All-Weather Feature-Based Combat Identification Navy SBIR FY2005.1 Sol No.: Navy SBIR FY2005.1 Topic No.: N05-030 Topic Title: All-Weather Feature-Based Combat Identification Proposal No.: N051-030-1578 Firm: ARGTEC, INC. 8640 Guilford Road, Suite 241 COLUMBIA, Maryland 21046 Contact: Monndy Eshera Phone: (410) 290-9891 Abstract: ARGTEC is leading the use of a new and innovative technology based on the theory of Attributed Relational Graph (ARG) in several application domains for robust feature-based target recognition and identification, data fusion, biometrics identification and content-based indexing and retrieval. We have achieved several breakthroughs in the development of this technology. Our ARG approach to Automated Fingerprint Identification Systems (AFIS) has been tested on large fingerprint databases provided by the FBI and the British Home Office, it delivered > 99% identification accuracy and close to zero false alarm rate in real-time. In benchmarks conducted by the customer, it outperformed other competing approaches with a significant margin, especially when presented with partial and spurious information. We propose to develop and implement a hierarchical ARG approach for feature-based combat target identification from RF-imagery. We will expand the AFIS ARG technology to a hierarchical ARG scheme capable of processing SAR/ISAR imagery. We will show that the hierarchical ARG representation technique, coupled with our suites of inexact matching algorithms are especially effective for the challenging scenarios of obscured, occluded and reduced signature targets in background clutter, dispersed over large areas or nearly indiscernible from decoys or civilian targets. ARGTEC has been working with several industrial partners in both defense and commercial arenas. Our commercialization strategy lies in converting our algorithm research and development into system innovations, then teaming with large system integrators to infuse our technology nuggets into fielded, operational systems. Benefits: Medical Imaging, Object Reconition, Industerial Robotics, Law Enforcement Return