Fast Alignment Using Probabilistic Indexing

The alignment method [4] is a model-based object recognition technique that determines possible object transformations from three hypothesized matches of model and image points. For images and/or models with many features, the running time of the alignment method can be large. This paper presents methods of reducing the number of matches that must be examined. The techniques we describe are: Using the probabilistic peaking effect [1] to eliminate unlikely matches (implemented in a probabilistic indexing system [6]) and eliminating groups of model points that produce large errors in the transformation determined by the alignment method. Results are presented that show we can achieve a speedup of over two orders of magnitude while still finding a correct alignment. 1 Introduction The alignment method [4] is a model-based object recognition technique for recognizing three-dimensional objects from a single view in two-dimensional images. For each model in the database, triples of image po..