Skip to content

Latest commit

 

History

History
48 lines (37 loc) · 1.21 KB

README.md

File metadata and controls

48 lines (37 loc) · 1.21 KB
Raw

OCR

This project refers to the handwritten recognition with CNN and RNN, decode with CTC.

demo Demo on youtube

Update

This repo has better model and higher accuracy

Dataset

IAM dataset

  • [Model1 - word_model.png] Train on WORD unit of dataset.
  • [Model2 - line_model.png] Train on LINE unit of dataset.
  • Split data: https://www.openslr.org/56/

Result

Test on IAM dataset:

Model Test Unit CER(%) WER(%)
WORD WORD 17.20 37.78

Train

[Google colab]

Usage

Training

$ python3 Train.py

Predict

$ python3 Prediction.py

predict

Evaluation

$ python3 EvaluationWord.py
$ python3 EvaluationLine.py

References

https://towardsdatascience.com/build-a-handwritten-text-recognition-system-using-tensorflow-2326a3487cd5 http://norvig.com/spell-correct.html