Using adaptive resonance theory networks and fuzzy matching to recognize target features in thermal images

Allocating resources to targets in a military engagement is complicated by the diversify of potential targets and by the need to make allocation decisions quickly. This paper describes a hybrid method applied to thermal images in order to discriminate targets with tracks from those having wheels. The hybrid method employs adaptive resonance theory neural networks and a fuzzy matching procedure to classify targets in thermal images that have been subjected to conventional edge enhancement. The performance of the hybrid method is compared to techniques employing global and local template matching. The hybrid algorithm was 15 to 30 times faster than global template matching. While local template matching was faster than the hybrid algorithm in some test cases, the hybrid algorithm generated far fewer false alarms. Also, using fuzzy criteria to locate elements of composite features enables the method to tolerate variations in both target scale and orientation.