A Mechanism for Detection of Text in Images Using DWT and MSER

  • B. N. AjayEmail author
  • C. Naveena
Part of the Studies in Computational Intelligence book series (SCI, volume 771)


The study of video optical character readers (OCR) is an eminent field of research in image processing due to various real-time applications. Hence, in this chapter, an algorithm is proposed for text detection in images. The proposed method consists of mainly three stages in which the image is initially sharpened using a Gaussian filter. A discrete wavelet transform (DWT) is then applied to the sharpened image. After this step, the maximally stable extremal region (MSER) is detected to obtain the average of the detailed components of the wavelet images. To detect foreground components in an image, the Connected Component Analysis (CCA) algorithm is applied to localized text components. The proposed method is evaluated on standard MSER and MSRA-TD500 datasets. Experimental results are satisfactory.




  1. 1.
    Yang, H., B. Quehl, and H. Sack. 2014. A framework for improved video text detection and recognition. Multimedia Tools and Applicattion, Springer 69: 217–245.CrossRefGoogle Scholar
  2. 2.
    Phan, T.Q., P. Shivakumar, S. Bhowmick, S. Li, and C. L. Tan. 2014. Semi-automatic ground truth generation for text detection and recognition in video images. IEEE Transactions on Circuits and Systems for Video Technology.Google Scholar
  3. 3.
    He, T., W. Huang, Y. Qiao, and J. Yao. 2016. Text-attentional convolutional neural network for scene text detection. IEEE Transactions on Image Processing 25 (6): 2529–2541.MathSciNetCrossRefGoogle Scholar
  4. 4.
    Wu, H., B. Zou, Y.Q. Zhao, and J. Guo. 2017. Scene text detection using adaptive color reduction, adjacent character model and hybrid verification strategy. The Visual Computer 33 (1): 113–126.CrossRefGoogle Scholar
  5. 5.
    Zhou, X., C. Yao, H. Wen, Y. Wang, S. Zhou, W. He, and J. Liang 2017. EAST: an efficient and accurate scene text detector. arXiv:1704–03155, 2017.
  6. 6.
    Shi, C., C. Wang, B. Xiao, S. Gao, and J. Hu. 2014. End-to-end scene text recognition using tree-structured models. Pattern Recognition: Elsevier.Google Scholar
  7. 7.
    Minetto, R., N. Thome, M. Cord, N.J. Leite, and J. Stolfi. 2013. SnooperText: A text detection system for automatic indexing of urban Scenes. Computer Vision and Image Understanding, Elsevier 122: 92–104.CrossRefGoogle Scholar
  8. 8.
    Yusufu, T., Y. Wang, and X. Fang. 2013. A video text detection and tracking system, 522–529. IEEE: In the proceedings of international symposium on multimedia.Google Scholar
  9. 9.
    Gomez, L., and D. Karatzas. 2014. MSER- based real-time text detection and tracking. In 22nd international conference on pattern recognition, IEEE, pp. 3110–3115.Google Scholar
  10. 10.
    Tabassum, A., and S.A. Dhondse. 2015. Text detection using MSER and stroke width transform. In Fifth international conference on communication system and network technologies, IEEE, 568–571.Google Scholar
  11. 11.
    Turki, H., M. B. Halima, and A. M Alimi. 2015. Scene text detection images with pyramid image and MSER enhanced. In 15th international conference on intelligent systems design and application (ISDA), IEEE.Google Scholar
  12. 12.
    Yao, C., X. Bai, W. Liu, Y. Ma, and Z. Tu. 2012. Detecting texts of arbitrary orientations in natural images. CVPR, 1083–1090.Google Scholar
  13. 13.
    Shivakumar, P., H.T. Basavaraju, D.S. Guru, and C.L. Tan. 2013. Detection of curved text in video: quad tree based method. In 12th international conference on document analysis and recognition(ICDAR), 594–598.Google Scholar
  14. 14.
    Lu, C., C. Wang, and R. Dai. 2005. Text detection in images based on unsupervised classification of edge-based features. In Proceedings of ICDAR, 610–614.Google Scholar
  15. 15.
    Zhao, X., K.H. Lin, Y. Fu, Y. Hu, Y. Liu, and T.S. Huang. 2011. Text from corners: a novel approach to detect text and caption in videos. IEEE Transactions on IP 20: 790–799.MathSciNetzbMATHGoogle Scholar
  16. 16.
    Kang, L., Y. Li, & D. Doermann. 2014. Orientation robust text line detection in natural images. In Proceedings of CVPR, 4034–4041.Google Scholar
  17. 17.
    Yao, C., X. Bai, and W. Liu. 2014. A Unified framework for multi-oriented text detection and recognition. IEEE Transactions IP 23: 4737–4749.zbMATHGoogle Scholar
  18. 18.
    Yin, X.C., W.Y. Pei, J. Zuang, and H.W. Hao. 2015. Multi-orientation scene text detection with adaptive clustering. IEEE Transactions PAMI 37: 1930–1937.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringVTU-RRCBelagaviIndia
  2. 2.Department of Computer Science and EngineeringSJB Institute of TechnologyBangaloreIndia

Personalised recommendations