Problem Identification and Solution:
This is an end to end solution that extracts all the text from the images, pdf documents or scanned files. So as opposed to entering the metadata of the documents manually, the OCR will identify the text in the documents which are fed into the document management system and send them to the database. So instead of entering the metadata manually, the OCR does the job of extracting the text from the images, scanned files, and other documents before sending them to the database.
Build Upon:
This smart system is build using python, Flask Web application, deep learning.
What's next for Smart OCR System
We can improve our model accuracy using hyperparameter tuning and use hard deep neural network model.
Log in or sign up for Devpost to join the conversation.