COMPUTATIONAL SOCIAL SCIENCE RESEARCH COLLOQUIUM /COLLOQUIUM IN COMPUTATIONAL AND DATA SCIENCES – Classifying Pill Spies Using Storks – William Lamberti
Computational Social Science Research Colloquium /
Colloquium in Computational and Data Sciences
William Lamberti, CSI PhD Student
Department of Computational and Data Sciences
George Mason University
Classifying Pill Spies Using Storks
Friday, November 9, 3:00 p.m.
Center for Social Complexity, 3rd Floor Research Hall
All are welcome to attend.
Abstract: Simple and intuitive measures of shape are substantial challenges in image analysis and computer vision. While measures of shape do exist, there are only a few intuitive and mathematically derived measures for other polygons. In this talk, a measure, which we call shape proportions, for regular polygons and circles are shown. From these proportions, we find the corresponding encircled image-histograms for classification purposes. This method of using shape proportions and encircled image-histograms is called SPEIs (which is pronounced as ‘spy’). An analysis using simulated and actual shape images were compared to ensure its utility. Future work regarding applying SPEIs to NIH pill data using stratified over-representative k-folds cross-validation (abbreviated as STORKC, which is pronounced as ‘stork’) will be discussed.