Abstract
Arabic Text Detection in News Video Based on Line Segment Detector
Highlights
With the development of a big Arabic news channels, News video archives keep increasing in size every day and require more efficient tools for indexing and searching to facilitate access to these collections
We propose a novel approach for automatic Arabic text detection in news videos frames using a specific geometric feature of Arabic text called baseline in order to perform detection task
It is clear that the proposed approach achieves good results for text detection using Dataset1 (HD) because these types of channels provide an excellent quality of graphic text
Summary
With the development of a big Arabic news channels, News video archives keep increasing in size every day and require more efficient tools for indexing and searching to facilitate access to these collections. Many methods for text detection and localization have been proposed during the last few years based on different architectures, feature sets, and studies characteristics. These can generally be classified into three categories: connected component-based, edge-based, and texture-based. In [5] the authors propose a method using multi-oriented text detection which is based on the discontinuity of the text regions To do this, they applied a Sobel mask and a Laplacian filter. Thereafter, Bayesian classifier is used to classify candidate pixels into text and non text regions These methods face difficulties when the text is embedded in complex background or touches other objects which have similar structural texture to texts.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.