Advertisement

Robust Uyghur Text Localization in Complex Background Images

  • Jianjun Chen
  • Yun Song
  • Hongtao XieEmail author
  • Xi Chen
  • Han Deng
  • Yizhi Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9917)

Abstract

Text localization in complex background images remains a challenging task, especially for Uyghur text. Since the existing methods mostly focus on English and Chinese. Uyghur as a minority language is paid less attention. This paper proposes a robust and precise method for locating Uyghur texts in complex background images. Firstly, a multi-color-channel enhanced Maximally Stable Extremal Regions (MSERs) extraction scheme is used to capture text components robustly. Then, the strong classification and retrieve strategy (SCRS) accurately identifies text components. Finally, our method precisely connects text components into lines according to component connectivity. The proposed method is evaluated on the UICBI400 dataset, and the F-measure is over 82.8%, which is much better than the state-of-the-art performance of 61.6%.

Keywords

Text detection Text localization MSERs Uyghur extraction 

Notes

Acknowledgement

This work is supported by the National Nature Science Foundation of China (61303171), Natural Science Foundation of Hunan Province (2016JJ2005), the “Strategic Priority Research Program” of the Chinese Academy of Sciences (XDA06031000), Xinjiang Uygur Autonomous Region Science and Technology Project (201230123), Hunan Provincial University Innovation Platform Open Fund Project of China (14K037).

References

  1. 1.
    Yin, X-C., et al.: Robust vanishing point detection for mobilecam-based documents. In: International Conference on Document Analysis & Recognition, Beijing, China, pp. 136–140 (2011)Google Scholar
  2. 2.
    Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480–1500 (2015)CrossRefGoogle Scholar
  3. 3.
    Lee, J-J., et al.: AdaBoost for text detection in natural scene. In: Proceedings of the 2011 International Conference on Document Analysis and Recognition, IEEE Computer Society, pp. 429–434 (2011)Google Scholar
  4. 4.
    Epshtein, B., Ofek, E., Wexler, Y.:. Detecting text in natural scenes with stroke width transform. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2963–2970. IEEE (2010)Google Scholar
  5. 5.
    Neumann, L., Matas, J.: Text localization in real-world images using efficiently pruned exhaustive search. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 687–691. IEEE (2011)Google Scholar
  6. 6.
    Matas, J.: Real-time scene text localization and recognition. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 3538–3545 (2012)Google Scholar
  7. 7.
    Yin, X.-C., et al.: Robust text detection in natural scene images. IEEE Trans. Pattern Anal. Mach. Intell. 36(5), 970–983 (2013)Google Scholar
  8. 8.
    Huang, W., Qiao, Y., Tang, X.: Robust scene text detection with convolution neural network induced MSER trees. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 497–511. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10593-2_33 Google Scholar
  9. 9.
    Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: reading text in scene images. In: International Conference on Document Analysis & Recognition, pp. 1491–1496. IEEE (2011)Google Scholar
  10. 10.
    Halima, M.B., Karray, H., Alimi, A.M.: A comprehensive method for arabic video text detection, localization, extraction and recognition. In: Qiu, G., Lam, K.M., Kiya, H., Xue, X.-Y., Kuo, C.-C.J., Lew, M.S. (eds.) PCM 2010. LNCS, vol. 6298, pp. 648–659. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15696-0_60 CrossRefGoogle Scholar
  11. 11.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 886–893 (2005)Google Scholar
  12. 12.
    Wolf, C., Jolion, J.M.: Object count/area graphs for the evaluation of object detection and segmentation algorithms. Int. J. Doc. Anal. Recogn. 8(4), 280–296 (2006)CrossRefGoogle Scholar
  13. 13.
    Liu, S., Zhou, Y., Zhang, Y., Wang, Y., Lin, W.: Text detection in natural scene images with stroke width clustering and superpixel. In: Ooi, W.T., Snoek, C.G.M., Tan, H.K., Ho, C.-K., Huet, B., Ngo, C.-W. (eds.) PCM 2014. LNCS, vol. 8879, pp. 123–132. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-13168-9_13 Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Jianjun Chen
    • 1
    • 2
  • Yun Song
    • 1
  • Hongtao Xie
    • 2
    Email author
  • Xi Chen
    • 1
  • Han Deng
    • 2
  • Yizhi Liu
    • 3
  1. 1.School of Computer and Communication EngineeringChangsha University of Science and TechnologyChangshaChina
  2. 2.Institute of Information Engineering, Chinese Academy of SciencesBeijingChina
  3. 3.School of Computer Science and EngineeringHunan University of Science and TechnologyXiangtanChina

Personalised recommendations