Improved Hybrid Binarization based on Kmeans for Heterogeneous document processing.

Mahmoud Soua Rostom Kachouri Mohamed Akil

Published in: ISPA (2015)

Keyphrases

document processing
document images
information retrieval
document analysis
digital libraries
k means
document clustering
e learning
information extraction
text processing
textual documents
search engine
database systems
html documents