Mark Vogel has extensive experience in developing image processing and pattern recognition systems. He has created innovative learning, information extraction, and classification techniques for biomedical, remote sensing, and object recognition applications. Mark is skilled in algorithm development, software generation, smart controls, and vision system design. He received his Ph.D. in Electrical Engineering from Carnegie Mellon University, with his doctoral work focused on biomedical pattern recognition and information theory. Mark has published numerous technical articles, reports, and conference papers on image analysis, object recognition, and learning and classification techniques.

Biomedical Technology

Mark developed a novel information tree algorithm for analyzing dermatoglyphic (finger and handprint) data, aiding in the diagnosis of some genetic disorders. He also created a statistical package for medical researchers and applied clustering and classification techniques to a patient history database to evaluate the effectiveness of alternative treatments. Additionally, he designed automated cell screening algorithms that select significant phenomena for rapid review and classification by experts. Mark’s work includes the design of a fully automated microscope vision system for blood sample analysis, capable of automatically focusing, color correcting, finding red blood cells, locating and mapping white blood cells, and providing a six-part differential analysis.

Multi-Sensor Systems

Mark designed data fusion techniques for combining information from multiple sensors for automated object recognition. He created advanced graph-matching recognition algorithms capable of classifying objects under conditions of partial occlusion. His research includes work with visible light, infrared, real beam radar, and synthetic aperture radar (SAR) based processing. Mark applied classical statistical pattern recognition and neural network techniques to image data for enhanced feature extraction and recognition. He also developed advanced automated target recognition (ATR) algorithms for recognizing partially occluded objects and analyzed and specified stereo collection systems for tallying and measuring parts and products.

Remote Sensing

Mark developed techniques for extracting information from satellite data and automatically generating ground feature databases. He utilized stereo extraction techniques for automated terrain elevation map creation and refined techniques for combining multi-look imagery to enhance object signatures and extract information.

Founded Recognition Science in 1994

Mark founded Recognition Science, where we design intelligent software products and provides consulting support for vision system development and object recognition applications. RSI developed the Recognition Toolkit, a software package for building image-based object recognition products, which is an add-on to the KBVision and Aphelion image processing software of Amerinex Applied Imaging. The Recognition Toolkit contains evaluation tools, classifiers, and corresponding learning and training routines for rapid development of tailored recognition software.

Previous Roles

Mark has held significant roles, including Biomedical Information Processing Coordinator for a joint program between Carnegie Mellon University and the A. I. duPont Institute. He has been a project leader on many recognition and image analysis efforts at The Analytic Sciences Corporation and group leader for algorithms and modeling in the research laboratory at Textron Systems Corporation.