Skip to content

Custom CRNN model with CTC Loss to detect multi string digits with decimals in a sequence.

Notifications You must be signed in to change notification settings

Mukil07/Handwritten-Digit-string-Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

Handwritten-Digit-string-Recognition

  • Handwritten Multi digit recognition is performed using a sequence based CRNN model ( Convolutional Recurrent Neural Network), which extracts meaningful features from sequencial window.
  • In this repository, I implemented a CRNN model with CTC Loss on our custom made Multi-digit numbers with decimals dataset to perform detection and recognition.

Training

Run the Custom_OCR.ipynb and save the model weights

Inference

Run the Digit_Recognition.ipynb using the saved model weight.

Results

With Decimals:

output (3) Without Decimals:

WhatsApp Image 2023-12-28 at 4 13 44 PM

About

Custom CRNN model with CTC Loss to detect multi string digits with decimals in a sequence.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published