Share Email Print

Journal of Electronic Imaging

Document page classification algorithms in low-end copy pipeline
Author(s): Xiaogang Dong; Kai-Lung Hua; Peter Majewicz; Gordon McNutt; Charles A. Bouman; Jan P. Allebach; Ilya Pollak
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 develop real-time, low-complexity image classification algorithms suitable for a copy mode selector embedded in a low-end copier. The algorithms classify scanned images represented in RGB or in an opponent color space. Classes are the eight combinations of mono/color and text/mix/picture/photo. Classification is 30–98% accurate with misclassifications tending to be benign. The algorithms provide for improved copy quality, a simplified user interface, and increased copy rate.

Paper Details

Date Published: 1 October 2008
PDF: 17 pages
J. Electron. Imag. 17(4) 043011 doi: 10.1117/1.3010879
Published in: Journal of Electronic Imaging Volume 17, Issue 4
Show Author Affiliations
Xiaogang Dong, Sony Electronics Inc. (United States)
Kai-Lung Hua, Purdue Univ. (United States)
Peter Majewicz, Hewlett-Packard Co. (United States)
Gordon McNutt, CradlePoint, Inc. (United States)
Charles A. Bouman, Purdue Univ. (United States)
Jan P. Allebach, Purdue Univ. (United States)
Ilya Pollak, Purdue Univ. (United States)

© SPIE. Terms of Use
Back to Top