Multimedia Tools and Applications

, Volume 78, Issue 5, pp 5345–5354 | Cite as

Video text localization based on Adaboost

  • Fang Yin
  • Rui Wu
  • Xiaoyang Yu
  • Guanglu SunEmail author


Video text localization is an important step in video text recognition system for monitored control system, auto navigation system, content based image analysis system and so on. So it’s necessary to find a good method to extract text from video image accurately and quickly. In this paper a new method of video text localization based on Adaboost is proposed. Firstly, the edge detection is performed using Sobel operator based on the gradient feature to extract text region in the image. Through the analysis the feature of the video image region, five kinds of features are extracted to form five weak classifiers, then these features are classified to construct Adaboost strong classifier with CART (Classification And Regression Tree) and the candidates text regions are sent to the classifier to get correct result of the text region detection. The experimental results show that this method can not only achieve good effect on the text localization in the video images with the text of various fonts, sizes and colors, but also can realize rapidly and accurately to meet the video text localization requires.


Video Text localization Edge detection Classifier Adaboost CART 



This paper is supported by the research project of science and technology of Heilongjiang provincial education department (No. 12541119).


  1. 1.
    Chen X, Yuille A (2004) Detecting and reading text in natural scenes [C]. Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 I.E. Computer Society Conference on 2:11366–11373Google Scholar
  2. 2.
    Cho H, Sung M, Jun B (2016) Canny text detector: fast and robust scene text localization algorithm [C]. IEEE conference on computer vision and. Pattern Recogn:3566–3573Google Scholar
  3. 3.
    Gao S, Ji L, Gao C (2014) Graphics text detection with max gradient difference [J]. Appl Res Comput 31(10):3174–3172Google Scholar
  4. 4.
    Gudipati VK, Barman OR, Gaffoor M, et al (2016) Efficient facial expression recognition using adaboost and haar cascade classifiers [C]. 2016 Annual Connecticut Conference on Industrial Electronics, Technology & Automation, 7868250Google Scholar
  5. 5.
    Hua X, Chen X, Li W, et al (2001) Automatic location of text in video frames [J]. Proceeding of ACM Multimedia 2001 Workshops: Multimedia Information Retrieval (MIR2001), pp 24–27Google Scholar
  6. 6.
    Jiang M, Cheng J, Chen M, et al. (2017) Text extraction in video and images: a review [J]. Comput Sci 44(11A): 8–18Google Scholar
  7. 7.
    Liu S, Lu M, Liu G (2017) A novel distance metric: generalized relative entropy [J]. Entropy 19(6):1704.06423MathSciNetGoogle Scholar
  8. 8.
    Liu S, Pan Z, Cheng X (2017) A novel fast fractal image compression method based on distance clustering in high dimensional sphere surface [J]. Fractals 25(4):1740004CrossRefGoogle Scholar
  9. 9.
    Pan Z, S Liu WF (2017) A review of visual moving target tracking [J]. Multimed Tools Appl 76(16):16989–17018CrossRefGoogle Scholar
  10. 10.
    Viola P, Jones M (2000) Fast and robust classification using symmetric daboost and a detector cascade [J]. Adv Neural Inf Process Syst:1311–1318Google Scholar
  11. 11.
    Wu D (2013) The research of video text extraction under complex background [D]. Shanxi province of China: Xian university science and technologyGoogle Scholar
  12. 12.
    Yu M, Yun L, Chen Z (2007) Research on video face detection based on AdaBoost algorithm training classifier [C]. 2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS), p 207Google Scholar
  13. 13.
    Zhao M, Li S, Kwok J (2010) Text detection in images using sparse representation with discriminative dictionaries [J]. Image Vis Comput 28:1590–1599CrossRefGoogle Scholar
  14. 14.
    Zhou Y, Lu T, Liao W (2011) A robust color independent text detection method from complex video [C]. International Conference on Document Analysis and Recognition IEEE, pp 374–378Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of computer Science and TechnologyHarbin University of Science and TechnologyHarbinChina
  2. 2.Instrument Science and Technology Postdoctoral Research StationHarbin University of Science and TechnologyHarbinChina
  3. 3.Department of Computer Science and TechnologyHarbin Institute of TechnologyHarbinChina

Personalised recommendations