Please use this identifier to cite or link to this item: https://doi.org/10.1109/DAS.2008.17
Title: An efficient edge based technique for text detection in video frames
Authors: Shivakumara, P. 
Huang, W. 
Tan, C.L. 
Issue Date: 2008
Source: Shivakumara, P., Huang, W., Tan, C.L. (2008). An efficient edge based technique for text detection in video frames. DAS 2008 - Proceedings of the 8th IAPR International Workshop on Document Analysis Systems : 307-314. ScholarBank@NUS Repository. https://doi.org/10.1109/DAS.2008.17
Abstract: Both graphic text and scene text detection in video images with complex background and low resolution is still a challenging and interesting problem for researchers in the field of image processing and computer vision. In this paper, we present a novel technique for detecting both graphic text and scene text in video images by finding segments containing text in an input image and then using statistical features such as vertical and horizontal bars for edges in the segments for detecting true text blocks efficiently. To identify a segment containing text, heuristic rules are formed based on combination of filters and edge analysis. Furthermore, the same rules are extended to grow the boundaries of a candidate segment in order to include complete text in the input image. The experimental results of the proposed method show that the technique performs better than existing methods in terms of a number of metrics. © 2008 IEEE.
Source Title: DAS 2008 - Proceedings of the 8th IAPR International Workshop on Document Analysis Systems
URI: http://scholarbank.nus.edu.sg/handle/10635/41052
ISBN: 9780769533377
DOI: 10.1109/DAS.2008.17
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

40
checked on Dec 14, 2017

WEB OF SCIENCETM
Citations

13
checked on Nov 19, 2017

Page view(s)

50
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.