A BLSTM-CTC model with 128 units, trained on 47,720 text lines, reaches 99.32% character accuracy on a 20-font Bengali test set, slightly above Google Drive OCR.
A gurmukhi script recognition system,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A BLSTM Network for Printed Bengali OCR System with High Accuracy
A BLSTM-CTC model with 128 units, trained on 47,720 text lines, reaches 99.32% character accuracy on a 20-font Bengali test set, slightly above Google Drive OCR.