Please use this identifier to cite or link to this item:
|Title:||A skeleton-based method for multi-oriented video text detection||Authors:||Phan, T.Q.
|Keywords:||Connected component analysis
Multi-oriented video text detection
|Issue Date:||2010||Citation:||Phan, T.Q.,Shivakumara, P.,Tan, C.L. (2010). A skeleton-based method for multi-oriented video text detection. ACM International Conference Proceeding Series : 271-278. ScholarBank@NUS Repository. https://doi.org/10.1145/1815330.1815365||Abstract:||In this paper, we propose a method based on the skeletonization operation for multi-oriented video text detection. The first step uses our existing Laplacian-based method to identify candidate text regions. In the second step, each region is classified as either a simple connected component (a single text string) or a complex connected component (multiple text strings that are connected to each other) depending on the number of intersection points in its skeleton. Complex connected components are then segmented into constituent parts based on the skeleton segments in order to separate the text strings from each other. Finally, text string straightness and edge density are used for false positive elimination. Experimental results show that the proposed method is able to detect multi-oriented graphics text and scene text. © Copyright 2010 ACM.||Source Title:||ACM International Conference Proceeding Series||URI:||http://scholarbank.nus.edu.sg/handle/10635/41434||ISBN:||9781605587738||DOI:||10.1145/1815330.1815365|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on May 15, 2019
checked on May 17, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.