WnCC - Seasons of Code
Seasons of Code is a programme launched by WnCC along the lines of the Google Summer of Code. It provides one with an opprtunity to learn and participate in a variety of interesting projects under the mentorship of the very best in our institute.
List of Projects
- KontaKt App
- Sudoku Spoiler
- GLSL Raytracing
- Decentralized Land Registration on Ethereum
- Galactic Collision Simulator
- Competetive coding
- The Unreasonable Effectiveness of Recurrent Neural Networks
- Generating a human pose dataset using PC games
- Monte Carlo Path Tracing Renderer
- Tabbing App
- Geo-location Augmented Reality
- AR chess app
- Prevention of Sophisticated DoS attack / Network Security
- Winning a Deep Learning challenge
- Automated Fiducial Localisation from MRI/CT Images
- Panorama in Cam Scanner
- 3D Object Reconstruction from Single Image
- Statistical Modelling of Star Maps
- Face Recognition Systems
- Competitive Coding
- Can Machines Identify Genres?
- Joint Modelling of Source Code and Natural Language
- Front end development for FOSSEE websites
- Institute Delivery System
- Capture The Swag
- Panorama in Cam-Scanner
- Poisson Solver with Image Editing
- Blind Source Separation
- FAQ Bot for Freshmen
- Capturing semantic structures in Neural Machine Translation
The goal of this project is to build an Augmented Reality smartphone application that can store and show text linked to locations and objects.
Linking text to objects or locations can be done in various ways. There can be a simple application that uses glyphs or QR codes, which is only feasible for use with objects that are nearby. The location of the smartphone and image-matching/recognition can also be used for nearby objects. And then there are some other ways to increase accuracy using the various sensors that are there in the smartphones. For locations or larger objects far away, geo-tagging works fine for the rough estimate, and adding image-matching/recognition to that would increase the accuracy.
This project would be broken up into smaller checkpoints, in increasing level of complexity. The idea is to build advanced features and get as close to the end goal as possible with each step, while overcoming the existing limitations. Thus, we’ll be moving from a simple AR app to a more advanced one, while increasing the accuracy and improving the user experience, and having something to show for all along.
Building this app would require work in the areas of Android Development, Augmented Reality and Computer Vision. Some amount of Computer Graphics and simple Machine Learning could also be involved.
In the end, we hope to build an Android Application that allows you to scribble text while pointing your camera at something (say a desk in your room or a building outside) and it would later show you the same text in real time when you point your camera at that thing again.
Who should choose this project? Some coding experience and an interest in problem-solving is a hard prerequisite. Experience in App development and/or Computer Vision would be a plus. As this project has multiple areas to work on and can be relatively complex in nature, willingness to learn and work sincerely is a must. This project would have positions for those willing to work in App Development, including those interested in Front-End development and UI/UX, which are very important in an AR application. And, of course, there will be a lot of work for those who are interested in Computer Vision and Augmented Reality.
Why should one choose this project? This project is a long term hobby project and would be built from scratch. Thus, any fresh ideas from your side would be appreciated and you would have a chance to get them to be implemented. You have an opportunity to gain the experience of building a complex application right from the beginning to the end. Augmented Reality is one of the hottest and the most promising fields out there, and this would be an opportunity for you to explore it. Those who want to get familiar with App Development, Computer Vision and the applications of Machine Learning algorithms would also find this project exciting and engaging.
|Week Number||Tasks to be Completed|
|Week 1||Getting familiar with the project, technologies, and frameworks involved; Initial brainstorming and beginning the coding part.|
|Week 2||Completing a simple application that overlays texts over glyphs.|
|Week 3||Starting the work on location-based and basic recognition-based overlaying.|
|Week 4||Completing the work on a basic location-based tagging. Accuracy wouldnÆt matter at this stage.|
|Week 5||Completing the work on a basic image-matching/recognition based overlaying. Accuracy wouldn’t matter at this stage.|
|Week 6||Integrating the location-based method with the image matching/recognition based method and bug-fixing.|
|Week 7||Same as week 6, increasing accuracy and working on the 3D rotation and orientation of the text.|
|Week 8||Buffer week, left for debugging, improvements, making up for the delays and integrating everything together.|