TextTrail - A Robust Text Tracking Algorithm In Wild Environments

Myriam Robert-Seidowsky, Jonathan Fabrizio, Séverine Dubuisson

2015

Abstract

In this paper, we propose TextTrail, a new robust algorithm dedicated to text tracking in uncontrolled environments (strong motion of camera and objects, partial occlusions, blur, etc.). It is based on a particle filter framework whose correction step has been improved. First, we compare some likelihood functions and introduce a new one which integrates tangent distance. We show that this likelihood has a strong influence on the text tracking performances. Secondly, we compare our tracker with a similar one and finally an example of application is presented. TextTrail has been tested on real video sequences and has proven its efficiency. In particular, it can track texts in complex situations starting from only one detection step without needing another one to reinitialize the model.

References

  1. Bertalmio, M., Bertozzi, A. L., and Sapiro, G. (2001). Navier-stokes, fluid dynamics, and image and video inpainting. In CVPR, pages 355-362.
  2. Bhattacharyya, A. (1943). On a measure of divergence between two statistical populations defined by their probability distributions. Bulletin of Cal. Math. Soc., 35(1):99-109.
  3. Brasnett, P. and Mihaylova, L. (2007). Sequential monte carlo tracking by fusing multiple cues in video sequences. Image and Vision Computing, 25(8):1217- 1227.
  4. Breitenstein, M. D., Reichlin, F., Leibe, B., Koller-Meier, E., and Gool, L. V. (2009). Robust tracking-bydetection using a detector confidence particle filter. In ICCV, pages 1515-1522.
  5. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In CVPR, pages 886- 893.
  6. Fabrizio, J., Dubuisson, S., and Béréziat, D. (2012). Motion compensation based on tangent distance prediction for video compression. Signal Processing: Image Communication, 27(2):153-171.
  7. Fabrizio, J., Marcotegui, B., and M.Cord (2013). Text detection in street level image. Pattern Analysis and Applications, 16(4):519-533.
  8. Fontmarty, M., Lerasle, F., and Danes, P. (2009). Likelihood tuning for particle filter in visual tracking. In ICIP, pages 4101-4104.
  9. Gordon, N., Salmond, D., and Smith, A. (1993). Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc. of Radar and Signal Processing, 140(2):107-113.
  10. challenge 3: text localization in video. http://dag.
  11. cvc.uab.es/icdar2013competition/?ch=3.
  12. Levillain, R., Geraud, T., and Najman, L. (2010). Why and howto design a generic and efficient image processing framework: The case of the milena library. In ICIP, pages 1941-1944.
  13. Lichtenauer, J., Reinders, M., and Hendriks, E. (2004). Influence of the observation likelihood function on object tracking performance in particle filtering. In FG, pages 227-233.
  14. Lucas, S. M. (2005). Text locating competition results. In Proceedings of the Eighth International Conference on Document Analysis and Recognition, ICDAR 7805, pages 80-85.
  15. Macherey, W., Keysers, D., Dahmen, J., and Ney, H. (2001). Improving automatic speech recognition using tangent distance. In ECSCT, volume III, pages 1825-1828.
  16. Mariani, R. (2002). A face location and recognition system based on tangent distance. In Multimodal interface for human-machine communication, pages 3-31. World Scientific Publishing Co., Inc.
  17. Medeiros, H., Holgun, G., Shin, P. J., and Park, J. (2010). A parallel histogram-based particle filter for object tracking on simd-based smart cameras. Computer Vision and Image Understanding, (11):1264-1272.
  18. Merino, C. and Mirmehdi, M. (2007). A framework towards real-time detection and tracking of text. In CBDAR, pages 10-17.
  19. Minetto, R., Thome, N., Cord, M., Leite, N. J., and Stolfi, J. (2011). Snoopertrack: Text detection and tracking for outdoor videos. In ICIP, pages 505-508.
  20. Phan, T. Q., Shivakumara, P., Lu, T., and Tan, C. L. (2013). Recognition of video text through temporal integration. In ICDAR, pages 589-593.
  21. Schwenk, H. and Milgram, M. (1996). Constraint tangent distance for on-line character recognition. In ICPR, pages 515-519.
  22. Simard, P., LeCun, Y., Denker, J., and Victorri, B. (1992). An efficient algorithm for learning invariances in adaptive classifiers. In ICPR, pages 651-655.
  23. Tanaka, M. and Goto, H. (2008). Text-tracking wearable camera system for visually-impaired people. In ICPR, pages 1-4.
  24. Tuong, N. X., Müller, T., and Knoll, A. (2011). Robust pedestrian detection and tracking from a moving vehicle. In Proceedings of the SPIE, volume 7878, pages 1-13.
Download


Paper Citation


in Harvard Style

Robert-Seidowsky M., Fabrizio J. and Dubuisson S. (2015). TextTrail - A Robust Text Tracking Algorithm In Wild Environments . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 268-276. DOI: 10.5220/0005292002680276


in Bibtex Style

@conference{visapp15,
author={Myriam Robert-Seidowsky and Jonathan Fabrizio and Séverine Dubuisson},
title={TextTrail - A Robust Text Tracking Algorithm In Wild Environments},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={268-276},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005292002680276},
isbn={978-989-758-091-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - TextTrail - A Robust Text Tracking Algorithm In Wild Environments
SN - 978-989-758-091-8
AU - Robert-Seidowsky M.
AU - Fabrizio J.
AU - Dubuisson S.
PY - 2015
SP - 268
EP - 276
DO - 10.5220/0005292002680276