Skip to content

The project was done under TCS iON as a virtual internship and aims to extract handwritten text from images using Deep Learning. Trained a Tensorflow Keras model on IAM public dataset on a sample of 90000 images using a CRNN architecture with a CTC loss function. Achieved a testing levenshtein accuracy of 92-94%.

Notifications You must be signed in to change notification settings

ihsan292292/HandWrittenTextExtraction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

HandWrittenTextExtraction

TCS iON RIO125 – Automate extraction of handwritten text from an image

The project was done under TCS iON as a virtual internship and aims to extract handwritten text from images using Deep Learning. Trained a Tensorflow Keras model on IAM public dataset on a sample of 90000 images using a CRNN architecture with a CTC loss function. Achieved a testing levenshtein accuracy of 92-94% and was deployed using streamlit cloud

About

The project was done under TCS iON as a virtual internship and aims to extract handwritten text from images using Deep Learning. Trained a Tensorflow Keras model on IAM public dataset on a sample of 90000 images using a CRNN architecture with a CTC loss function. Achieved a testing levenshtein accuracy of 92-94%.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages