Scientific Journal

Applied Aspects of Information Technology


Optical character recognition systems for the images are used to convert books and documents into electronic form, to automate accounting systems in business, when recognizing markers using augmented reality technologies and etс. The quality of optical character recognition, provided that binarization is applied, is largely determined by the quality of separation of the foreground pixels from the background.  Methods of text image binarization are analyzed and insufficient quality of binarization is noted. As a way of research the minimum-distance classifier for the improvement of the existing method of binarization of color text images is used. To improve the quality of the binarization of color text images, it is advisable to divide image pixels into two classes, “Foreground” and “Background”, to use classification methods instead of heuristic threshold selection, namely, a minimum-distance classifier. To reduce the amount of processed information before applying the classifier, it is advisable to select blocks of pixels for subsequent processing. This was done by analyzing the connected components on the original image. An improved method of the color text image binarization with the use of analysis of connected components and minimum-distance classifier has been elaborated. The research of the elaborated method showed that it is better than existing binarization methods in terms of robustness of binarization, but worse in terms of the error of the determining the boundaries of objects. Among the recognition errors, the pixels of images from the class labeled “Foreground” were more often mistaken for the class labeled “Background”. The proposed method of binarization with the uniqueness of class prototypes is recommended to be used in problems of the processing of color images of the printed text, for which the error in determining the boundaries of characters as a result of binarization is compensated by the thickness of the letters. With a multiplicity of class prototypes, the proposed binarization method is recommended to be used in problems of processing color images of handwritten text, if high performance is not required. The improved binarization method has shown its efficiency in cases of slow changes in the color and illumination of the text and background, however, abrupt changes in color and illumination, as well as a textured background, do not allowing the binarization quality required for practical problems.

  1. Ishchenko, O. V. “Rozrobka modulia intelektualnoi systemy obrobky vidskanovanykh dokumentiv na bazi kombinovanoho metodu sehmentatsii zobrazhen. Suchasnyi stan naukovykh doslidzhen ta tekhnolohii v promyslovosti”. The current state of research and technology in industry (in Ukrainian). 2019; No. 2(8):44–53. DOI: 10.30837/2522-9818.2019.8.044. 
  2. Ishchenko, A., Polyakova, M. & Nesteryuk, A. “The technique of extraction text areas on scanned document image using linear filtration”. Applied Aspects of Information TechnologyPubl. Science i Technical. Odesa: Ukraine.2019; No.2(3): 206-215. DOI: 10.15276/aait.03.2019.3.
  3. Polyakova, M., Ishchenko, A., Volkova, N. & Pavlov, O. “The combining segmentation method of the scanned documents images with sequential division of the photo, graphics, and the text areas”. Eastern- European Journal of Enterprise Technologies. 2018; No. 5/2 (95): 6–16. DOI: 10.15587/1729-4061.2018.142735.
  4. Ishchenko, A., Polyakova, M., Kuvaieva, V. & Nesteryuk, A. “Elaboration of structural representation of regions of scanned document images for MRC model”. Eastern-European Journal of Enterprise Technologies. 2018; No. 6/2 (96): 32–38. DOI: 10.15587/1729-4061.2018.147671.
  5. Polyakova, M. V., Dishlyuk, V. O. & Makovetskiy, O. S. “Mobilnyi dodatok na osnovi tekhnolohii dopovnenoi realnosti dlia navchannia anhliiskii movi ditei doshkilnoho viku”. Practical and theoretical nutritional development of science and education(part IIІ):materials of the 25th International Conference on Practical Science (in Ukrainian). 2020. Lviv: Lviv Science Forum. 2020. p.54–56. 
  6. Molchanova, V.S. “Adaptivnyj porogovyj metod binarizacii rastrovykh izobrazhenij tekhnicheskikh chertezhej”. Radioelectronika. Informatics. Management (in Russian). 2015; No. 2: 62–70. 
  7. Bolotova, Yu. A., Spitsyn, V. G. & Osina, P. M. “Obzor algoritmov detektirovaniya tekstovykh oblastej na izobrazheniyakh i videozapisyakh”. Computer optics (in Russian). 2017; Vol. 41, Issue 3: 441–452. 
  8. Almeida, M., Lins, R. D., Bernardino, R., Jesus, D. & Lima, B. “A new binarization algorithm for historical documents”. Journal of Imaging. 2018; Vol. 4, No. 27: 110–122. DOI: 10.3390 / jimaging4020027.
  9. Ostapov, D. S. “Binarizaciya “fon-ob’ekt” predobrabotkoj izobrazheniya i nechyotkim algoritmom k-means”. Bulletin of the Astrakhan State Technical University. Series: Management, computer technology and information (in Russian). 2016; No. 3: 32–39. 
  10.  Gonzalez, R. & Woods, R. “Digital Image processing (4th edition)”. London: Pearson Education. 2018. 1020 p. DOI / PMID / ISBN: 9780133356724.
  11.  Das, A. & Chowdhury, S. “Adaptive method for multi colored text binarization”. Proc. of theInt. Conf. on Systems, Signals and Image Processing (IWSSIP)(Poznan, Poland, 22-24 May, 2017). Poznan: Poland. 2017: p.359–366.
  12.  Chaban, S. V. & Polyakova, M. V. “Adaptyvna binaryzatsiia kolorovykh zobrazhen tekstu za dopomohoiu metodu Otsu”. Program, Project, Portfolio p3management: materials of the IV International Scientific and Practical Conference (Odessa, 6 – 7 December, 2019) (in Ukrainian). Odessa, 2019. p. 22–28. 
  13. Savuola, J. & Pietikainen, M. “Adaptive document image binarization”. Pattern Recognition. 2000; Vol. 33, No. 2: 225–236.
  14.  Gatos, B., Pratikakis, I. & Perantonis, S. “Adaptive degraded document image binarization”. Pattern Recognition. 2006; Vol. 39, No. 3: 317–327.
  15.  Biswas, B., Bhattacharya, U. & Chaudhuri, B. B. “A global-to-local approach to binarization of degraded document images”. Proc. of the 22nd Int. Conf. on Pattern Recognition (Stockholm, Sweden, 24–28 August, 2014). Washington: 2014. p. 3008–3013.
  16.  Kasar, T., Kumar, J. & Ramakrishnan, A. G. “Font and background color independent text binarization”. Proc. of the 2nd Int. Workshop on Camera-Based Document Analysis and Recognition (Curitiba, Brazil, September 22, 2007). Washington: 2007. p. 3–9.
  17.  Israfilov, Kh. S. “Investigation of methods for binarization of images”. Bulletin of Science and Education (in Russian). 2017; Vol. 2, No. 6 (30): 14–19. 
  18.  Vats, E., Hast, A. & Singh, P. “Automatic Document Image Binarization using Bayesian Optimization”. 4th International Workshop on Historical Document Imaging and Processing (HIP2017). ACM. New York: NY, USA. 2017: p.89–94. DOI: 10.1145 / 3151509.3151520
  19.  Su, B., Lu, S. & Tan, C. L. “Combination of Document Image Binarization Techniques”. 2011 International Conference on Document Analysis and Recognition. Beijing: China. 2011: p.22–26. DOI: 10.1109 / ICDAR.2011.14.
  20.  Tu, J. & Gonzalez, R. “Principy raspoznavaniya obrazov”. Publ.  Mir (in Russian). Moscow: Russian Federation. 1978. 412 p. 
  21.  Canny, J. “A computational approach to edge detection”. IEEE Trans. on PAMI. 1986; Vol.8: 679–698.
  22.  Akinlar, C. & Topal, C. “Color ED: Color edge and segment detection by Edge Drawing (ED)”. Journal of Visual Communication and Image Representation. 2017; Vol. 44: 82–94.
  23.  Gatos, B., Ntirogiannis, K. & Pratikakis, I. “DIBCO 2009: document image binarization contest”. Int. Journal on Document Analysis and Recognition. 2011; Vol. 14, No. 1: 35–44.
  24.  Michalak, H. & Okarma, K. “Improvement of Image Binarization Methods Using Image Preprocessing with Local Entropy Filtering for Alphanumerical Character Recognition Purposes”. Entropy. 2019; 21 (6): 562 p. DOI:
  25.  Michalak, H. & Okarma, K. “Optimization of Degraded Document Image Binarization Method Based on Background Estimation”. 28th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision WSCG 2020. Pilsen: Czech Republic. Journal of WSCG28 (1-2). p.89-98. DOI: 10.24132 / CSRN.2020.3001.11.
  26.  Sehad, A. “Ancient degraded document image binarization based on texture features”. 8th International Symposium on Image and Signal Processing and Analysis, ISPA 2013, Trieste: Italy. September 4-6, 2013. p.189-193. DOI:10.1109 / ISPA.2013.6703737.
  27.  Sehad, A., Chibani, Y., Hedjam, R. & Cheriet, M. “Gabor filter-based texture for ancient degraded document image binarization”. Pattern Analysis and Applications. 2019; Vol. 22: 1–22. DOI:
  28.  Sulaiman, A., Omar, K. & Nasrudin, M. F. “Degraded Historical Document Binarization: A Review on Issues, Challenges, Techniques, and Future Directions”. Journal of Imaging. 2019; No. 5 (4): 48–73 DOI:10.3390 / jimaging5040048.
  29.  Bukhari, S. S., Shafait, F. & Breuel, T. “Improved document image segmentation algorithm using multiresolution morphology”. In Proc. of the 18th Document Recognition and Retrieval Conf., Document Recognition and Retrieval XVIII - DRR 2011. San Jose: CA, USA. 2011. DOI: 10.1117 / 12.873461.
  30.  Polyakova, M., Ishchenko, A. & Huliaieva, N. “Document image segmentation using averaging filtering and mathematical morphology”. 14th International Conference on Advanced Trends in Radioelecrtronics. Telecommunications and Computer Engineering (TCSET). Lviv-Slavske: Ukraine. 2018. p.966-969. DOI:
Last download:
10 May 2021


[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2018.]