NEU GRAND LIBRARY
Opening Hours: Monday-Saturday, 08:00-20:00 | E-mail: library@neu.edu.tr
 

You are not logged in Show Basket
  Home     Advanced Search     Back  
Print
Add to Basket
  Brief display     MARC Display     Reserve  
Global Binarization of Document Images Using a Neural Network (Khashman, Adnan,)
Bibliographical information (record 269940)
Help
Global Binarization of Document Images Using a Neural Network
Author:
 Khashman, Adnan, Search Author in Amazon Books

Publisher:
IEEE,
ISBN:
 978-0-7695-3122-9
Edition:
 2008.
Classification:
 QA76
URL:
http://library.neu.edu.tr:2048/login?url=http://dx.doi.org/10.1109/SITIS.2007.58
Detailed notes
    - In degraded scanned documents, where considerable background noise or variation in contrast and illumination exists, pixels may not be easily classified as foreground or background pixels. Thus, the need to perform document binarization in order to enhance the document image by separating foregrounds (text)from backgrounds. A new approach that combines a global thresholding method and a supervised neural network classifier is proposed to enhance scanned documents and to separate foreground and background layers. Thresholding is first applied using Mass-Difference thresholding to obtain various local optimum threshold values in an image. The neural network is then trained using these values at its input and a single global optimum threshold value for the entire image at its output. Compared with other methods, experimental results show that this combined approach is computationally cost-effective and is capable of enhancing degraded documents with superior foreground and background separation results.
Related links
Items (1)
Barcode
Status
Library
Section
EOL-1739
Item available
NEU Grand LibraryOnline (QA76 .G56 2008)
Online electronic
NEAR EAST UNIVERSITY GRAND LIBRARY +90 (392) 223 64 64 Ext:5536. Near East Boulevard, Nicosia, TRNC
This software is developed by NEU Library and it is based on Koha OSS
conforms to MARC21 library data transfer rules.