9 November 2016 Multiorientation/multiscript scene text detection based on projection profile analysis and graph segmentation
Author Affiliations +
Textline detection in natural images has been an important problem and researchers have attempted to address this problem by grouping connected components (CCs) into clusters corresponding to textlines. However, developing bottom-up rules that work for multiorientation and/or multiscript textlines is not a simple task. In order to address this problem, we propose a framework that incorporates projection profile analysis (PPA) into the CC-based approach. Specifically, we build a graph of CCs and recursively partition the graph into subgraphs, until textline structures are detected by PPA. Although PPA has been a common technique in document image processing, it was developed for scanned documents, and we also propose a method to compute projection profiles for CCs. Experimental results show that our method is efficient and achieves better or comparable performance on conventional datasets (ICDAR 2011/2013 and MSRA-TD500), and shows promising results on a challenging dataset (ICDAR 2015 incidental text localization dataset).
© 2016 SPIE and IS&T
Hyung Il Koo, Hyung Il Koo, } "Multiorientation/multiscript scene text detection based on projection profile analysis and graph segmentation," Journal of Electronic Imaging 25(6), 063001 (9 November 2016). https://doi.org/10.1117/1.JEI.25.6.063001 . Submission:


Hardware scheme for plankton recognition
Proceedings of SPIE (September 19 2001)
New approach for logo recognition
Proceedings of SPIE (March 30 2000)
Architecture Of High Speed Image Processing System
Proceedings of SPIE (January 17 1988)
Road recognition for a tracked vehicle
Proceedings of SPIE (June 22 2000)

Back to Top