projects | Arvind Seshan

Image Inpainting

Designed and implemented process for inpainting regions in images by interpolating structure (image gradients) using a Poisson solver and color values via PDE’s (anisotropic diffusion) in C++.

Object Tracking & Gesture Recognition

Created interactive game with real-time hand-tracking and neural network-based gesture identification using OpenCV and TensorFlow in Python. 1st place term project.

AI-Powered CV Analyzer

Designed an AI-powered platform using Flask and Gemini that compares résumés to job descriptions to provide a match score and feedback with a backend in Python and frontend in HTML and CSS.

Python · web-apps
Image Inpainting

Designed and implemented process for inpainting regions in images by interpolating structure (image gradients) using a Poisson solver and color values via PDE’s (anisotropic diffusion) in C++.

C/C++ visual-computing · class-projects
UNIX-like Operating System

Implemented several key parts of virtual memory system, network protocol stack, system call interfaces, and file system in C.

C/C++ systems · class-projects
RISC-V Processor Optimized for Neural Network Inference

Built CPU with 4-stage pipeline, bypassing, and custom instruction set extensions for inference. Implemented loop unrolling and function inlining code optimizations.

C/C++ systems machine-learning · class-projects
Iterative Neural Network Based Approach to Automated IFT-20 Sensory Neuron Identification in Caenorhabditis elegans

Developed custom multistage neural network implemented using PyTorch to classify 22 sensory neurons in the IFT-20 subunit of the C. elegans brain. Paper available upon request

Python visual-computing machine-learning · papers
Using Machine Learning to Augment Dynamic Time Warping Based Signal Classification

Designed neural network using TensorFlow that predicts likely distortions between signals to eliminate unnecessary computations in Dynamic Time Warping (DTW), a popular signal comparison algorithm. arXiv:2206.07200

Python machine-learning · papers
Object Tracking & Gesture Recognition

Created interactive game with real-time hand-tracking and neural network-based gesture identification using OpenCV and TensorFlow in Python. 1st place term project.

Python visual-computing machine-learning · class-projects
Enabling High-Accuracy Human Activity Recognition with Fine-Grained Indoor Localization

Used multilateration with fine-grained distance estimates from Wi-Fi Round Trip Time to perform high-accuracy indoor localization. Combined location, accelerometer, and audio data collected from a custom-made Android application programmed in Java to train a neural network that performs activity recognition of various household tasks. arXiv:2108.06838

Python Java machine-learning · papers
(ALTo) Ad Hoc High-Accuracy Touch Interaction Using Acoustic Localization

Designed low-cost tool programmed using Python to increase the usable interactive touch surface area of devices. Implemented system using pairs of piezoelectric microphones and time difference of arrival (TDOA) based multilateration to determine the origin of a tap on a surface. arXiv:2108.06837

Python · papers
Robots for LEGO MINDSTORMS App

Designed 3 robots for official MINDSTORMS App, incorporating end-user needs and product design guidelines.

robotics
LEGO Robotics Games and Other Projects

For the last seven years, I have been creating and sharing interactive LEGO robotics models. Many of these robots have been featured on LEGO and LEGO Education social media sites, and LEGO events such as LEGOWORLD Copenhagen.

robotics