Other Projects

Patternfinder 3.0

This was a semester-long project that was supervised by Ben Schneiderman during his graduate level course Information Visualization (Spring 2006). Patternfinder is an interactive interface for doctors and clinicians to generate dynamic queries on temporal datasets. The original interface was designed using a
simulated dataset. We explored the usability of the interface with a real medical history dataset obtained from the Washington National Hospital. Afterwards, we improved the usability of the user interface to be more intuitive for non-technically oriented users. [pdf]
Particle Growing Method
This was a semester-long project in which I collaborated with Dr. Ingmar Bitter of the National Institutes for Health for the class Recent Advances in Computer Graphics (Spring 2005). In this project, we designed and implemented a new segmentation method, named particle growing. It uses a speed image, each value of which determines the amount of progress that each control point can proceed per iteration. By using an adaptive step size, it can segment convex regions such as the ventricle of the brain faster than existing methods. Since the results of the segmentation are lines in 2D and triangles in 3D (in the future), we can directly use them for rendering.[pdf]
Face Localization from Video Streams
This was a summer project at the Samsung Advanced Institute of Technology in which I collaborated with Dr. Lee to create a facial image database from video streams. We collected facial images from 120 people, in horizontal angles from 0 to 180 degrees (every 10 degrees) and in vertical angles from 0 to 120 degrees (every 10 degrees). This dataset was used to write the Multi-view 3D Face Descriptor 2003 MPEG 7 proposal, with which I assisted.[pdf]