Text extraction in MPEG Compressed video for content-based indexing

Young K. Lim, Song H. Choi, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingChapter

30 Citations (Scopus)

Abstract

Video text extraction is a core technique for multimedia applications such as News-On-Demand(NOD) and digital libraries, and research about video text extraction have been conducted vigorously. In this paper, we propose an efficient method for extracting texts in MPEG compressed videos for content-based indexing. The proposed method makes the best use of 2-level DCT coefficients and macroblock type information in MPEG compressed video, and this method can be organized into three stages to increase overall performance : text frame detection, text region extraction, and character extraction. The main advantage of the proposed method is that it can avoid the overhead of decompressing video into individual frames in the pixel domain. We evaluated this method using various types of news video data.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages409-412
Number of pages4
Volume15
Edition4
Publication statusPublished - 2000

Fingerprint

Digital libraries
Pixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Lim, Y. K., Choi, S. H., & Lee, S. W. (2000). Text extraction in MPEG Compressed video for content-based indexing. In Proceedings - International Conference on Pattern Recognition (4 ed., Vol. 15, pp. 409-412)

Text extraction in MPEG Compressed video for content-based indexing. / Lim, Young K.; Choi, Song H.; Lee, Seong Whan.

Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. p. 409-412.

Research output: Chapter in Book/Report/Conference proceedingChapter

Lim, YK, Choi, SH & Lee, SW 2000, Text extraction in MPEG Compressed video for content-based indexing. in Proceedings - International Conference on Pattern Recognition. 4 edn, vol. 15, pp. 409-412.
Lim YK, Choi SH, Lee SW. Text extraction in MPEG Compressed video for content-based indexing. In Proceedings - International Conference on Pattern Recognition. 4 ed. Vol. 15. 2000. p. 409-412
Lim, Young K. ; Choi, Song H. ; Lee, Seong Whan. / Text extraction in MPEG Compressed video for content-based indexing. Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. pp. 409-412
@inbook{ecce444437904ac8b968a212d65c4ebf,
title = "Text extraction in MPEG Compressed video for content-based indexing",
abstract = "Video text extraction is a core technique for multimedia applications such as News-On-Demand(NOD) and digital libraries, and research about video text extraction have been conducted vigorously. In this paper, we propose an efficient method for extracting texts in MPEG compressed videos for content-based indexing. The proposed method makes the best use of 2-level DCT coefficients and macroblock type information in MPEG compressed video, and this method can be organized into three stages to increase overall performance : text frame detection, text region extraction, and character extraction. The main advantage of the proposed method is that it can avoid the overhead of decompressing video into individual frames in the pixel domain. We evaluated this method using various types of news video data.",
author = "Lim, {Young K.} and Choi, {Song H.} and Lee, {Seong Whan}",
year = "2000",
language = "English",
volume = "15",
pages = "409--412",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "4",

}

TY - CHAP

T1 - Text extraction in MPEG Compressed video for content-based indexing

AU - Lim, Young K.

AU - Choi, Song H.

AU - Lee, Seong Whan

PY - 2000

Y1 - 2000

N2 - Video text extraction is a core technique for multimedia applications such as News-On-Demand(NOD) and digital libraries, and research about video text extraction have been conducted vigorously. In this paper, we propose an efficient method for extracting texts in MPEG compressed videos for content-based indexing. The proposed method makes the best use of 2-level DCT coefficients and macroblock type information in MPEG compressed video, and this method can be organized into three stages to increase overall performance : text frame detection, text region extraction, and character extraction. The main advantage of the proposed method is that it can avoid the overhead of decompressing video into individual frames in the pixel domain. We evaluated this method using various types of news video data.

AB - Video text extraction is a core technique for multimedia applications such as News-On-Demand(NOD) and digital libraries, and research about video text extraction have been conducted vigorously. In this paper, we propose an efficient method for extracting texts in MPEG compressed videos for content-based indexing. The proposed method makes the best use of 2-level DCT coefficients and macroblock type information in MPEG compressed video, and this method can be organized into three stages to increase overall performance : text frame detection, text region extraction, and character extraction. The main advantage of the proposed method is that it can avoid the overhead of decompressing video into individual frames in the pixel domain. We evaluated this method using various types of news video data.

UR - http://www.scopus.com/inward/record.url?scp=1242271676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1242271676&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:1242271676

VL - 15

SP - 409

EP - 412

BT - Proceedings - International Conference on Pattern Recognition

ER -