This repository contains the links to the reports and the code that was used for the course on deep learning that is offered at IIT Mandi : "EE608 - Digital Image Processing". Please note that the major contribution towards this project was provided only by Aditya Sarkar and Gajraj Singh.
Table of contents
Sarkar A., Singh G., Rameshan R., "Decomposing documents into HTML using Text Classification and Layout Contouring".
We have scored 85/100 in this assignment, which is the third highest in the course EE608. A lot of efforts has been put into making the report and codes of these assignments. If you are taking certain parts of the code, please ensure that you cite it in your report.
Code tested on Ubuntu 20.04, if you are not on linux please follow platform-specific instructions.
pip3 install matplotlib opencv-python numpy pandas scikit-learn tqdm ipywidgets dominate pytesseract pillow
sudo apt install tesseract-ocr
jupyter nbextension enable --py widgetsnbextension
This repository is under Creative Commons license. For more information, please read our LICENSE.md file.
Please do not hesitate to contact us ([email protected]) if you have any comments, suggestions, or clarification requests regarding the study or if you would like to contribute to this resource.