Segmentation-Free Bangla Offline Handwriting Recognition Using Sequential Detection of Characters and Diacritics with a Faster R-CNN

Nishatul Majid, Elisa H. Barney Smith

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

18 Scopus citations

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.

Original languageAmerican English
Title of host publication2019 International Conference on Document Analysis and Recognition (ICDAR)
StatePublished - 2019
EventICDAR 2019: 15th International Conference on Document Analysis and Recognition - Sydney, Australia
Duration: 23 Sep 2019 → …

Conference

ConferenceICDAR 2019: 15th International Conference on Document Analysis and Recognition
Period23/09/19 → …

Keywords

  • Bangla handwriting recognition
  • character spotting
  • handwriting recognition using faster R-CNN
  • offline handwriting recognition
  • segmentation-free handwriting recognition

EGS Disciplines

  • Electrical and Computer Engineering

Fingerprint

Dive into the research topics of 'Segmentation-Free Bangla Offline Handwriting Recognition Using Sequential Detection of Characters and Diacritics with a Faster R-CNN'. Together they form a unique fingerprint.

Cite this