Professor of computer science with over two decades of experience at the forefront of the analysis and processing of electronic documents and document images. Has contributed extensively to the document analysis research community on problems including page and zone segmentation, labeling and genre classification, forms processing, signature detection and verification, modeling of handwriting, image quality estimation, enhancement, image-based indexing and retrieval, and related mobile applications. He has specialized technical expertise in the analysis, indexing, and retrieval of information from a range of sources, including images, video, and audio, as well as related media forensics.
Formal Education
- Ph.D. in Computer Science, University of Maryland
- M.S. in Computer Science, University of Maryland
- B.S. in Computer Science and Mathematics, Bloomsburg University
Career Highlights
- Developed, selected, and oversaw research funding in the areas of computer vision, human language technologies, and voice analytics for a major U.S. government research agency
- Co-founder of a company that developed cross-platform computer vision algorithm implementations for image processing and document analysis for a range of mobile devices from multiple manufacturers
- Consultant to industry and government agencies, including major government agencies in the intelligence and space sectors, in the areas of document image understanding, document retrieval, and image processing
- Founding director of an interdisciplinary university research laboratory focused on automated audio and video processing technologies to assist the U.S. intelligence community
Expert Qualifications
- Submitted an expert report and testified at deposition and trial as an defense expert in a U.S. District Court for the Northern District of California patent infringement litigation related to Optical Character Recognition (OCR) technologies
- Testifying expert for the plaintiff in a patent infringement litigation in the U.S. District Court for the Eastern District of Texas regarding automatic cleaning and enhancing technology for scanned documents
- Retained as a testifying expert in other intellectual property litigations relating to image retrieval, mobile and remote document systems, and methods of organizing digital images
- Assisted with a court-ordered detection and removal of duplicate document images from discovery materials
Related Experts
- Power Electronics and Motor Drive Expert Profile
- Electrical Fire and Battery Failure Expert Profile
- Crystalline Coatings and Optical Cavity Systems Expert Profile
- Embedded Firmware and Digital Signal Processing Expert Profile
- Real-Time Embedded Systems and Firmware Expert Profile
Frequently Asked Questions
What types of cases can this expert support?
This expert has testified in patent cases involving OCR, document enhancement, and mobile imaging systems, serving as both defense and plaintiff expert. They're equipped to support image retrieval, mobile/remote document systems, and intellectual property disputes. Across their litigation and research background, they can advise on cases involving AI, signal processing, computer vision, document automation, and consumer electronics.
What is this expert's technical background?
They hold a Ph.D. and M.S. in computer science from the University of Maryland, plus a B.S. in computer science and mathematics. Their 20+ year career includes leading DARPA research funding in computer vision and voice analytics, co-founding a computer vision company for mobile platforms, and directing a university research lab for audio and video processing. They've also consulted for the NSA Advisory Board and NASA on image and document analysis.
What technologies does this expert specialize in?
This expert specializes in AI and machine learning applied to document and image analysis—page segmentation, forms processing, signature detection, handwriting modeling, image enhancement, and quality estimation. They have expertise in computer vision, speech recognition, multimedia audio/video processing, pattern recognition, forensic analysis, and image-based indexing. Their work includes pen computing, wireless protocols, and media forensics.
- Artificial intelligence and machine learning
- Computer vision
- Forensic analysis
- Image processing
- Multimedia audio and video processing
- Pattern recognition
- Pen computing
- Speech recognition
- Wireless protocols
- U.S. District Courts