Journal of Multimedia Information System

한국멀티미디어학회 (Korea Multimedia Society)
권호 표지
DOI QR코드

DOI QR Code

Automatic Name Line Detection for Person Indexing Based on Overlay Text

  • 투고 : 2015.03.26
  • 심사 : 2015.04.20
  • 발행 : 2015.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Many overlay texts are artificially superimposed on the broadcasting videos by humans. These texts provide additional information to the audiovisual content. Especially, the overlay text in news videos contains concise and direct description of the content. Therefore, it is most reliable clue for constructing a news video indexing system. To make the automatic person indexing of interview video in the TV news program, this paper proposes the method to only detect the name text line among the whole overlay texts in one frame. The experimental results on Korean television news videos show that the proposed framework efficiently detects the overlaid name text line.

키워드

참고문헌

  1. Z. Wang, L. uang, X. Wu, and Y. Zhang, "A survey on video caption extraction technology", in Fourth International Conference on Multimedia Information Networking and Security, Nov. 2012.
  2. P. Shivakumara, TQ. Phan, CL. Tan Hong, and K. J. Lim, "A gradient difference based technique for video text detection", in ICDAR, pp. 15-160, 2009.
  3. U. Gargi, S. Antani, and RE. Woods, "Indexing text events in digital video database", Pattern Recognition, vol. 1, pp.1481-1483, 1998.
  4. P. Shivakumara, W. Huang, and CL. Tan, "An efficient edge based technique for text detection in video frames", in DAS, pp. 307-314, 2008.
  5. F. Xiaoling and G. Hua, "Gray-based news video text extraction approach", in 5th International Conference on computer Science and Convergence Information Technology, 2010.
  6. Z. Yang and P. Shi, "Caption detection and text recognition in news video", in 5th International Congress on Image and Signal Processing, 2012.
  7. S. Huey, H. W. Chang, C. J. Wang, and C. W. Wang, "Robust news video text detection based on edges and line-deletion", WSEAS Transaction on Signal Processing, vol. 6, no.4, October 2010.
  8. T. Sato, T. Kanade, E. K. Huges, M. A. Smith, and S. Sato, "Video OCR: Indexing digital news libraries by recognition of superimposed caption", Multimedia Systems, vol. 7, no. 5, pp.385-395, January 1999. https://doi.org/10.1007/s005300050140
  9. J. Poignant, L. Besacier, G. Quenot, and F. Thollard, "From text detection in videos to person identification", in International Conference on Multimedia and Expo, 2012.
  10. S. Satoh, Y. Nakamura, T. Kanade, "Name-It: Naming and detecting faces in news videos", Proc. of IEEE Multimedia, 1999.
  11. P. Gay, G. Dupuy, C. Lailler, J. Odobez, S. Meignier, and P. Deleglise, "Comparison of two methods for unsupervised person identification in TV shows", in 12th international workshop on content based multimedia indexing, 2014.
  12. P. T. Pham, T. Tuytelaars, and M. Mones, "Naming people in news videos with label propagation", in Proc. of ICME, 2010.
  13. B. Jou, H. Li, G. Ellis, D. Morozoff-Abegauz, and S. F. Chang, "Structured exploration of who, what, when, and where in heterogeneous multimedia news source", in Proc. of ACM Multimedia, 2013.
  14. J. Poignant, L. Besacier, V. B. Le, S. Rosset, and G. Quenot, "Unsupervised speaker identification in TV broadcast based on written names", in Proc. of Interspeech, 2013.
  15. J. Poignant, H. Bredin, V. B. Le, L. Besacier, C. Barras, and G. Quenot, "Unsupervised speaker identification using overlay texts in TV broadcast", in Proc. of Interspeech, 2012.
  16. M. Bendris, B.Favre, D. Charlet, G. Damnati, G. Senay, R. Auguste, and J. Martinet, "Unsupervised face identification in TV content using audio-visual sources", in Proc. of CBMI 2013.
  17. S. Lee, H. Park, J. Ahn, Y. On, and K. Jo, "Overlay text graphic region extraction for video quality enhancement", JBE, vol. 18, no. 4, pp-559-571, July 2013.

피인용 문헌

  1. Comparison of Text Beginning Frame Detection Methods in News Video Sequences vol.21, pp.3, 2015, https://doi.org/10.5909/jbe.2016.21.3.307