READING STREET SIGNS USING A GENERIC STRUCTURED OBJECT DETECTION AND SIGNATURE RECOGNITION APPROACH

Sobhan Naderi Parizi, Alireza Tavakoli Targhi, Omid Aghazadeh, Jan-Olof Eklundh

2009

Abstract

In the paper we address the applied problem of detecting and recognizing street name plates in urban images by a generic approach to structural object detection and recognition. A structured object is detected using a boosting approach and false positives are filtered using a specific method called the texture transform. In a second step the subregion containing the key information, here the text, is segmented out. Text is in this case characterized as texture and a texton based technique is applied. Finally the texts are recognized by using Dynamic Time Warping on signatures created from the identified regions. The recognition method is general and only requires text in some form, e.g. a list of printed words, but no image models of the plates for learning. Therefore, it can be shown to scale to rather large data sets. Moreover, due to its generality it applies to other cases, such as logo and sign recognition. On the other hand the critical part of the method lies in the detection step. Here it relied on knowledge about the appearance of street signs. However, the boosting approach also applies to other cases as long as the target region is structured in some way. The particular scenario considered deals with urban navigation and map indexing by mobile users, e.g. when the images are acquired by a mobile phone.

References

  1. Adamek, T., OConnor, N., and Smeaton, A. (2007). Word matching using single closed contours for indexing handwritten historical documents. In International Journal on Document Analysis and Recognition.
  2. Ataer, E. and Duygulu, P. (2007). Matching ottoman words: an image retrieval approach to historical document indexing. In Proc. ACM international conference on Image and video retrieval.
  3. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proc. Computer Vision and Pattern Recognition.
  4. Freund, Y. and Schapire, R. (1995). A decision-theoretic generalization of on-line learning and an application to boosting. In Proc. European Conference on Computational Learning Theory.
  5. Ganapathi, T. and Lourde, R. (2006). Thresholding and character recognition from a digital raster image. In Proc. International Confrence on System of Systems Engineering.
  6. Ishidera, E., Lucas, S., and Downton, A. (2002). Likelihood word image generation model for word recognition. In Proc. International Conference on Pattern Recognition.
  7. Kim, K., Jung, K., and Kim, J. (2003). Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm. In IEEE Transactions on Pattern Analysis and Machine Intelligence.
  8. Laptev, I. (2006). Improvements of object detection using boosted histograms. In Proc. British Machine Vision Conference.
  9. Leon, M., Mallo, S., and Gasull, A. (2005). A tree structured-based caption text detection approach. In In Fifth IASTED VIIP.
  10. Merino, C. and Mirmehdi, M. (2007). A framework towards realtime detection and tracking of text. In International Workshop on Camera-Based Document Analysis and Recognition.
  11. Ojala, T., Pietikinen, M., and Menp, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. In IEEE Transactions on Pattern Analysis and Machine Intelligence.
  12. Papageorgiou, C., Oren, M., and Poggio, T. (1998). A general framework for object detection. In Proc. International Conference on Computer Vision.
  13. Rath, T. and Manmatha, R. (2003). Word image matching using dynamic time warping. In Proc. Computer Vision and Pattern Recognition confrence.
  14. Ratti, C., Sevtsuk, A., Huang, S., and Pailer, R. (2007). Mobile landscapes: Graz in real time. In Location Based Services and TeleCartography.
  15. Sakoe, H. and Chiba, S. (1990). Dynamic programming algorithm optimization for spoken word recognition. In Readings in speech recognition.
  16. Schroff, F., Criminisi, A., and Zisserman, A. (2006). Singlehistogram class models for image segmentation. In Computer Vision, Graphics and Image Processing.
  17. Shanker, A. and Rajagopalan, A. (2007). Off-line signature verification using dtw. In Pattern Recognition Letters.
  18. Shapiro, V. and Gluhchev, G. (2004). Multinational license plate recognition system: Segmentation and classification. In Proc. International Conference on Pattern Recognition.
  19. Shapiro, V., Gluhchev, G., and Dimov, D. (2006). Towards a multinational car license plate recognition system. In Machine Vision and Applications.
  20. Tavakoli, A., Bjrkman, M., Hayman, E., and Eklundh, J. (2006). Real-time texture detection using the lutransform. In In Workshop on Computation Intensive Methods for Computer Vision.
  21. Tavakoli, A., GeuseBroek, J., and Zisserman, A. (2008). Texture classification with minimal training images. In Proc. International Conference on Pattern Recognition.
  22. Varma, M. and Zisserman, A. (2003). Texture classification: Are filter banks necessary? In Proc. Computer Vision and Pattern Recognition confrence.
  23. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proc. Accepted Confrence on Computer Vision and Pattern Recognition.
  24. Yan, D., Hongqing, M., Jilin, L., and Langang, L. (2001). A high performance license plate recognition system based on the web technique. In Proc. Intelligent Transportation Systems confrence.
  25. Ye, Q., Jiao, J., Huang, J., and Yu, H. (2007). Text detection and restoration in natural scene images. In Journal of Visual Communication and Image Representation.
Download


Paper Citation


in Harvard Style

Naderi Parizi S., Tavakoli Targhi A., Aghazadeh O. and Eklundh J. (2009). READING STREET SIGNS USING A GENERIC STRUCTURED OBJECT DETECTION AND SIGNATURE RECOGNITION APPROACH . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 346-355. DOI: 10.5220/0001797703460355


in Bibtex Style

@conference{visapp09,
author={Sobhan Naderi Parizi and Alireza Tavakoli Targhi and Omid Aghazadeh and Jan-Olof Eklundh},
title={READING STREET SIGNS USING A GENERIC STRUCTURED OBJECT DETECTION AND SIGNATURE RECOGNITION APPROACH},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={346-355},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001797703460355},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - READING STREET SIGNS USING A GENERIC STRUCTURED OBJECT DETECTION AND SIGNATURE RECOGNITION APPROACH
SN - 978-989-8111-69-2
AU - Naderi Parizi S.
AU - Tavakoli Targhi A.
AU - Aghazadeh O.
AU - Eklundh J.
PY - 2009
SP - 346
EP - 355
DO - 10.5220/0001797703460355