Abstract
Text area detection from video frame is an essential step for Video OCR. The key problem is the complex background of the video frames. This paper proposes a novel approach to this problem. First, we use the vertical edge information to detect candidate text areas. The horizontal edge information is then used to eliminate some of the false candidates. Finally, shape suppression technique is applied to further refine the results. Experimental results have shown the proposed approach is very effective in text area detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Li, H.; Doermann, D.; Kia, O.: Automatic text detection and tracking in digital video, IEEE Trans. on Image Processing, 9(1) (2000) 147–156
Zhong, Y., Zhang, H., Jain, A. K.: Automatic Caption Extraction of Digital Videos, Proc. ICIP’99, Kobe, (1999) 24–27
Sato, T., Kanade, T.: Video OCR: Indexing digital news libraries by recognition of superimposed caption. ICCV Workshop on Image and Video retrieval (1998)
Gray R. M.: Vector Quantization, IEEE ASSP Magazine, 1(2) (1984) 4–29
Sung, K., Poggio, T.: Example-based learning for view-based human face detection. A.I.Memo 1521, CBCL Paper 112, MIT (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, X., Zhang, H. (2001). Text Area Detection from Video Frames. In: Shum, HY., Liao, M., Chang, SF. (eds) Advances in Multimedia Information Processing — PCM 2001. PCM 2001. Lecture Notes in Computer Science, vol 2195. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45453-5_29
Download citation
DOI: https://doi.org/10.1007/3-540-45453-5_29
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42680-6
Online ISBN: 978-3-540-45453-3
eBook Packages: Springer Book Archive