Sirius

The frontend of the application

Inspiration

Many students tend to copy stuff and simply ignore the essence of the project. Hence it is an attempt to check to what degree the 2 documents are similar and give a short summary of the 2 documents so that the user can understand the keynote stuff.

What it does

-User has to select 2 files be it in txt or pdf format -OCR is used so that the application can easily accept all types of pdf by means of recognition of if the content is text or images. -Any other file type excepting these would result in an error. -After processing, it will give the desired value.

How I built it

I have used several open source technologies to get the model going. I have used OCRs, concepts of NLP and also used an equivalent amount of Pyqt5 as the frontend technology to float our project.

Challenges I ran into

I was quite new to the field of NLP but with the use of various youtube tutorials and friends, I got to know about such technologies and implemented it. -The OCR one was a bit tough on our part as I didn't know how to do it. ##Accomplishments that I am proud of -I am happy that this works on all types of pdfs irrespective of image pdf or searchable pdfs and all gives the correct output.