Working on detecting and recognising text in the images from Mobility Assistant for Visually Impaired (MAVI) developed at IIT-Delhi.
Lead a team of three for creating a robot using a RaspberryPi. It was capable of detecting waste bottles and picking them up.
Developed an algorithm for getting a rough estimate of the distance of the garbage from the robot (with an error margin of 2 cm).
Developed a path planning algorithm based on the concept of PID (by considering bottle as the centre).
One of the top 4% projects selected for demonstration at SSIP annual conference.
Created an end-to-end system for detecting smiling faces in a live video stream using Convolutional Neural Network.
In this project, I worked on autoencoders to learn the features from 1,40,000 images. Then using the trained autoencoder with added convolution layers to classify the anime to answer various questions with 74.6% accuracy like -
Does the image contain any nudity or sexual content? (Yes, No)
Is this an interesting image or not? (Yes, no).