Category: Computer Science

About a year ago someone lent me a Tetris Cube which has been sitting in my office since then. Being a fan of puzzles I thought it would be fun to tinker away at it occasionally during any down time or if I needed to clear my mind. For a few months I would spend a few minutes here and there trying to solve it. After a while I figured that my puzzle solving skills would not be enough and decided to put my programming skills to use. Since then I have hardly touched the puzzle and I haven’t had much time to try to create a solver until recently.

Throughout the past semester, as part of my computer vision course, I had to implement several image processing and computer vision techniques and algorithms to operate on grayscale images. There were three programming tasks in total. The first was to count the number of objects in a particular image, which required several simple steps. The second was to implement an edge detection algorithm, specifically Canny edge detector. The last programming assignment was to implement photometric stereo. This post will contain three (mostly) independent sections describing each of the assignments.

With recent advances in technology, new methods of computer interaction are becoming available. In this blog post I will briefly describe my investigation of gesture recognition using the Microsoft Kinect for Windows as a means of controlling software. For a much more detailed description of the methods and results of this project, you can read the paper.