Adaptive target recognition

Target recognition is a multilevel process requiring a sequence of algorith ms at low, intermediate and high levels. Generally, such systems are open l oop with no feedback between levels and assuring their performance at the g iven probability of correct identification (PCI) and probability of false a larm (Pf) is a key challenge in computer vision and pattern recognition res earch. In this paper, a robust closed-loop system for recognition of SAR im ages based on reinforcement learning is presented. The parameters in model- based SAR target recognition are learned. The method meets performance spec ifications by using PCI and Pf as feedback for the learning system. It has been experimentally validated by learning the parameters of the recognition system for SAR imagery, successfully recognizing articulated targets, targ ets of different configuration and targets at different depression angles.