An Effective Video Text Tracking Algorithm Based on SIFT Feature and Geometric Constraint

  • Yinan Na
  • Di Wen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6297)


Video text provides important clues for semantic-based video analysis, indexing and retrieval. And text tracking is performed to locate specific text information across video frames and enhance text segmentation and recognition over time. This paper presents a multilingual video text tracking algorithm based on the extraction and tracking of Scale Invariant Feature Transform (SIFT) features description through video frames. SIFT features are extracted from video frames to correspond the region of interests across frames. Meanwhile, a global matching method using geometric constraint is proposed to decrease false matches, which effectively improves the accuracy and stability of text tracking results. Based on the correct matches, the motion of text is estimated in adjacent frames and a match score of text is calculated to determine Text Change Boundary (TCB). Experimental results on a large number of video frames show that the proposed text tracking algorithm is robust to different text forms, including multilingual captions, credits, scene texts with shift, rotation and scale change, under complex backgrounds and light changing.


Video Indexing Text Tracking SIFT Geometric Constraint Match Score 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Battiato, S., Gallo, G., Puglisi, G.: SIFT Features Tracking for Video Stabilization. In: 14th International Conference on Image Analysis and Processing (2007)Google Scholar
  2. 2.
    Jung, K., Kim, K.I., Jain, A.K.: Text information extraction in images and video: a survey. Pattern Recognition 37, 977–977 (2004)CrossRefGoogle Scholar
  3. 3.
    Lienhart, R.: Video OCR: A Survey and Practitioner’s Guide. In: Video Mining, pp. 155–184. Kluwer Academic Publisher, Dordrecht (2003)Google Scholar
  4. 4.
    Lienhart, R., Effelsberg, W.: Automatic Text Segmentation and Text Recognition for Video Indexing, Technical Report TR-98-009, Praktische Informatik IV, University of Mannheim (1998)Google Scholar
  5. 5.
    Antani, S., Gargi, U., Crandall, D., Gandhi, T., Kasturi, R.: Extraction of Text in Video, Technical Report of Department of Computer Science and Engineering, Penn. State University, CSE-99-016 (August 30, 1999)Google Scholar
  6. 6.
    Gargi, U., Crandall, D., Antani, S., Gandhi, T., Keener, R., Kasturi, R.: A System for Automatic Text Detection in Video. In: Proc. of International Conference on Document Analysis and Recognition, pp. 29–32 (1999)Google Scholar
  7. 7.
    Nakajima, Y., Yoneyama, A., Yanagihara, H., Sugano, M.: Moving Object Detection from MPEG Coded Data. In: Proc. of SPIE, vol. 3309, pp. 988–996 (1998)Google Scholar
  8. 8.
    Pilu, M.: On Using Raw MPEG Motion Vectors to Determine Global Camera Motion. In: Proc. of SPIE, vol. 3309, pp. 448–459 (1998)Google Scholar
  9. 9.
    Li, H., Kia, O., Doermann, D.: Text Enhancement in Digital Video. In: Proc. of SPIE, Document Recognition IV, pp. 1–8 (1999)Google Scholar
  10. 10.
    Shi, J., Luo, X., Zhang, J.: DCT Feature Based Text Capturing and Tracking. In: Chinese Conference on Pattern Recognition, pp. 294–297 (2009)Google Scholar
  11. 11.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Yinan Na
    • 1
  • Di Wen
    • 2
  1. 1.Department of AutomationTsinghua UniversityBeijingChina
  2. 2.State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Electronic EngineeringTsinghua UniversityBeijingChina

Personalised recommendations