Notes Seperator Project under Machine Learning and AI society of Developer Students Club - IIT Patna.
Generally, during exams we take many images from notes of other people to study from. And once exams are over, it is a tedious job to find each of the images again and delete them one by one from our gallery. This is the very motivation for this project - To develop an algorithm that can classify a given image as "image from notes" and "image not from notes".
This project will help students to automatically remove images of notes from there gallery automatically without the user looking for any particular image .
The aim of the project is to autonomously detect whether a given image is taken from some notes or not. To achieve this, we will use Convolutional Neural Networks as our tool. We will be using different CNN architectures and choose the one with maximum accuracy parameters.
Image not from notes
- Basic Deep Learning concepts.
- Basics of Convolutional Neural Networks.
- Tools
- Python
- Tensorflow
- Keras
- Basic python libraries used in ML (Scikit-learn, Pandas, Matplotlib, Seaborn).
Plenty of resources can be found at this link.
The datset used for this model can be found here.
Further we may deploy the model on Google’s API or make an app that will automatically detect such images and will remove from your phone.
Our chat channel is to be found on Gitter here
- Piyush Tiwary (Project Lead).
- Anubhav Jangra.
- Shreyash Gedkar.
- Rahul Grover.