Target recognition systems have undergone a variety of changes over the past 20 years. Initial systems exploited signal processing techniques to detect ground-based targets based on one-dimensional signals. Limitations of these systems eventually led to the development of automated target recognizers (ATRs) that processed two-dimensional digital images to detect, classify, and identify targets. Though their performance exceeded that of signal processing systems, ATRs exhibited several deficiencies to which artificial intelligence (Al) offered numerous potential solutions. This paper reviews the evolution of target recognition systems with primary focus on Al applications. Deficiencies of Al approaches to target recognition are presented and complemented by a discussion of a blackboard-based ATR system currently being developed at Georgia Tech.