A New Binarization Algorithm for Historical Documents
Autor: | Rafael Dueire Lins, Darlisson Marinho de Jesus, Marcos Martins de Almeida, Rodrigo Barros Bernardino, Bruno Lima |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2017 |
Předmět: |
Channel (digital image)
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 0102 computer and information sciences 02 engineering and technology lcsh:Computer applications to medicine. Medical informatics 01 natural sciences Grayscale lcsh:QA75.5-76.95 Handwriting 0202 electrical engineering electronic engineering information engineering Radiology Nuclear Medicine and imaging Computer vision lcsh:Photography Electrical and Electronic Engineering information_technology_data_management back-to-front interference business.industry Bandwidth (signal processing) Process (computing) Pattern recognition Filter (signal processing) bleeding lcsh:TR1-1050 Computer Graphics and Computer-Aided Design 010201 computation theory & mathematics ComputingMethodologies_DOCUMENTANDTEXTPROCESSING RGB color model lcsh:R858-859.7 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Bilateral filter Artificial intelligence lcsh:Electronic computers. Computer science binarization business Algorithm documents |
Zdroj: | Journal of Imaging, Vol 4, Iss 2, p 27 (2018) Journal of Imaging; Volume 4; Issue 2; Pages: 27 |
Popis: | Monochromatic documents claim for much less computer bandwidth for network transmission and storage space than their color or even grayscale equivalent. The binarization of historical documents is far more complex than recent ones as paper aging, color, texture, translucidity, stains, back-to-front interference, kind and color of ink used in handwritting, printing process, digitalization process, etc. are some of the factors that affect binarization. This article presents a new binarization algorithm for historical documents. The new global filter proposed is performed in four steps: filtering the image using a bilateral filter, splitting image into the RGB components, decision-making for each RGB channel based on an adaptive binarization method inspired by Otsu's method with a choice of the threshold level, and classification of the binarized images to decide which of the RGB components best preserved the document information in the foreground. The quantitative and qualitative assessment made with 21 binarization algorithms in three sets of “real world” documents showed very good results. |
Databáze: | OpenAIRE |
Externí odkaz: |