The problem of 3D object recognition has been one that has perplexed the computer vision community for the past two decades. This paper describes and analyzes techniques which have been developed for object representation and recognition. A set of specifications, which all object recognition systems should strive to meet, forms the basis upon which this critical review has been formulated. The literature indicates that there is a powerful requirement for a precise and accurate representation, which is simultaneously concise in nature. Such a representation must be relatively inexpensive and provide a means for determining the error in the surface fit such that the effects of error propagation may be analyzed in the system and appropriate confidence bounds determined in the subsequent pose estimation. (C) 2002 Elsevier Science (USA).