A fast algorithm to binarize and filter documents with back-to-front interference

ABSTRACT

Whenever one finds documents written on both sides on translucent paper there is a "back-to-front interference". The direct binarization of such documents yields unreadable documents. This paper presents a fast segmentation-based method for generating high-quality binarized images of documents with back-to-front interference. The proposed segmentation algorithm is based on the entropy of the histogram of the image.

REFERENCES

• 1: N. Abramson. Information Theory and Coding. McGraw-Hill Book Company, 1963.
• 2: Rafael Dueire Lins , Mário Guimarães Neto , Leopoldo Fraņa Neto , Luciano Galdino Rosa, An environment for processing images of historical documents, Microprocessing and Microprogramming, v.40 n.10-12, p.939-942, Dec. 1994
• 3: R. D. Lins, B. T. Ávila, and A. A. Formiga, BigBatch: An Environment for Processing Monochromatic Documents. ICIAR2006, LNCS 4142, pp.886--896, SpringerVerlag 2006.
• 4: Rafael Dueire Lins , João Marcelo Monte da Silva, A quantitative method for assessing algorithms to remove back-to-front interference in documents, Proceedings of the 2007 ACM symposium on Applied computing, March 11-15, 2007, Seoul, Korea [doi>10.1145/1244002.1244142]
• 5: João Marcelo M. da Silva , Rafael Dueire Lins , Valdemar Cardoso da Rocha, Binarizing and filtering historical documents with back-to-front interference, Proceedings of the 2006 ACM symposium on Applied computing, April 23-27, 2006, Dijon, France [doi>10.1145/1141277.1141471]
• 6: FUNDAJ: http://www.fundaj.gov.br.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Information filtering

General Terms:
Algorithms

Keywords:
back-to-front interference, bleeding, document engineering, entropy, show-through