Abhishek Ranjan Singh's Projects
A beautiful, simple, clean, and responsive Jekyll theme for academics
This is the code from my ECE-558, Digital Imaging Systems, Final Project. Here I have implemented Blob Detection for images using Laplacian of Gaussian by creating a Laplacian Scale space via varying image size which helped increase the speed. After that I have performed Harrisβ Non-Max Suppression and encircled the Blobs.
Lane Finding Project for Self-Driving Car ND
This is my work for the Self driving cars specialization offered by University of Toronto on Coursera
Repository to do cricket ananlysis on the existing cricsheet data
Cricket analysis on cricsheet.org data
Compared the performance of Gaussian model, Mixture of Gaussian model, t-distribution, Mixture of t-distribution, Factor Analysis and Mixture of Factor Analyzer on the task of facial recognition under the Generative modeling scheme.
Collection of LeetCode questions to ace the coding interview! - Created using [LeetHub](https://github.com/QasimWani/LeetHub)
Monte Carlo Simulator for Bit Error Rate Estimation in Digital Communication
Implementation of Multilayered Perceptron
This project simulates pathfinding for a Roomba-like robot in a pre-mapped environment. The environment is represented by an occupancy grid where each cell indicates the presence of an obstacle or free space. The program calculates a collision-free path from a starting position to a goal position.
The project includes functionality for detecting planes in point clouds, reorienting these planes, and smoothing the point clouds using Poisson surface reconstruction. It aims to provide a comprehensive set of tools for point cloud manipulation and analysis
A simple code to understand polynomial regression for curve fitting
This is a Text Similarity Score Generator. It takes in two different texts and compares how similar they are. To calculate the similarity score I am using Vector Space Model. This model creates a vector Space where each dimension represents a single word. Words are taken from all the texts that are considered. One document is a single vector space. Each dimension of a single document vector represents how often this word appears in the text.To compare two documents a cosine similarity is used. This generates a value between 0 and 1, 0 meaning no similarity and 1 meaning perfect match.
This was my Project for ECE 542