Back to articles
Articles
Volume: 17 | Article ID: art00080_2
Image
Document Resizing Using a Multi-Layer Neural Network
Mohamed N. Ahmed
Brian E. Cooper
Shaun T. Love
  DOI :  10.2352/ISSN.2169-4451.2001.17.1.art00080_2  Published Online :  January 2001
Abstract

In this paper we present a resizing neural network for edge and detail preserving image interpolation. The multilayer neural network is trained by using pairs of high resolution and low resolution imagery. The high resolution is an 8-bit image scanned at 600 dpi. The low resolution image (300 dpi) is either a processed version of the high resolution image, or it is scanned independently. pixels are extracted from the low (high) resolution image and are used as inputs to the neural networks. The interpolated pixels obtained as output are compared with the high (low) resolution pixels after enhancement and the error is used to train the neural network.

Journal Title : NIP & Digital Fabrication Conference
Publisher Name : Society of Imaging Science and Technology
Publisher Location : 7003 Kilworth Lane, Springfield, VA 22151, USA
Subject Areas :
Views 7
Downloads 0
 DOI 10.2352/ISSN.2169-4451.2001.17.1.art00080_2
 articleview.views 7
 articleview.downloads 0
  Cite this article 

Mohamed N. Ahmed, Brian E. Cooper, Shaun T. Love, "Document Resizing Using a Multi-Layer Neural Network"  in Proc. IS&T Int'l Conf. on Digital Printing Technologies (NIP17),  2001,  pp 792 - 796,  https://doi.org/10.2352/ISSN.2169-4451.2001.17.1.art00080_2

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2001
72010410
NIP & Digital Fabrication Conference
nip digi fabric conf
2169-4451
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA
2169-4451(20010101)2001:2L.792;1-
nip_v2001n2/splitsection80.xml
/ist/nipdf/2001/00002001/00000002/art00080
Articles
Document Resizing Using a Multi-Layer Neural Network
AhmedMohamed N.
CooperBrian E.
LoveShaun T.
01012001
2001
2
792
796
2001
In this paper we present a resizing neural network for edge and detail preserving image interpolation. The multilayer neural network is trained by using pairs of high resolution and low resolution imagery. The high resolution is an 8-bit image scanned at 600 dpi. The low resolution image (300 dpi) is either a processed version of the high resolution image, or it is scanned independently. pixels are extracted from the low (high) resolution image and are used as inputs to the neural networks. The interpolated pixels obtained as output are compared with the high (low) resolution pixels after enhancement and the error is used to train the neural network.