Back to Search
Start Over
Scene text recognition by learning co-occurrence of strokes based on spatiality embedded dictionary.
- Source :
-
IET Computer Vision (Wiley-Blackwell) . 2015, Vol. 9 Issue 1, p138-148. 11p. - Publication Year :
- 2015
-
Abstract
- Text information contained in scene images is very helpful for high-level image understanding. In this study, the authors propose to learn co-occurrence of local strokes for scene text recognition by using a spatiality embedded dictionary (SED). Unlike spatial pyramid partitioning images into grids to incorporate spatial information, the authors SED associates every codeword with a particular response region and introduces more precise spatial information for robust character recognition. After localised soft coding and max pooling of the first layer, a sparse dictionary is learned to model cooccurrence of several local strokes, which further improves classification performance. Experimental results on two scene character recognition datasets ICDAR2003 and CHARS74 K demonstrate that their character recognition method outperforms state-of-the-art methods. Besides, competitive word recognition results are also reported for four benchmark word recognition datasets ICDAR2003, ICDAR2011, ICDAR2013 and street view text when combining their character recognition method with a conditional random field language model. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 17519632
- Volume :
- 9
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- IET Computer Vision (Wiley-Blackwell)
- Publication Type :
- Academic Journal
- Accession number :
- 100802737
- Full Text :
- https://doi.org/10.1049/iet-cvi.2014.0022