2001
PDF: 10 pages
Proc. SPIE 4676, Storage and Retrieval for Media Databases 2002, (19 December 2001); doi: 10.1117/12.451108

Published in SPIE Proceedings Vol. 4676:
Storage and Retrieval for Media Databases 2002
Minerva M. Yeung; Chung-Sheng Li; Rainer W. Lienhart, Editor(s)