Back to Search
Start Over
Learning Co-occurrence of Local Spatial Strokes for Robust Character Recognition
- Source :
- IEICE Transactions on Information and Systems. :1937-1941
- Publication Year :
- 2014
- Publisher :
- Institute of Electronics, Information and Communications Engineers (IEICE), 2014.
-
Abstract
- In this paper, we propose a representation method based on local spatial strokes for scene character recognition. High-level semantic information, namely co-occurrence of several strokes is incorporated by learning a sparse dictionary, which can further restrain noise brought by single stroke detectors. The encouraging results outperform state-of-the-art algorithms.
- Subjects :
- business.industry
Computer science
Speech recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Co-occurrence
Pattern recognition
Artificial Intelligence
Hardware and Architecture
Computer Vision and Pattern Recognition
Noise (video)
Artificial intelligence
Electrical and Electronic Engineering
business
Representation (mathematics)
Software
Character recognition
ComputingMethodologies_COMPUTERGRAPHICS
Subjects
Details
- ISSN :
- 17451361 and 09168532
- Database :
- OpenAIRE
- Journal :
- IEICE Transactions on Information and Systems
- Accession number :
- edsair.doi...........e55f9960f27b322aedfaa981468720bb