Text Localization Based on Fast Feature Pyramids and Multi-Resolution Maximally Stable Extremal Regions

  • Alessandro Zamberletti
  • Lucia Noce
  • Ignazio Gallo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9009)


Text localization from scene images is a challenging task that finds application in many areas. In this work, we propose a novel hybrid text localization approach that exploits Multi-resolution Maximally Stable Extremal Regions to discard false-positive detections from the text confidence maps generated by a Fast Feature Pyramid based sliding window classifier. The use of a multi-scale approach during both feature computation and connected component extraction allows our method to identify uncommon text elements that are usually not detected by competing algorithms, while the adoption of approximated features and appropriately filtered connected components assures a low overall computational complexity of the proposed system.


Text Component Scene Image Text Localization Text Detection Image Pyramid 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Pan, Y.F., Hou, X., Liu, C.L.: Text localization in natural scene images based on conditional random field. In: Proceedings of the ICDAR (2009)Google Scholar
  2. 2.
    Coates, A., Carpenter, B., Case, C., Satheesh, S., Suresh, B., Wang, T., Wu, D.J., Ng, A.Y.: Text detection and character recognition in scene images with unsupervised feature learning. In: Proceedings of the ICDAR (2011)Google Scholar
  3. 3.
    Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: Proceedings of the BVMC (2012)Google Scholar
  4. 4.
    Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: Proceedings of the ICCV (2011)Google Scholar
  5. 5.
    Koo, H.I., Kim, D.H.: Scene text detection via connected component clustering and non-text filtering. IEEE Trans. IP 22, 2296–2305 (2013)MathSciNetGoogle Scholar
  6. 6.
    Li, Y., Jia, W., Shen, C., Hengel, A.: Characterness: an indicator of text in the wild. IEEE Trans. IP 23, 1666–1677 (2014)Google Scholar
  7. 7.
    Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 770–783. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  8. 8.
    Shi, C., Wang, C., Xiao, B., Zhang, Y., Gao, S.: Scene text detection using graph model built upon maximally stable extremal regions. Pattern Recogn. Lett. 34, 107–116 (2013)CrossRefGoogle Scholar
  9. 9.
    Yin, X.C., Yin, X., Huang, K.: Robust text detection in natural scene images. IEEE Trans. PAMI 36, 970–983 (2013)MathSciNetGoogle Scholar
  10. 10.
    Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: Proceedings of the CVPR (2010)Google Scholar
  11. 11.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proceedings of the BMVC (2002)Google Scholar
  12. 12.
    Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., Bigorda, L., Mestre, S., Mas, J., Mota, D., Almaz, J., Heras, L.: ICDAR 2013 robust reading competition. In: Proceedings of the ICDAR (2013)Google Scholar
  13. 13.
    Dollár, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. PAMI 36, 1532–1545 (2014)CrossRefGoogle Scholar
  14. 14.
    Forssén, P.E., Lowe, D.G.: Shape descriptors for maximally stable extremal regions. In: Proceedings of the ICCV (2007)Google Scholar
  15. 15.
    Crimisi, A.: Microsoft Research Cambridge Object Recognition Image Database (2004)Google Scholar
  16. 16.
    Yao, C., Bai, X., Liu, W., Ma, Y.: Detecting texts of arbitrary orientations in natural images. In: Proceedings of the CVPR (2010)Google Scholar
  17. 17.
    Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: Proceedings of the CVPR (2012)Google Scholar
  18. 18.
    Mathias, M., Timofte, R., Benenson, R., Gool, L.V.: Traffic sign recognition: how far are we from the solution? In: Proceedings of the IJCNN (2013)Google Scholar
  19. 19.
    Benenson, R., Mathias, M., Tuytelaars, T., Gool, L.V.: Seeking the strongest rigid detector. In: Proceedings of the CVPR (2013)Google Scholar
  20. 20.
    Appeal, R., Fuchs, T., Dollár, P., Perona, P.: Quickly boosting decision trees pruning underachieving features early. In: Proceedings of the ICML (2013)Google Scholar
  21. 21.
    Villamizar, M., Andrade-Cetto, J., Sanfeliu, A., Moreno-Noguer, F.: Bootstrapping boosted random ferns for discriminative and efficient object classification. Pattern Recogn. 45, 3141–3153 (2012)CrossRefGoogle Scholar
  22. 22.
    de Campos, T.E., Babu, B.R., Varma, M.: Character recognition in natural images. In: Proceedings of the VISAPP (2009)Google Scholar
  23. 23.
    Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: Proceedings of the CVPR (2010)Google Scholar
  24. 24.
    Manen, S., Guillaumin, M., Gool, L.V.: Prime object proposals with randomized prims algorithm. In: Proceedings of the ICCV (2013)Google Scholar
  25. 25.
    Yi, C., Tian, Y.: Localizing text in scene images by boundary clustering, stroke segmentation, and string fragment classification. IEEE Trans. IP 21, 4256–4268 (2012)MathSciNetGoogle Scholar
  26. 26.
    Neumann, L., Matas, J.: On combining multiple segmentations in scene text recognition. In: Proceedings of the ICDAR (2013)Google Scholar
  27. 27.
    Bai, B., Yin, F., Liu, C.L.: Scene text localization using gradient local correlation. In: Proceedings of the ICDAR (2013)Google Scholar
  28. 28.
    Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competition. In: Proceedings of the ICDAR (2003)Google Scholar
  29. 29.
    Wolf, C., Jolion, J.M.: Object count/area graphs for the evaluation of object detection and segmentation algorithms. IJDAR 8, 280–296 (2006)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Alessandro Zamberletti
    • 1
  • Lucia Noce
    • 1
  • Ignazio Gallo
    • 1
  1. 1.Department of Theoretical and Applied ScienceUniversity of InsubriaVareseItaly

Personalised recommendations