Abstract
This paper presents a novel approach to binarizing document images. All blocks with individual background intensity values in a document image are first extracted using a two-stage extraction procedure. Then, the intensity distribution of each block is calculated to determine the variation ranges of background intensity. For each extracted block, interior pixels whose intensity values fall within these ranges are regarded as background pixels. For those pixels outside all extracted blocks, Otsu’s global threshold method is applied to binarize them. To evaluate the developed system, 275 representative document images are collected to evaluate the binarization results by recognizing characters extracted from those binarized images. These binarized images are generated using the proposed and other existent approaches and fed into the same optical character recognition system to evaluate the practicability of each method. The proposed document binarization method obtains the highest recognition accuracy.
Similar content being viewed by others
References
Lee SU, Chung SY (1990) A comparative performance study of several global thresholding techniques for segmentation. Comput Vis Graph 52:171–190
Otsu N (1979) A thresholding selection method from gray-scale histogram. IEEE T Syst Man Cyb 9:62–66
Kittler J, Illingworth J (1985) On threshold selection using clustering criteria. IEEE T Syst Man Cyb 15:652–655
Kapur JN, Sahoo PK, Wong AKC (1985) A new method for gray-level picture thresholding using the entropy of the histogram. Comput Vis Graph 29:273–285
Trier ØD, Taxt T (1995) Evaluation of binarization methods for document images. IEEE Trans Pattern Anal 17(3):312–315
Trier ØD, Jain AK (1995) Goal-directed evaluation of binarization method. IEEE Trans Pattern Anal 17(12):1191–1201
Niblack W (1986) An introduction to digital image processing. Prentice Hall, New Jersey, pp 115–116
Bernsen J (1986) Dynamic thresholding of gray-level images. In: Proc Int Conf on Pat Recog, pp 1251–1255
Tabbone S, Wendling L (2000) Multi-scale binarization of images. Pattern Recognit Lett 24(1–3):927–943
Sauvola J, Pietikainen M (2000) Adaptive document image binarization. Pattern Recognit 33(2):225–236
Dawoud A, Kamel MS (2004) Iterative multimodel subimage binarization for handwritten character segmentation. IEEE Trans Image Process 13(9):1223–1230
Murtagh F, Starck JL (2003) Quantization from Bayes factors with application to multilevel thresholding. Pattern Recognit Lett 24(12):2001–2007
O’Gorman L (1994) Binarization and multithresholding of document images using connectivity. Graph Model Im Proc 56(6):494–506
Chang CC, Wang LL (1997) A fast multilevel thresholding method based on lowpass and highpass filtering. Pattern Recognit Lett 18(14):1469–1478
Sezgin M, Tasaltin R (2000) A new dichotomization technique to multilevel thresholding devoted to inspection applications. Pattern Recognit Lett 21(2):151–161
Gonzalez RC, Woods RE (2002) Digital image processing, 2/E. Prentice-Hall, New Jersey, pp 578–579
Tseng YH, Kuo CC, Lee HJ (1998) Speeding up Chinese character recognition in an automatic document reading system. Pattern Recognit 31(11):1601–1612
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tseng, YH., Lee, HJ. Document image binarization by two-stage block extraction and background intensity determination. Pattern Anal Applic 11, 33–44 (2008). https://doi.org/10.1007/s10044-007-0077-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-007-0077-7