JanataHack: Computer Vision Hackathon

Computer Vision as a field of research is notoriously difficult. Almost no research problem has been satisfactorily solved. One main reason for this difficulty is that the human visual system is simply too good for many tasks (e.g., face recognition), so that computer vision systems suffer by comparison. 

A human can recognize faces under all kinds of variations in illumination, viewpoint, expression, etc. In most cases we have no difficulty in recognizing a friend in a photograph taken many years ago. Also, there appears to be no limit on how many faces we can store in our brains for future recognition. There appears no hope in building an autonomous system with such stellar performance.

Given all this, computer vision has shown a lot of promise and reshaping the future of various industries such as automobile industry, healthcare industry, financial industry and so on

This weekend we bring to you another hackathon to apply your deep learning skills to solve a computer vision problem. This time you are in for a two week ride so brush up on our computer vision skills and hop on.

FAQs

1. Where can I find the dataset and the problem statement for the hackathon?

The contest will go live on the designated contest start date and time. There is a timer that is shown at the top of this page which shows the remaining time before the contest goes live. This is when you can access the problem statement and datasets from the problem statement tab.

2. Can I share my approach/code?

Absolutely. You are encouraged to share your approach and code file with the community. There is even a facility at the leaderboard to share the link to your code/solution description.

3. I am facing a technical issue with the platform/have a doubt regarding the problem statement. Where can I get support?

Join the AV slack channel by clicking on 'Join Slack Live Chat' button and ask your query at channel: janata_hack