Articolo in rivista, 2007, ENG, 10.1007/s10032-006-0015-z

Fast correction of bleed-through distortion in grayscale documents by a blind source separation technique

Tonazzini A.; Salerno E.; Bedini L.

CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy

Ancient documents are usually degraded by the presence of strong background artifacts. These are often caused by the so-called bleed-through effect, a pattern that interferes with the main text due to seeping of ink from the reverse side. A similar effect, called show-through and due to the nonperfect opacity of the paper, may appear in scans of even modern, well-preserved documents. These degradations must be removed to improve human or automatic readability. For this purpose, when a color scan of the document is available, we have shown that a simplified linear pattern overlapping model allows us to use very fast blind source separation techniques. This approach, however, cannot be applied to grayscale scans. This is a serious limitation, since many collections in our libraries and archives are now only available as grayscale scans or microfilms. We propose here a new model for bleed-through in grayscale document images, based on the availability of the recto and verso pages, and show that blind source separation can be successfully applied in this case too. Some experiments with real-ancient documents are presented and described.

International journal on document analysis and recognition (Internet) 10 , pp. 17–25

Keywords

I.4.4 Restoration, Blind source separation

CNR authors

Bedini Luigi, Salerno Emanuele, Tonazzini Anna

CNR institutes

ISTI – Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"

ID: 68351

Year: 2007

Type: Articolo in rivista

Creation: 2009-06-16 00:00:00.000

Last update: 2018-01-25 10:34:07.000

External links

OAI-PMH: Dublin Core

OAI-PMH: Mods

OAI-PMH: RDF

DOI: 10.1007/s10032-006-0015-z

External IDs

CNR OAI-PMH: oai:it.cnr:prodotti:68351

DOI: 10.1007/s10032-006-0015-z

ISI Web of Science (WOS): 000247735200002