Towards the Rectification of Highly Distorted Texts

Stefania Calarasanu, Séverine Dubuisson, Jonathan Fabrizio


A frequent challenge for many Text Understanding Systems is to tackle the variety of text characteristics in born-digital and natural scene images to which current OCRs are not well adapted. For example, texts in perspective are frequently present in real-word images, but despite the ability of some detectors to accurately localize such text objects, the recognition stage fails most of the time. Indeed, most OCRs are not designed to handle text strings in perspective but rather expect horizontal texts in a parallel-frontal plane to provide a correct transcription. In this paper, we propose a rectification procedure that can correct highly distorted texts, subject to rotation, shearing and perspective deformations. The method is based on an accurate estimation of the quadrangle bounding the deformed text in order to compute a homography to transform this quadrangle (and its content) into a horizontal rectangle. The rectification is validated on the dataset proposed during the ICDAR 2015 Competition on Scene Text Rectification.


  1. Almazan, J., Fornes, A., and Valveny, E. (2013). Deformable hog-based shape descriptor. In ICDAR, pages 1022-1026.
  2. Busta, M., Drtina, T., Helekal, D., Neumann, L., and Matas, J. (2015). Efficient character skew rectification in scene text images. In ACCV, pages 134-146.
  3. Calarasanu, S., Fabrizio, J., and Dubuisson, S. (2015). Using histogram representation and earth mover's distance as an evaluation tool for text detection. In ICDAR.
  4. Cambra, A. and Murillo, A. (2011). Towards robust and efficient text sign reading from a mobile phone. In ICCV, pages 64-71.
  5. Chen, X., Yang, J., Zhang, J., and Waibel, A. (2004). Automatic detection and recognition of signs from natural scenes. TIP, 13(1):87-99.
  6. Clark, P., Mirmehdi, D., and Doermann, D. (2001). Recognizing text in real scenes. IJDAR, 4:243-257.
  7. Fan, K. C. and Huang, C. H. (2005). Italic detection and rectification. JISE, 23:403-419.
  8. Ferreira, S., Garin, V., and Gosselini, B. (2005). A text detection technique applied in the framework of a mobile camera-based application. In CBDAR, pages 133-139.
  9. Hase, H., Yoneda, M., Shinokawa, T., and Suen, C. (2001). Alignment of free layout color texts for character recognition. In ICDAR, pages 932-936.
  10. Kiran, A. G. and Murali, S. (2013). Automatic rectification of perspective distortion from a single image using plane homography. IJCSA, 3(5):47-58.
  11. Li, L. and Tan, C. (2008). Character recognition under severe perspective distortion. In ICPR.
  12. Liang, J., DeMenthon, D., and Doermann, D. (2008). Geometric rectification of camera-captured document images. PAMI, 30(4):591-605.
  13. C. and Wang, B. (2015). Icdar 2015 competition on scene text rectification.
  14. str/.
  15. Lu, S. and Tan, C. (2006). Camera text recognition based on perspective invariants. In ICPR, volume 2, pages 1042-1045.
  16. Merino-Gracia, C., Mirmehdi, M., Sigut, J., and GonzálezMora, J. L. (2013). Fast perspective recovery of text in natural scenes. IVC, 31(10):714-724.
  17. Myers, G., Bolles, R., Luong, Q.-T., Herson, J., and Aradhye, H. (2005). Rectification and recognition of text in 3-d scenes. IJDAR, 7(2-3):147-158.
  18. Phan, T. Q., Shivakumara, P., Tian, S., and Tan, C. L. (2013). Recognizing text with perspective distortion in natural scenes. In ICCV, pages 569-576.
  19. Santosh, K. and Wendling, L. (2015). Character recognition based on non-linear multi-projection profiles measure. FCS, 9(5):678-690.
  20. Smith, R. (2007). An overview of the tesseract ocr engine. In ICDAR, pages 629-633.
  21. Stamatopoulos, N., Gatos, B., Pratikakis, I., and Perantonis, S. (2011). Goal-oriented rectification of camera-based document images. TIP, 20(4):910-920.
  22. Yao, C. (2012). Detecting texts of arbitrary orientations in natural images. In CVPR, pages 1083-1090.
  23. Ye, Q., Jiao, J., Huang, J., and Yu, H. (2007). Text detection and restoration in natural scene images. VCIR, 18(6):504-513.
  24. Yonemoto, S. (2014). A method for text detection and rectification in real-world images. InICIV, pages 374-377.
  25. Zhang, L., Lu, Y., and Tan, C. (2004). Italic font recognition using stroke pattern analysis on wavelet decomposed word images. In ICPR, volume 4, pages 835-838.
  26. Zhang, X., Lin, Z., Sun, F., and Ma, Y. (2013). Rectification of optical characters as transform invariant low-rank textures. In ICDAR, pages 393-397.
  27. Zhou, P., Li, L., and Tan, C. (2009). Character recognition under severe perspective distortion. In ICDAR, pages 676-680.

Paper Citation

in Harvard Style

Calarasanu S., Dubuisson S. and Fabrizio J. (2016). Towards the Rectification of Highly Distorted Texts . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 241-248. DOI: 10.5220/0005772602410248

in Bibtex Style

author={Stefania Calarasanu and Séverine Dubuisson and Jonathan Fabrizio},
title={Towards the Rectification of Highly Distorted Texts},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},

in EndNote Style

JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - Towards the Rectification of Highly Distorted Texts
SN - 978-989-758-175-5
AU - Calarasanu S.
AU - Dubuisson S.
AU - Fabrizio J.
PY - 2016
SP - 241
EP - 248
DO - 10.5220/0005772602410248