Text Detection Using Maximally Stable External Regions and Stroke Width Variation

  • Nishant Singh
  • Vivek KumarEmail author
  • Charul BhatnagarEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1122)


There is a proverb “an image is worth, than ten thousand words”. So it is very difficult to explain a single image. But what happens if a single image itself contains some information in the form of text. Though it is easy to extract text from the structured image, it is difficult to retrieve it from unstructured image. Thus in this paper, we are providing an efficient and concrete algorithm to solve this problem. This algorithm consists of detecting candidate text region using maximally stable external regions (MSER). Then it removes false region based on basic geometric properties. Now, again removing false region based on stroke width variation (SWV) and finally merging all text regions for detection of the result. At last, recognition of detected text with the help of optical character recognition (OCR). All these methods are combined to give high performance of the proposed algorithm.


Text retrieval Maximally stable external regions (MSER) Geometric properties Stroke width variation (SWV) Optical character recognitions (OCR) 


  1. 1.
    Tsai, S., Chen, D., Chandrasekhar, V., Takacs, G., Cheung, N.M., Vedantham, R., Grzeszczuk, R., Girod, B.: Mobile product recognition. In: Proceedings of ACM Multimedia 2010 (2010)Google Scholar
  2. 2.
    Liang, J., Doermann, D., Li, H.P.: Camera-based analysis of text and documents: a survey. IJDAR 7(2–3), 84–104 (2005)CrossRefGoogle Scholar
  3. 3.
    Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. IEEE Part IV LNCS 8692, 497–511 (2012)Google Scholar
  4. 4.
    Fabrizio, J., Cord, M., Marcotegui, B.: Text extraction from street level images. In: CMRT, pp. 199–204 (2009)Google Scholar
  5. 5.
    Yi, C., Tian, Y.: Assistive text reading from complex background for blind persons. In: Camera-Based Document Analysis and Recognition, pp. 15–28. Springer (2012)Google Scholar
  6. 6.
    Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 2963–2970 (2010)Google Scholar
  7. 7.
    Saini, S., Marawaha, C.: Comparative study of text detection in natural scene images. In: IEEE International Conference on Recent Trends in Electronics Information & Communication Technology, RTEICT, pp. 1981–1985 (2016)Google Scholar
  8. 8.
  9. 9.
    Chen, H., et al.: Robust text detection in natural images with edge-enhanced maximally stable extremal regions. In: 18th IEEE International Conference on Image Processing, ICIP. IEEE (2011)Google Scholar
  10. 10.
    Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR. IEEE (2012)Google Scholar
  11. 11.
    Gonzalez, A., et al.: Text location in complex images. In: 21st International Conference on Pattern Recognition, ICPR. IEEE (2012)Google Scholar
  12. 12.
    Li, Y., Lu, H.: Scene text detection via stroke width. In: 21st International Conference on Pattern Recognition ICPR. IEEE (2012)Google Scholar
  13. 13.
    Subramanian, K., Natarajan, P., Decerbo, M., Castañòn, D.: Character-stroke detection for text-localization and extraction. In: International Conference on Document Analysis and Recognition, ICDAR (2005)Google Scholar
  14. 14.
    Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: CVPR, pp. 2963–2970 (2010)Google Scholar
  15. 15.
    Minetto, R., Thome, N., Cord, M., Fabrizio, J., Marcotegui, B.: Snoopertext: a multiresolution system for text detection in complex visual scenes. In: ICIP, pp. 3861–3864 (2010)Google Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Computer Engineering and Application, Institute of Engineering and TechnologyGLA UniversityMathuraIndia

Personalised recommendations