Automatic text discovering through stroke-based segmentation and text string combination

ABSTRACT

In this paper we present a novel framework of automatic text discovering for content-based multimedia application. For single image, the stroke-based binarization and the coarse-to-fine text extraction will collaborate to generate a clean text image for recognition. For image sequence, multi-frame text enhancement is adopted to increase the text/background contrast, and the recognition results are finally refined by the text string combination algorithm to get more precise semantic information. Two prototype demos have been successfully developed on mobile phones. The experimental results on different platforms show the superior performance of the proposed method.

REFERENCES

• 1: X. Chen and A. L. Yuille. Detecting and Reading Text in Natural Scenes. In Proceedings of CVPR, pages 366--373, 2004.
• 2: Nobuo Ezaki , Marius Bulacu , Lambert Schomaker, Text Detection from Natural Scene Images: Towards a System for Visually Impaired Persons, Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2, p.683-686, August 23-26, 2004 [doi>10.1109/ICPR.2004.895]
• 3: I. Haritaoglu. Scene Text Extraction and Translation for Handheld Devices. In Proceedings of CVPR, pages 408--413, 2001.
• 4: X.-S. Hua, P. Yin, and H.-J. Zhang. Efficient Video Text Recognition Using Multiple Frame Integration. In Proceedings of ICIP, pages 397--400, 2002.
• 5: Jinqiao Wang , Lingyu Duan , Lei Xu , Hanqing Lu , Jesse S. Jin, TV ad video categorization with probabilistic latent concept learning, Proceedings of the international workshop on Workshop on multimedia information retrieval, September 24-29, 2007, Augsburg, Bavaria, Germany [doi>10.1145/1290082.1290113]
• 6: K. Wang and J. A. Kangas. Character Location in Scene Images from Digital Camera. Pattern Recognition, 36(10):2287--2299, 2003.
• 7: Y. Watanabe , K. Sono , K. Yokomizo , Y. Okada, Translation camera on mobile phone, Proceedings of the 2003 International Conference on Multimedia and Expo, p.177-180, July 06-09, 2003
• 8: L. Xu and K. Wang. Extracting Text Information for Content-Based Video Retrieval. In Proceedings of MMM, pages 58--69, 2008.
• 9: Jian Yi , Yuxin Peng , Jianguo Xiao, Color-based clustering for text detection and extraction in image, Proceedings of the 15th international conference on Multimedia, September 25-29, 2007, Augsburg, Germany [doi>10.1145/1291233.1291426]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.1 Multimedia Information Systems
          Subjects: Evaluation/methodology

General Terms:
Algorithms, Experimentation, Performance

Keywords:
stroke-based segmentation, text discovering, text string combination