Speed-up Line Detection Approach for Large-size Document Images by Parallel Pixel Scanning and Hough Space Minimization

H. Waruna H. Premachandra, Chinthaka Premachandra, Chandana Dinesh Parape, Hiroharu Kawanaka

Abstract

Hough transform (HT) is typically used to detect lines in images, but that method is slow due to its use of voting-based parameter detection; detecting lines in large document images can take dozens of minutes. Nonetheless HT is very effective at detecting lines, so we investigate methods for fast HT-based line detection of large document images by minimizing Hough space processing and reducing the image area used for line detection with parallel pixel scanning and local image domain analysis. We conduct experiments to confirm the effectiveness of the proposed method using appropriate large documents images. The results show a significant computational time reduction as compared to conventional methods.

References

  1. Jin, S.,You, Y., Huafen, Y., 2010. Scanned Document Image Processing Model for Information System, AsiaPacific Conf. on Wearable Computing Systems.
  2. Wang, Q., Chi, Z., Zhao, R., 2002. Hierarchical content classification and script determination for automatic document image processing, 16th International Conference on Pattern Recognition.
  3. Yip, S. K., Chi, Z., 2001. Page segmentation and content classification for automatic document image processing, IEEE International Conference on Computational Intelligence and Computing Research (ICCIC).
  4. Manikandan, V., Venkatachalam, V., Kirthiga, M., Harini, K., Devarajan, N., 2010. An enhanced algorithm for Character Segmentation in document image processing , IEEE International Conference on Computational Intelligence and Computing Research (ICCIC).
  5. Yang, Y., Yan, H., 2000. A robust documefdotnt processing system combining image segmentation with contentbased document compression, 15th International Conference on Pattern Recognition.
  6. Borges, P. V. K., Mayer, J., Izquierdo, E., 2008. Document Image Processing for Paper Side Communications, IEEE Transactions on Multimedia,” Vol. 10, Issue 7, pp. 1277-1287.
  7. Shi, Z., Setlur, S., Govindaraju, V. 2013. A Model Based Framework for Table Processing in Degraded Document Images, 12th International Conference on Document Analysis and Recognition (ICDAR).
  8. Takasu, A., Satoh, S., E. Katsura, E., 1995. A rule learning method for academic document image processing, Third International Conference on Document Analysis and Recognition.
  9. Premachandra, H. W.H., Premachandra, C., Parape, C. D., 2013. Parallel Scanning Based Speed-up Method for Detection of Elliptical Obstacles in High-resolution Image, International Journal of Computer Science and Communication Networks, Vol. 3, Issue5, pp.265-270.
  10. Premachandra, C.,Premachandra, H. W.H., Parape, C. D., Kawanaka, H., 2014. Parallel Layer Scanning Based Fast Dot/Dash Line Detection Algorithm for Large Scale Binary Document Images, Lecture Notes in Computer Science (LNCS), Vol. 8814.
  11. Premachandra, H. W.H., Premachandra, C., Parape, C. D., Kawanaka, H., 2015. Speed-up Ellipse Detection Approach for Large Document Images by Parallel Scanning and Hough Transform, International Journal of Machine Learning and Cybernetics.
  12. Li, W. C., Tsai, D. M., 2011. Defect Inspection in LowContrast LCD Images Using Hough Transform-Based Nonstationary Line Detection, IEEE Transactions on Industrial Informatics, Vol. 7, Issue 1, pp.136-147.
  13. Zhao, X., Liu, P., Zhang, M., Zhao, X., 2010. A novel line detection algorithm in images based on improved Hough Transform and wavelet lifting transform, IEEE International Conference on Information Theory and Information Security (ICITIS).
  14. Aggarwal, N., Karl, W. C., 2006. Line detection in images through regularized hough transform, IEEE Transactions on Image Processing, Vol. 15, Issue 3, pp.582-591.
  15. Lefevre, S., Dixon, C., Jeusse, C., Vincent, N., 2002. A Local Approach for Fast Line Detection, IEEE International Conference on Digital Signal Processing.
  16. Kawanaka, H., Sumida, T., Yamamoto, K., Shinogi, T.,Tsuruoka, S., 2007. Document Recognition and XML Generation of Tabular Form Discharge Summaries for Analogous Case Search System, Method Inf. Med., Vol. 46, pp. 700-708.
  17. Otsu., N., Lopes, J., 1999. Threshold Detection Method from Grey-Level Histograms, IEEE Trans. Systems, Man, and Cybernities,Vol. 9 No.1, pp.62-66.
Download


Paper Citation


in Harvard Style

Premachandra H., Premachandra C., Parape C. and Kawanaka H. (2016). Speed-up Line Detection Approach for Large-size Document Images by Parallel Pixel Scanning and Hough Space Minimization . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISION4HCI, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 765-769. DOI: 10.5220/0005840707650769


in Bibtex Style

@conference{vision4hci16,
author={H. Waruna H. Premachandra and Chinthaka Premachandra and Chandana Dinesh Parape and Hiroharu Kawanaka},
title={Speed-up Line Detection Approach for Large-size Document Images by Parallel Pixel Scanning and Hough Space Minimization},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISION4HCI, (VISIGRAPP 2016)},
year={2016},
pages={765-769},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005840707650769},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISION4HCI, (VISIGRAPP 2016)
TI - Speed-up Line Detection Approach for Large-size Document Images by Parallel Pixel Scanning and Hough Space Minimization
SN - 978-989-758-175-5
AU - Premachandra H.
AU - Premachandra C.
AU - Parape C.
AU - Kawanaka H.
PY - 2016
SP - 765
EP - 769
DO - 10.5220/0005840707650769