This is an Android app that does content-aware image resizing. More info coming soon!
Market link:
Example shrinking: 
Different display modes: normal, edge, cumulative energy of cheapest path 
This is an Android app that does content-aware image resizing. More info coming soon!
Market link:
Example shrinking: 
Different display modes: normal, edge, cumulative energy of cheapest path 
Here's a little game I made way back in 1999. See if you have what it takes to conquer the world!
Requires the Shockwave plugin(sorry).
Andrew Harp and Amir Mehrtash

Sample Expectation Maximization; red Xs represent initial guessed means.
This is a parallel implementation of the Expectation Maximization algorithm for Gaussian Mixture Models, designed to run on NVidia graphics cards supporting CUDA. On my machine*, it provides up to 170x performance increases versus a CPU reference version.
See the report for more information.
This page is for the demonstration I had to give for my Computer Vision class in Spring 2009. It is a modified version R. Fergus's Simple Parts and Structure Object Detector.
It will learn to detect objects given a couple of manually trained examples, by using the alignment of individual parts. It will also perform Expectation Maximization to improve the model.
I've been working on and off on WorldFamilies.net for a couple of years.
It's a genealogy project coordination site my uncle runs. There are nearly 1600 surname project sites run there. My job was to make them database driven and upgrade the look of the site.
(been a while since I've worked on this site)
This is something I made back in 2003 to teach myself collision detection, Direct3D and C++.
The objective is to knock your opponent's ball out of the arena without being knocked out yourself.
Alternatively, you can just spawn a lot of balls and play around.
This is a Java project to generate synthetic images for training machine vision systems.
I haven't been able to work on it for a while but I'll post a webstart link here once I get it running again.

Doggone Catastrophe was an IGF student finalist at the 2003 Game Developer's Conference.
Written in Java, you play as a dog attempting to take down the evil SuperCat and his feline followers.
Click HERE to play (Requires Java webstart)