Skip to content. Skip to navigation
CIM Menus
 

Fast, High Dynamic Range Light Field Processing for Pattern Recognition


Scott McCloskey


March 11, 2016 at  10:00 AM
McConnell Engineering Room 320

Abstract:

This talk addresses how the image processing steps involved in computational imaging can be adapted to specific image-based recognition tasks, and how significant reductions in computational complexity can be achieved by leveraging the recognition algorithm’s robustness to defocus, poor exposure, and the like. Unlike aesthetic applications of computational imaging, industrial imaging systems need not produce the best possible image quality, but instead need only satisfy certain quality thresholds that allow for reliable recognition. The talk specifically addresses light field rendering for recognition tasks with some robustness to defocus, and presents both a novel optimization problem and a provably optimal solution via dynamic programming.

Bio:

Scott McCloskey joined Honeywell Labs in 2007, following his completion of graduate work at McGill. He is currently an Engineering Fellow and serves as the principle investigator for several commercial and externally-funded research projects. His research interests include computational photography, computer vision, and biometrics. A former CIMite, Dr. McCloskey received his PhD in Computer Science from McGill University in 2008, a MS in Computer Science from the Rochester Institute of Technology, and a BS in Computer Science and Math from the University of Wisconsin-Madison. He is the author of many peer-reviewed conference papers including recent work at ICCP, ECCV and ICCV. He is a Program Chair for WACV 2016.