109 urn:lsid:arphahub.com:pub:3dc5f44e-8666-58db-bc76-a455210e8891 JUCS - Journal of Universal Computer Science jucs 0948-695X 0948-6968 Journal of Universal Computer Science 10.3217/jucs-014-02-0299 28947 Research Article H.3.3 - Information Search and Retrieval A New and Efficient Algorithm to Binarize Document Images Removing Back-to-Front Interference João Marcelo Monte Da Silva joaommsilva@gmail.com 1 Lins Rafael Dueire 2 Martins Fernando Mário Junqueira 3 Wachenchauzer Rosita 4 Universidade Federal de Pernambuco, Recife, Brazil Universidade Federal de Pernambuco Recife Brazil Federal University of Pernambuco, Recife, Brazil Federal University of Pernambuco Recife Brazil Universidade do Minho, Braga, Portugal Universidade do Minho Braga Portugal Universidad de Buenos Aires, Buenos Aires, Argentina Universidad de Buenos Aires Buenos Aires Argentina

Corresponding author: João Marcelo Monte Da Silva (joaommsilva@gmail.com).

Academic editor:

2008 28 01 2008 14 2 299 313 1D644B4A-551A-52C7-9895-5214FE450EAC 7000094 João Marcelo Monte Da Silva, Rafael Dueire Lins, Fernando Mário Junqueira Martins, Rosita Wachenchauzer This article is freely available under the J.UCS Open Content License.

"Back-to-front interference", "bleeding" and "show-through"is the name given to the phenomenon found whenever documents are written on both sides of translucent paper and the print of one side is visible on the other one. The binarization of documents with back-to-front interference with standard algorithms yields unreadable documents. This paper presents a fast entropy-based segmentation method for generating high-quality binarized images of documents with back-to-front interference.