Share Email Print

Proceedings Paper

Overlaid caption extraction in news video based on SVM
Author(s): Manman Liu; Yuting Su
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Overlaid caption in news video often carries condensed semantic information which is key cues for content-based video indexing and retrieval. However, it is still a challenging work to extract caption from video because of its complex background and low resolution. In this paper, we propose an effective overlaid caption extraction approach for news video. We first scan the video key frames using a small window, and then classify the blocks into the text and non-text ones via support vector machine (SVM), with statistical features extracted from the gray level co-occurrence matrices, the LH and HL sub-bands wavelet coefficients and the orientated edge intensity ratios. Finally morphological filtering and projection profile analysis are employed to localize and refine the candidate caption regions. Experiments show its high performance on four 30-minute news video programs.

Paper Details

Date Published: 15 November 2007
PDF: 7 pages
Proc. SPIE 6786, MIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition, 67864O (15 November 2007); doi: 10.1117/12.749148
Show Author Affiliations
Manman Liu, Tianjin Univ. (China)
Yuting Su, Tianjin Univ. (China)

Published in SPIE Proceedings Vol. 6786:
MIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition
Tianxu Zhang; Tianxu Zhang; Carl Anthony Nardell; Carl Anthony Nardell; Hanqing Lu; Duane D. Smith; Hangqing Lu, Editor(s)

© SPIE. Terms of Use
Back to Top