The recognition problem is probably one of the most studied in computer vision. However, most techniques were developed on point features and were not designed to cope explicitly with uncertainty in measurements. The aim of this paper is to formulate recognition algorithms explicitly in terms of uncertain geometric features (such as points, lines, oriented points or frames). In the first part we review the principal matching algorithms and adapt them to work with generic geometric features. Then we analyze how to handle uncertainty on geometric features and the influence it has on the matching algorithms. Last but not least, we analyse four key problems for the implementation of these generic algorithms. Key Words: 3D Object Recognition, Invariants of 3D objects. 1 Introduction The recognition problem is probably one of the most studied in computer vision (see for instance [BJ85, CD86]) and many algorithms were developed to compare two images or to recognize objects with an a prior...