Confusion network based video OCR post-processing approach

Authors:
Anan Liu;Jinghao Fei;Jianping Fan;Lin Pang;Yongdong Zhang;Jintao Li
Affiliations:
School of Computer Science, Carnegie Mellon University, Pittsburgh, PA and School of Electronic Engineering, Tianjin University, Tianjin and Shenzhen Institute of Advanced Technology, Shenzhen and ...;School of Computer Science, Carnegie Mellon University, Pittsburgh, PA and Shenzhen Institute of Advanced Technology, Shenzhen and Institute of Computing Technology, CAS, Beijing, China;Shenzhen Institute of Advanced Technology, Shenzhen and Institute of Computing Technology, CAS, Beijing, China;Institute of Computing Technology, CAS, Beijing, China;Institute of Computing Technology, CAS, Beijing, China;Institute of Computing Technology, CAS, Beijing, China
Venue:
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Year:
2009

Citing 4
Cited 0

Text Identification in Noisy Document Images Using Markov Random Field

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
A syntax-based statistical translation model

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Localizing and segmenting text in images and videos

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper originally presents a confusion network based framework for Video OCR post-processing. The framework consists of four parts: selection of reference and hypotheses, construction of confusion network, decoding for final output, and a novel metric of quantitatively evaluating Video OCR post-processing approaches. By integrating both visual and textual information, we construct the character transition network to reduce the error rate for OCR outputs. The large-scale experimental results demonstrate that this approach can significantly improve the accuracy of Video OCR results with only little incremental time. Moreover, with comparison and the detailed analysis, we conclude that "Voting+2-gram" is the most applicable method for real application.