Share Email Print
cover

Proceedings Paper

Identification and ranking of relevant image content
Author(s): Mustafa Jaber; Eli Saber; Sohail Dianat; Mark Shaw; Ranjit Bhaskar
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, we present an image understanding algorithm for automatically identifying and ranking different image regions into several levels of importance. Given a color image, specialized maps for classifying image content namely: weighted similarity, weighted homogeneity, image contrast and memory colors are generated and combined to provide a metric for perceptual importance classification. Further analysis yields a region ranking map which sorts the image content into different levels of significance. The algorithm was tested on a large database of color images that consists of the Berkeley segmentation dataset as well as many other internal images. Experimental results show that our technique matches human manual ranking with 90% efficiency. Applications of the proposed algorithm include image rendering, classification, indexing and retrieval.

Paper Details

Date Published: 3 March 2008
PDF: 6 pages
Proc. SPIE 6812, Image Processing: Algorithms and Systems VI, 68120I (3 March 2008); doi: 10.1117/12.753609
Show Author Affiliations
Mustafa Jaber, Rochester Institute of Technology (United States)
Eli Saber, Rochester Institute of Technology (United States)
Sohail Dianat, Rochester Institute of Technology (United States)
Mark Shaw, Hewlett-Packard Corp. (United States)
Ranjit Bhaskar, Hewlett-Packard Corp. (United States)


Published in SPIE Proceedings Vol. 6812:
Image Processing: Algorithms and Systems VI
Jaakko T. Astola; Karen O. Egiazarian; Edward R. Dougherty, Editor(s)

© SPIE. Terms of Use
Back to Top