4944

Discriminative Learning for Script Recognition

Sheikh Faisal Rashid, Faisal Shafait, Thomas Breuel

International Conference on Image Processing International Conference on Image Processing (ICIP-10), September 26-29, Hong Kong, China , IEEE , 2010
Document script recognition is one of the important preprocessing steps in a multilingual optical character recognition (MOCR) system. A MOCR system requires prior knowledge of script to accurately recognize multilingual text in a single document. In multilingual documents two scripts can be mixed together within a single text line. Many existing script recognition methods lack the ability to recognize multiple scripts mixed within a single text line. Besides, these methods usually use script dependent features for script recognition thereby limiting their scope to particularly that script. In this paper we propose a discriminative learning approach for multi-script recognition at connected component level by using a convolutional neural network. The convolutional neural network combines feature extraction and script recognition process in one step and discriminative features for script recognition are extracted and learned as convolutional kernels from raw input. This eliminates the need for manually defining discriminative features for particular scripts. Results show above 95% script recognition accuracy at connected component level on datasets of Greek-Latin, Arabic-Latin multi-script documents and Antiqua-Fraktur documents. The proposed method can be easily adapted to different scripts.

Show BibTex:

@inproceedings {
       abstract = {Document script recognition is one of the important preprocessing steps in a multilingual optical character recognition (MOCR) system. A MOCR system requires prior
knowledge of script to accurately recognize multilingual text
in a single document. In multilingual documents two scripts
can be mixed together within a single text line. Many existing script recognition methods lack the ability to recognize
multiple scripts mixed within a single text line. Besides,
these methods usually use script dependent features for script
recognition thereby limiting their scope to particularly that
script. In this paper we propose a discriminative learning approach for multi-script recognition at connected component
level by using a convolutional neural network. The convolutional neural network combines feature extraction and script
recognition process in one step and discriminative features for
script recognition are extracted and learned as convolutional
kernels from raw input. This eliminates the need for manually
defining discriminative features for particular scripts. Results
show above 95% script recognition accuracy at connected
component level on datasets of Greek-Latin, Arabic-Latin
multi-script documents and Antiqua-Fraktur documents. The
proposed method can be easily adapted to different scripts.},
       number = {}, 
       month = {9}, 
       year = {2010}, 
       title = {Discriminative Learning for Script Recognition}, 
       journal = {}, 
       volume = {}, 
       pages = {}, 
       publisher = {IEEE}, 
       author = {Sheikh Faisal Rashid, Faisal Shafait, Thomas Breuel}, 
       keywords = {},
       url = {http://www.dfki.de/web/forschung/publikationen/renameFileForDownload?filename=Rashid-Script-Detection-ICIP10.pdf&file_id=uploads_777}
}