Document Type
Conference Proceeding
Publication Date
2019
Abstract
This paper presents an offline handwriting recognition system for Bangla script using sequential detection of characters and diacritics with a Faster R-CNN. This is an entirely segmentation-free approach where the characters and associated diacritics are detected separately with different networks named C-Net and D-Net. Both of these networks were prepared with transfer learning from VGG-16. The essay scripts from the Boise State Bangla Handwriting Dataset along with standard data augmentation techniques were used for training and testing. The F1 scores for the C-Net and D-Net networks are 89.6% and 93.2% respectively. Afterwards, both of these detection modules were fused into a word recognition unit with CER (Character Error Rate) of 11.2% and WER (Word Error Rate) of 24.4%. A spell checker further minimized the errors to 8.9% and 21.5% respectively. This same method is likely to be equally effective on several other Abugida scripts similar to Bangla.
Copyright Statement
This is an author-produced, peer-reviewed version of this conference proceeding. The final, definitive version of this document can be found online at 2019 International Conference on Document Analysis and Recognition (ICDAR), published by IEEE. Copyright restrictions may apply. https://doi.org/10.1109/ICDAR.2019.00045
Publication Information
Majid, Nishatul & Barney Smith, Elisa H. (2019). "Segmentation-Free Bangla Offline Handwriting Recognition using Sequential Detection of Characters and Diacritics with a Faster R-CNN". In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 228-233). IEEE. https://doi.org/10.1109/ICDAR.2019.00045