Lockheed Martin Corporation

Charles Call

David L Ii

Dennis A Tillotson

Lawrence E Albertelli

Elliott D Reitz, Ii

Nina Kung

Robert S Lunt, Iv

A method and computer program product are disclosed for automatically encoding a complex system architecture for a pattern recognition classifier. A plurality of subclassifier states are defined as a plurality of sets of state variables, each set of variables corresponding to a subclassifier state. A set of rules are then determined for a state machine governing transitions between the plurality of subclassifier states. The plurality of sets of state variables and the determined rules are encoded into a configuration file. This configuration file is provided to a generic classifier system, including a state machine and a predefined generic classifier object.

Automatic encoding of a complex system architecture in a pattern recognition classifier

A method and system provide measures of the performance of a region of interest identification algorithm. The method includes obtaining known region of interest data for an object. A candidate region of interest for that object is identified using the region of interest identification algorithm to be evaluated. Candidate region of interest data is then obtained. The known region of interest is superimposed on the candidate region of interest. The area of the overlap between the known region of interest and the candidate region of interest is determined. Finally, a measure of performance based on the area overlap is obtained. The method is implemented in a system including one or more processors and or memories.

Method and system for providing a measure of performance of region of interest identification algorithms

The systems and methods of this invention provide a simple classifier suitable for real time use. The classifier adapts to changing system conditions and does not require recalculating the details of the classifier.

Growing community of inventors

Owego, NY, United States of America

Charles Call