Seasons of Code is a programme launched by the WnCC, along the lines of GSoC without much greenery though. The incentive is similar to ITSP, based on the current form of it, the fundamental difference is that one can choose from the ideas offered by mentors who are senior undergrads, doctorate students or professors, and in some exceptional cases, startups. We plan to have a really long timeframe though, until the next winter extending this programme into a mentorship of sorts into the semester. It is not just about development by the way. We have some mentors ready to take up programmes regarding competitive coding and scientific computation too.
Seasons of Code gives you an amazing opportunity to learn and dive into coding under the mentorship of the best in our institute. Our list of projects gives you a chance to pick up and work on any topic you are enthusiastic about.
The Force is strong with you. Train yourself to let go of everything you fear to lose. The Force will be with you always. Ready are you?
I can feel you code. It gives you focus. It makes you stronger. Your focus determines your reality. Use the force and someday you will be the most powerful Jedi ever.Become a Master
This project would tackle the problem of Image Super Resolution. Image super-resolution (SR) techniques reconstruct a higher-resolution image or sequence from the observed lower-resolution images. Often a low-resolution image is taken as an input and the same image is upscaled to a higher resolution, which is the output. The details in the high-resolution output are filled in where the details are essentially unknown. Super resolution is essentially what you see in films and series like CSI where someone zooms into an image and it improves in quality and the details just appear.
The aim of this project is to train students who aim to do well at ICPC regionals. We will be covering a wide variety of content in Competitive Programming, and we will be asking you to participate in certain competitions in which we will discuss individual performances to understand where you need to improve to take yourself to the next level.
This is a continuation of the project “3D road network rendering” completed in the last SoC. The next aim is to build a traffic flow modelling tool and visualize the congestion at various parts of the road network.
This project aims to develop a source code plagiarism detector using Python.
The idea is to develop a spatial distribution model for Air Pollution for the city of Delhi using SVR (Support Vector Regression) and the model will be self enhancing using machine learning.
The project will aim more towards Machine learning on the Audio dataset, and the drone would only be used as an application.
The core idea behind this project is to familiarize with Deep NLP (one of the most sough-after domains of AI) & get hands-on experience with various deep network architectures while trying to accomplish 2 major tasks: Sentiment Analysis (Classification) & Automatic Lyrics Generation (Text Generation)
They main idea behind this project is to understand and implement the algorithms used by FaceApp, especially the aging/de-aging filter. Developing an actual app that does this would be a plus point!
In this project, mentees will learn about the four of the famous Convolutional Neural Network (CNN) architectures - AlexNet, VGGNet, ResNet and GoogleNet.
“Machine intelligence is the last invention that humanity will ever need to make.” ~Nick Bostrom Try out your hands on developing a superhuman AI to ace the game of 2048.
There are many fields of computer science that deal with solving problems of a geometric nature. These include computer graphics, computer vision and image processing, robotics, computer-aided design and manufacturing, computational fluid-dynamics, and geographic information systems, to name a few.
The volatility of stock market is generally modeled by three techniques; namely Technical Analysis, Machine Learning algorithms & statistical analysis. These models help in developing optimal portfolio for best returns with minimum risk.
If you wish to get a flavour(yes more or less a flavour) of such techniques, find exoplanets that may support life, estimate galaxy redshifts, classify galaxies based on their visible shapes, do some image processing, then this project is meant for you.
Computer Vision. You might’ve heard of this extremely versatile domain and some of you might even be familiar with it. With applications ranging from self-driving cars to say, automated translation, this is a very handy and not to mention, cool thing to know and in this project, we aim to do just that.
This project aims to introduce use of Convolutional Neural Networks which is the state-of-the-art technique for various image-based machine learning problems.
The perfect project for all the quantum physics enthusiasts. The code you will create for this project could one day break RSA/ revolutionise machine learning once the real hardware catches up.
This project is for the people interested in exploring front-end web development and learning Data Structures and Algorithms.
Traditionally, machine learning models have required huge amounts of computation power and could only be run on specialized hardware (GPU etc). Thanks to the efforts to many researchers and developers, it is now possible to run these models right in your browser.
A project that helps you create such a client based application for all document related operations in a single location, which includes reading handwritten notes!
This project would be dealing with dealing with reinforcement learning.
The goal is to build a fully functional 3D Physics Engine from scratch that can be integrated into any Rendering Framework
Don’t like black and white images? No worries. This project involves building a machine learning model which will do this image colorization for you!
This project aims to build an open source code editor (like Sublime Text), that uses natural language processing to create a language model for code prediction
Object detection with live input & data analysis using tensorflow, opencv, yolo, faster-rcnn, python
Design a texting Android Application that is secure and provides additional features escpecially for team coordination.
uilding an app that gives the status or track of books that someone has already issued
We propose to create a collaborative platform for collecting resources and making them available for use by all. Students will be able to upload past papers, tutorials etc for the courses they have taken and will be able to access the material uploaded by others.
We propose a Harvey-your own lawyer as a browser extension that will read the document for you and summarize the important points in simple language that actually matter to you and which you might want to consider before signing up.
We shall build an app that’s smart enough like an assistant to help me know how I spend my time and then help me manage my time.
The Input to this application will be “your daily class lectures” and the expected output is a brief but detailed summary of the entire lecture.
The Input to this application will be “your daily class lectures” and the expected output is a brief but detailed summary of the entire lecture.
This project aims to create a real time engine capable of rendering an infinite open world terrain with procedural generation with complex cave systems in OpenGL framework.
This project will involve learning many machine learning algorithms leading to RNNs. Mentees will implement a Neural Network and a Recurrent Neural Network framework from scratch
The grand challenge website hosts multiple challenges on biomedical imaging. We are interested in getting good results and hopefully winning the Head Circumference challenge .
Spreading ‘rumours’ on devices connected to the same Wi-Fi via an app
This project is mostly aimed towards people who want to excel in the sport of competitive programming. The agenda during the summers would be to get people acquainted with standard data structures and algorithms. Apart from this the project would require the mentees to give substantial time to practice problems on various online judges like Codeforces, Codechef, SPOJ etc.
This project will focus on getting human pose estimates in games to generate a dataset using no manual annotations or labelling.
This project tries to explore navigation using Geolocation AR.
It’s a Pokémon library, lists all Pokemon available on the PokeAPI, allows user to add favorites and store them to the browser local storage, dark/light mode.
We will be implementing rampart algorithm, for the prevention of denial of service attack. We will begin with socket programming in C++ and implement pop3 algorithm for email access. In case it gets completed real soon and easily, we will try to implement rampart in c++.
The goal of this project is to build an Augmented Reality smartphone application that can store and show text linked to locations and objects.
The task is to build a chatbot for answering FAQs aimed primarily at the newly joined students, faculty and staff at the Institute.
Your mission, should you choose to accept it, is to create a mobile application with which you can click any sudoku from the camera and fill it with the correct solution, giving you the power to spoil the fun of your sudoku solving friends.
To celebrate the recent findings uncovered by scientists in the physics community, we will try to make a simulation of gravitational lensing caused by a black hole using GLSL, beside other simple simulations.
This project focuses on building a Decentralised Application (DApp) for registering land and using it as collateral for transactions. Being on the blockchain, all the registrations would be publicly verifiable and disputes could be settled with ease.
The goal is to design a visually appealing gravity simulator. The final aim is to simulate two colliding galaxies. The project will have two components, one is implementing physics stuff, and the other one will be rendering the system onto the screen and creating a GUI.
Yann LeCun described GANs as “the most interesting idea in the last 10 years in Machine Learning”. And, indeed, Generative Adversarial Networks (GANs for short) have had a huge success since they were introduced in 2014 by Ian J. Goodfellow.
Producing 2D images of a 3D world is inherently a lossy process, i.e. the entire geometric richness of 3D gets projected onto a single flat 2D image. We aim to create an API in Python which primarily reconstructs 3D volumes from 2D X-Ray Images.
Implementing mesh neural network for 3D shape representation.
Implement your own sequence neural net
The project is about making a web platform where a user can upload the data, choose any model according to which they want their data to be trained and see the results. In the first phase, we will make a platform where every parameter is given by the user. After successfully completing this, we will add a feature to suggest the best method and parameters for the data. In the final stage, the platform will have features for uploading raw data and getting results after pre-processing. Pre req: Grip over linear algebra
I’m planning to create a game that simulates a real-life situation, similar to those strategic games done by the finance club, IITB. What needs to be done is that we need to create a game using Django so that multiple students are able to play it in real-time. The student will learn OOPs concepts and Web Development through this project. He/she needs to learn FrontEnd Technologies (Html, CSS, JS, JQuery) to design an attractive interface for the players to play the game, Backend( Django), OOP in Python.
The project has two parts: The front-end is an Android app/website that provides an interface to choose food recipes and create schedules. The back-end will be a Django server that provides personalized recommendations through machine learning.
Super Shenron is an android application that lists all the dragon ball characters in card form with details such as Name, Planet of Origin, Species etc. and these characters are sorted on the basis of no of likes.
Have you ever wondered what will be the future of interaction with computers or smart devices. Well here is a clue, its going to be touch less.This project will contain the research part as well as the development (front end and back end) part of the technology.
A conversational chatbot is a software that conducts conversation via auditory or textual methods. This project aims to build a closed-domain, generative-based conversational chatbot from scratch.
We all have used scanned copies of books and have been irritated by the fact that we cannot directly navigate to a particular section of the document or do a Ctrl+F. This project aims to take unstructured text as the input data and to give us nice and good looking structured text. This is not only restricted to properly written text as in a book but also extends to targeting problems like a self driving car detecting and understanding random road signs, automatic detection systems to record and interpret number plates of vehicles which did not follow the red light, and much more!
This project focuses on the task of creating a UI for visualizing traffic flow in a city(a road network) using OpenGL. The problem of traffic congestion has seen different types of approaches from using simple heuristics to complex machine learning based approaches to predict correct traffic signals in a road network. This project does not aim to solve the traffic congestion problem! It will merely serve as a tool to help solving the aforementioned problem.
The project is about making a virtual keyboard that can be projected on any flat surface like a table and then can be used to type in real-time. To start with, we need to program image processing that senses touch at a certain key on the virtual setting of keyboard. after that we need to fetch programs for individual as well as combination of keys (ex. Shift + any letter = Capital).
Get started with Machine Learning!
This internship involves front-end development for various FOSSEE websites.
Get started with competitive coding!
Build a real time planet renderer engine.
--- This internship involves the implementation of a Monte Carlo Path Tracer.
Augmented reality is an interactive experience of a real-world environment where the objects that reside in the real-world are “augmented” by computer-generated perceptual information.
60 Capture the Flag challenges in 60 days.
To build intrusion detection system using statistical analysis and ml.
This project aims at introducing the student to the use of statistics in machine learning. We will present several tools such as Principle Component Analysis giving them a theoretical and practical understanding of the same. After completing the basics we will apply the learned concepts and build a simple face recognition system and implement some parts of a paper on the same.
Rubik’s cube is one of the most fascinating 3-D combination puzzles we encounter. It is simple to understand the game, given a permutation we need to reduce the cube to a single goal state by rotating it. In this project, we will accomplish solving this cube with as minimum rotations as possible using the ideas of reinforcement learning.
Develop a Django website for Tinkerers’ Laboratory
We are working to add on certain features to the pre-existing Tinkerers’ Laboratory website to incorporate it with a new setup for entry recording, issuing items from the lab, and access to machines using biometric data.
This project aims at introducing the student to the world of software development and graphic design. We will present several tools such as Android Studio, Google’s Firebase, Django, Adobe Xd, Adobe Photoshop and Adobe Premiere Pro. After completing the basics, we will apply the learned concepts to build and design an ergonomic music app.
Digital Image Perception is a simplified algorithm to have the perception of depth (or distance) based on the two different images taken at same time from different (but related) perspectives. This project is inspired by the perception of depth (or distances) by human visual system.
The aim of the project is to build Kontakt app- a social media application which will provide an interface to anyone in Insti to ask doubts/questions or post anything anonymously(user dependent) subjected to some constraints/filters.
The project aims at extending the web application built for the pooling of possible services that can be shared. This is an idea we are implementing as one of our course projects but want to take it further.
Texter takes a piece of boring text, mostly educational and inserts relevant images in between to make the reading interesting.
This is an application by which a user can plan his day to day schedule and get timely reminders for the various tasks or events he has set or planned for any particular day chosen at the appropriate time.
This notebook will be written using python, also employing numpy and OpenCV, we will initially implement Poisson solver for the discrete case which is immensely useful for many application then we will proceed on the application part which will be from this paper
Insti buddy will be an assistant that helps you search telephone directory of IIT Bombay and keeps you updated with the Facebook feed of campus groups at IIT Bombay.
Each one of us must have used the Cam-scanner app on Android phones for quick and good quality scanning of documents. But what if you have to scan a really big document? Or maybe you want to capture more detail?
Boosting is a well known machine learning technique, we use simple weak classifiers in cascade fashion to form a strong classifier. It’s extremely effective, facebook uses some version of this algorithm for detecting faces (99.9% accurate). Implement basic adaboost on simulated data, then for digit recognition.