Title
Document page classification algorithms in low-end copy pipeline
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. (C) 2008 SPIE and IS&T.
Year
DOI
Venue
2008
10.1117/1.3010879
JOURNAL OF ELECTRONIC IMAGING
Keywords
Field
DocType
algorithms,data storage
Computer vision,Color space,Pattern recognition,Computer science,Document image processing,Image representation,Artificial intelligence,RGB color model,Statistical classification,Contextual image classification,User interface
Journal
Volume
Issue
ISSN
17
4
1017-9909
Citations 
PageRank 
References 
3
0.44
4
Authors
7
Name
Order
Citations
PageRank
Xiaogang Dong1133.63
Kai-Lung Hua226542.99
Peter Majewicz372.20
Gordon McNutt430.44
Charles A. Bouman52740473.62
Jan P. Allebach61230170.88
Ilya Pollak77917.38