Siddhant Bansal

I am a Research Fellow at CVIT Lab, IIIT Hyderabad. I am working under Dr C.V. Jawahar on creating an OCR (Optical Character Reader) for detecting Indian languages (Hindi, Tamil, and Telugu) just from the images. I also work as Dr Jawahar's Teaching Assistant (TA) for the course 'Statistical Methods for Artificial Intelligence'. I am broadly interested in 2D and 3D Computer Vision, Deep Learning and related problems.

My ultimate goal is to contribute to the development of machines capable of reading an instruction manual and creating new machines! I'm a very inquisitive person and always willing to learn about fields including, but not limited to, science, technology, astrophysics, and physics.

Email  /  CV  /  Github  /  LinkedIn  /  Twitter

My Photo!
Updates

Experience
ICP on Chairs GIF

Research Intern
IIT Gandhinagar

March 2019 - August 2019 (Gandhinagar, Gujarat)

Internship Webpage

Worked on the project titled "Cultural Heritage Preservation and Restoration using Digital 3D Models", under Prof. Shanmuganathan Raman. The project was supported by NVIDIA and IMPRINT (Impacting Research Innovation and Technology) an initiative of the Government of India.

Major work done:

  1. Data Collection in the form of Point Clouds using Faro Focus 3D Laser Scanner.
  2. Point Cloud Alignment using algorithms like ICP (Using Eigenvalues Eigenvectors, SVD, and studied various deep learning approaches like Deep Closest Point, DeepICP, Discriminative Optimization, Auto-Encoder Approach, PointNetLK).
  3. Developed an algorithm for Point Cloud Completion using Fully-Connected Auto-Encoder and got some decent results on ShapeNet dataset.

ELOPE Flow Chart

Artificial Intelligence Intern
Meditab Software, Inc.

September 2018 - March 2019 (Ahmedabad, Gujarat)

Internship Webpage

Worked on the project titled "Facility Layout Optimization using Genetic Algorithm".

Major work done:

  1. Created a python environment named ELOPE (Evolutionary Layout Optimization and Evaluator) from scratch, for testing and visualizing all the evolutionary optimization algorithms.
  2. Created an automatic system for analyzing log files for anomaly detection in the DosePacker system.

Foot Images Samples

Artificial Intelligence Research Intern
Bennett University

June 2018 - July 2018 (Greater Noida, Uttar Pradesh)

Internship Webpage YouTube

Worked on the project titled "Credibility Examination of Human Footprint Using Minutiae Features". The project was supported by NVIDIA by providing DGX 1 Tesla V100.

Major work done:

  1. Collected dataset of footprints from 180 volunteers, using just a simple paper scanner at 600dpi.
  2. Developed a custom Convolution Neural Network for classifying humans based on the shape and size of their footprints. The network was trained on the data collected earlier.
Bioscan Device

Data Analyst Intern
Bioscan Research

April 2018 - July 2018 (Ahmedabad, Gujarat)

Worked on applying Artificial Intelligence and Machine Learning to an onsite detection tool for instantaneous scanning of intracranial bleeding.

Major work done:

  1. Developed a GUI for keeping track of patients and the data coming from the device.
  2. Developed an automatic detector (using Python) for detecting actual signal (coming from a near-infrared laser scanner) amidst the noise from the brain scan.

Projects
Robot

Automatic Garbage Detection and Collection
Publication

The only project selected out of 30 projects, this project was funded by the Government of India under the SSIP (Student Startup and Innovation Policy) scheme. In this project, we used Python for Image Processing and Artificial Intelligence to detect the garbage, once detected then the robot automatically picks up the garbage and leaves the valuables untouched. The AI algorithms used were made to run on the Raspberry Pi model B+ and all the motors and the arm is controlled using the Arduino Mega.

Dad Smiling!

Smile Detector
GitHub

This project was made for detecting smile in a live video using the webcam or a pre-recorded video.

Self driving car screenshot!

Self Driving Car
GitHub YouTube

This project was made while learning about Deep Q Learning which is a widely used technique for Reinforcement Learning.

Anime sample from the dataset.

Anime Classification
GitHub

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 like:

  1. Does the image contain any nudity or sexual content? (Yes, No)
  2. Is this an interesting image or not? (Yes, no)

Research

  • Siddhant Bansal, Seema Patel, Ishita Shah, Prof. Alpesh Patel, Prof. Jagruti Makwana, and Dr. Rajesh Thakker. "AGDC: Automatic Garbage Detection and Collection." ArXiv:1908.05849


Template!