A novel approach to detecting scene text in video
Author:
- 1 October 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 469-473
Abstract
Scene text in video contains semantic information and thus can contribute significantly to video retrieval and understanding. However, most methods detect scene text in image or single frame. Videos differ from images in temporal redundancy. In this paper we present a novel approach to detecting video scene text based on the video temporal redundancy. Video scene texts in consecutive frames have arbitrary motion due to camera or object movement. Therefore, first, we perform the motion detection in 30 consecutive frames to synthesize motion image. Second we implement video scene text detection in single frame to retrieve candidate text regions. Finally, the synthesized motion image is used to filter out candidate text regions and only keep the candidate text regions which have motion occurrence as final scene text. Experimental results show that our algorithm performs well for detecting scene text with various color, font-size and text alignment.Keywords
This publication has 12 references indexed in Scilit:
- Color-based clustering for text detection and extraction in image2007
- A comprehensive method for multilingual video text detection, localization, and extractionIEEE Transactions on Circuits and Systems for Video Technology, 2005
- Automatic Detection and Recognition of Signs From Natural ScenesIEEE Transactions on Image Processing, 2004
- Scene text extraction in natural scene images using hierarchical feature combining and verification2004
- Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithmIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Image categorization using texture features2002
- Locating uniform-colored text in video frames2002
- Automatic location of text in video frames2001
- Video OCR: indexing digital news libraries by recognition of superimposed captionsMultimedia Systems, 1999
- A note on the gradient of a multi-imageComputer Vision, Graphics, and Image Processing, 1986