Name: Manikandan Murugesan
Type: User
Company: Indiana University Bloomington
Bio: I am a Computer Science graduate student at Indiana University Bloomington. I have been coding for a while now and also have 2 years of industry experience
Location: Bloomington, Indiana
Blog: www.manikandanm.com
Manikandan Murugesan's Projects
Implementation of a naive OS with process synchronization, basic memory management, networking and simple file systems.
A complete computer science study plan to become a software engineer.
Shell script to copy files from one github repository to another. Needs SSH key to be set up before proceeding.
Solutions to the problems on the HackerRank site
AI Player to play Rameses and Totogram using Heuristic Search algorithms such as BFS and Iterative Deepening.
Given two images of the same object, but of different view, the program tries to find the matching SIFT points. Then it estimates the homography and performs the projective transformation so that the second image is transformed into the same view as the first image.
The program tries to find the right orientation of the given image. It trains on the given dataset and classifies the orientation using K-nearest neighbors and Neural networks.
Code written while practicing for interviews
The program address the typical map coloring problem and tries to come up with a solution so that no adjacent states have the same color.
The project classifies the objects in every image into a pre-defined class. In this project, we have compared the results found using a simple baseline(subsampled pixel points passed to a SVM), Principal Component Analysis (PCA), Haar-like features (Viola-Jones), Bag Of Words model and a Convolutional Neural Network.
A minimal Jekyll Theme to host your resume (CV)
The code finds the edges on the Musical note images first by performing convolution with a sobel filter. Then it tries to find the coordinates of the notes occur using template matching. It finds the location of staff lines using Hough transform. With this data, it estimates the correct note.
Program which classifies the given sentence into its respective part of speech using Bayesian network models and Natural Language Processing techniques.
Simple python script to rename the pattern of names in files to the new pattern recursively.
Scene classification is a problem under the domain of object recognition. Scene classification is a very interesting problem of automatically labeling an image among a set of semantic categories. To achieve this, we had implemented a Bag Of Words model and used Cornell's SVMLight to train and classify the data.
Indexation of documents provided using Lucene Package.
Implementation of Query Centric Page Rank algorithm using Lucene and JUNG packages.
Implementation of various retrieval algorithms using Lucene Package.
A shopping website with which lets the user register, view and order the products on the site and an admin panel to monitor the orders and manage the inventory of the site.
The program creates a stereo image from the normal image and the disparity map from the same view. If a seed image is given instead of a disparity map is not given, it tries to estimate the disparity using Markov Random Field energy minimization.
Our attempt at the Yelp Dataset Challenge that could be found at the site https://www.yelp.com/dataset_challenge
Zacate is traditional dice game played in Latin America. It is a game of chance. The rules of the game can be found in the github repository. The code here is an AI program which takes certain decisions to maximize the score. This program competed against other programs and came 4th in a class of 64.