Automatic rectification of warped Bangla document images

Access Full Text

Automatic rectification of warped Bangla document images

For access to this article, please select a purchase option:

Buy article PDF
$19.95
(plus tax if applicable)
Add to cart
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)
Add to cart

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Image Processing — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

© The Institution of Engineering and Technology
Received 01/07/2019, Accepted 02/10/2019, Revised 16/09/2019, Published 08/10/2019

In this study, a robust algorithm for dewarping of camera-captured document images, mainly in Bangla script, is proposed. The algorithm can handle various types of warped document images and they are generated due to different types of document surfaces (convex, concave or multi-folded). The proposed algorithm is independent of font type, font size, font style and camera view angle. After initial preprocessing, the method first demarcates the text lines present in the document image. Then, the headline (shirorekha) position of each text line is estimated. Based on the headline position and shape, each text line is dewarped. If the document is highly warped, distorted text (e.g. thinner and shorter characters) is generated after dewarping. Special care has been taken to minimise this distortion based on most undistorted character information. Exhaustive testing shows the robustness and shape improvement of the proposed algorithm. Finally, for shape quality evaluation, some new measures are defined.

Inspec keywords: natural language processing; document image processing; cameras; text analysis

Other keywords: distorted text; dewarping; shape improvement; text line; warped Bangla document images; Bangla script; camera-captured document images; document image; automatic rectification; robust algorithm; camera view angle; font type; document surfaces; headline position; font style; font size

Subjects: Computer vision and image processing techniques; Natural language processing; Document processing techniques; Optical, image and video signal processing; Image sensors

References

    1. 1)
      • 16. Lu, S., Tan, C.L.: ‘Document flattening through grid modeling and regularization’. 18th Int. Conf. on Pattern Recognition (ICPR'06), Florida, USA, 2006, vol. 1, pp. 971–974.
    2. 2)
      • 6. Brown, M.S., Seales, W.B.: ‘Image restoration of arbitrarily warped documents’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (10), pp. 1295–1306.
    3. 3)
      • 32. Premchaiswadi, N., Yimgnagm, S., Premchaiswadi, W.: ‘A scheme for salt and pepper noise reduction and its application for ocr systems’, W. Trans. Comput, 2010, 9, (4), pp. 351–360.
    4. 4)
      • 40. Gatos, B., Louloudis, G., Stamatopoulos, N.: ‘Segmentation of historical handwritten documents into text zones and text lines’. 2014 14th Int. Conf. on Frontiers in Handwriting Recognition, Crete, Greece, 2014, pp. 464–469.
    5. 5)
      • 42. Vo, Q.N., Kim, S.H., Yang, H.J., et al: ‘Text line segmentation using a fully convolutional network in handwritten document images’, IET Image Process., 2017, 12, (3), pp. 438–446.
    6. 6)
      • 17. Ulges, A., Lampert, C.H., Breuel, T.M.: ‘Document image dewarping using robust estimation of curled text lines’. Eighth Int. Conf. on Document Analysis and Recognition (ICDAR'05), Seoul, South Korea, 2005, vol. 2, pp. 1001–1005.
    7. 7)
      • 33. Leung, C.C., Chan, K.S., Chan, H.M., et al: ‘A new approach for image enhancement applied to low-contrast–low-illumination ic and document images’, Pattern Recognit. Lett., 2005, 26, (6), pp. 769–778.
    8. 8)
      • 26. Su, B., Lu, S., Tan, C.L.: ‘Robust document image binarization technique for degraded document images’, IEEE Trans. Image Process., 2013, 22, (4), pp. 1408–1417.
    9. 9)
      • 43. Green, P.J., Silverman, B.W.: ‘Nonparametric regression and generalized linear models: a roughness penalty approach’ (Taylor & Francis group: Chapman and Hall/CRC, UK, 1993).
    10. 10)
      • 22. Kil, T., Seo, W., Koo, H.I., et al: ‘Robust document image dewarping method using text-lines and line segments’. 2017 14th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017, vol. 1, pp. 865–870.
    11. 11)
      • 35. Shafait, F., Breuel, T.M.: ‘A simple and effective approach for border noise removal from document images’. 2009 IEEE 13th Int. Multitopic Conf., Islamabad, Pakistan, 2009, pp. 1–5.
    12. 12)
      • 21. Kim, B.S., Koo, H.I., Cho, N.I.: ‘Document dewarping via text-line based optimization’, Pattern Recognit., 2015, 48, (11), pp. 3600–3614.
    13. 13)
      • 2. Shafait, F.: ‘Document image dewarping contest’. 2nd Int. Workshop on Camera-Based Document Analysis and Recognition, Curitiba, Brazil, 2007, pp. 181–188.
    14. 14)
      • 13. You, S., Matsushita, Y., Sinha, S., et al: ‘Multiview rectification of folded documents’, IEEE Trans. Pattern Anal. Mach. Intell., 2018, 40, (99), pp. 505–511.
    15. 15)
      • 28. Said, J.N., Cheriet, M., Suen, C.Y.: ‘Dynamical morphological processing: a fast method for base line extraction’. Proc. of 13th Int. Conf. on Pattern Recognition, Vienna, Austria, 1996, vol. 2, pp. 8–12.
    16. 16)
      • 3. Bukhari, S.S., Shafait, F., Breuel, T.M.: ‘The iupr dataset of camera-captured document images’. 4th Int. Conf. on Camera-based Document Analysis and Recognition (CBDAR 2011), Beijing, China, 2011, pp. 164–171.
    17. 17)
      • 27. Farahmand, A., Sarrafzadeh, A., Shanbehzadeh, J.: ‘Document image noises and removal methods’. Int. Multi Conf. of Engineers and Computer Scientists (IMECS 2013), Hong Kong, 2013, vol. 1, pp. 436–440.
    18. 18)
      • 44. Bukhari, S.S., Shafait, F., Breuel, T.M.: ‘Coupled snakelets for curled text-line segmentation from warped document images’, Int. J. Doc. Anal. Recognit. (IJDAR), 2013, 16, (1), pp. 33–53.
    19. 19)
      • 4. Ke, M., Zhixin, S., Bai, X., et al: ‘Docunet: document image unwarping via a stacked u-net’. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Utah, USA, 2018.
    20. 20)
      • 7. Yamashita, A., Kawarago, A., Kaneko, T., et al: ‘Shape reconstruction and image restoration for non-flat surfaces of documents with a stereo vision system’. Proc. of the 17th Int. Conf. on Pattern Recognition, 2004, ICPR 2004, Cambridge, UK, 2004, vol. 1, pp. 482–485.
    21. 21)
      • 11. Meng, G., Pan, C., Xiang, S., et al: ‘Metric rectification of curved document images’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (4), pp. 707–722.
    22. 22)
      • 38. Bukhari, S.S., Shafait, F., Breuel, T.M.: ‘Border noise removal of camera-captured document images using page frame detection’. In, Iwamura, M., Shafait, F. (Eds.): ‘Camera-based document analysis and recognition’ (Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, pp. 126–137.
    23. 23)
      • 10. Zhang, L., Tan, C.L.: ‘Restoringwarped document images using shape-from-shading and surface interpolation’. 18th Int. Conf. on Pattern Recognition (ICPR'06), Hong Kong, China, 2006, vol. 1, pp. 642–645.
    24. 24)
      • 24. Pratikakis, I., Zagoris, K., Barlas, G., et al: ‘Icdar2017 competition on document image binarization (dibco 2017)’. 2017 14th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017, vol. 1, pp. 1395–1403.
    25. 25)
      • 36. Shafait, F., van Beusekom, J., Keysers, D., et al: ‘Document cleanup using page frame detection’, Int. J. Doc. Anal. Recognit. (IJDAR), 2008, 11, (2), pp. 81–96.
    26. 26)
      • 23. Yang, P.: ‘Effective geometric restoration of distorted historical document for large-scale digitisation’, IET Image Process., 2017, 11, (12), pp. 841–853.
    27. 27)
      • 18. Gatos, B., Pratikakis, I., Ntirogiannis, K.: ‘Segmentation based recovery of arbitrarily warped document images’. Ninth Int. Conf. on Document Analysis and Recognition (ICDAR 2007), Curitiba, Brazil, 2007, vol. 2, pp. 989–993.
    28. 28)
      • 8. Fu, B., Li, W., Wu, M., et al: ‘A document rectification approach dealing with both perspective distortion and warping based on text flow curve fitting’, Int. J. Image. Graph., 2012, 12, (1), p. 1250002.
    29. 29)
      • 1. Liu, C., Zhang, Y., Wang, B., et al: ‘Restoring camera-captured distorted document images’, Int. J. Doc. Anal. Recognit. (IJDAR), 2015, 18, (2), pp. 111–124.
    30. 30)
      • 14. He, Y., Pan, P., Xie, S., et al: ‘A book dewarping system by boundary-based 3d surface reconstruction’. 2013 12th Int. Conf. on Document Analysis and Recognition, Washington, D.C., USA, 2013, pp. 403–407.
    31. 31)
      • 9. Cao, H., Ding, X., Liu, C.: ‘A cylindrical surface model to rectify the bound document image’. Proc. Ninth IEEE Int. Conf. on Computer Vision, Nice, France, 2003, vol. 1, pp. 228–233.
    32. 32)
      • 41. Moysset, B., Louradour, J., Kermorvant, C., et al: ‘Learning text-line localization with shared and local regression neural networks’. 2016 15th Int. Conf. on Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China, 2016, pp. 1–6.
    33. 33)
      • 20. Stamatopoulos, N., Gatos, B., Pratikakis, I., et al: ‘Goal-oriented rectification of camera-based document images’, IEEE Trans. Image Process., 2011, 20, (4), pp. 910–920.
    34. 34)
      • 5. Garai, A., Biswas, S., Mandal, S., et al: ‘Automatic dewarping of camera captured born-digital Bangla document images’. 2017 Ninth Int. Conf. on Advances in Pattern Recognition (ICAPR), Bangalore, India, 2017, pp. 1–6.
    35. 35)
      • 39. Rath, T.M., Manmatha, R.: ‘Word image matching using dynamic time warping’. 2003 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Proc., 2003, vol. 2, pp. II–II.
    36. 36)
      • 34. Dutta, A., Garai, A., Biswas, S.: ‘Segmentation of meaningful text-regions from camera captured document images’. 2018 Fifth Int. Conf. on Emerging Applications of Information Technology (EAIT), Howrah, India, 2018, pp. 1–4.
    37. 37)
      • 29. Dey, S., Mitra, B., Mukhopadhyay, J., et al: ‘A comparative study of margin noise removal algorithms on marnr: a margin noise dataset of document images’. 2017 14th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017, vol. 4, pp. 35–39.
    38. 38)
      • 37. Dey, S., Mukhopadhyay, J., Sural, S., et al: ‘Margin noise removal from printed document images’. Proc. of the Workshop on Document Analysis and Recognition. DAR‘12, New York, NY, USA, 2012, pp. 86–93.
    39. 39)
      • 19. Bukhari, S.S., Shafait, F., Breuel, T.M.: ‘Dewarping of document images using coupled-snakes’. Proc. of Third Int. Workshop on Camera-Based Document Analysis and Recognition, Barcelona, Spain, 2009, pp. 34–41.
    40. 40)
      • 30. Fan, H., Zhu, L., Tang, Y.: ‘Skew detection in document images based on rectangular active contour’, Int. J. Doc. Anal. Recognit. (IJDAR), 2010, 13, (4), pp. 261–269.
    41. 41)
      • 31. Agrawal, M., Doermann, D.: ‘Stroke-like pattern noise removal in binary document images’. 2011 Int. Conf. on Document Analysis and Recognition, Peking, China, 2011, pp. 17–21.
    42. 42)
      • 45. Stamatopoulos, N.: ‘Performance evaluation methodology for document image dewarping techniques’, IET Image Process., 2012, 6, (7), pp. 738–745.
    43. 43)
      • 25. Meng, G., Yuan, K., Wu, Y., et al: ‘Deep networks for degraded document image binarization through pyramid reconstruction’. 2017 14th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017, vol. 1, pp. 727–732.
    44. 44)
      • 12. Liang, J., DeMenthon, D., Doermann, D.: ‘Geometric rectification of camera-captured document images’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (4), pp. 591–605.
    45. 45)
      • 15. Ezaki, H., Uchida, S., Asano, A., et al: ‘Dewarping of document image by global optimization’. Eighth Int. Conf. on Document Analysis and Recognition (ICDAR'05), Seoul, South Korea, 2005, vol. 1, pp. 302–306.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.0831
Loading

Related content

content/journals/10.1049/iet-ipr.2019.0831
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading