Browse by topic
Type of publication
An Approximate Nearest Neighbours Search Algorithm Based on the Extended General Spacefilling Curves Heuristic. Workshop on Statistical Pattern Recognition SPR-98, 1998.In this paper, an algorithm for approximate nearest neighbours search in vector spaces is proposed. It is based on the Extended General Spacefilling Curves Heuristic (EGSH). Under this general scheme, a number of mappings are established between a region of a multidimensional real vector space and an interval of the real line, and then for each mapping the problem is solved in one dimension. To this end, the real values that represent the prototypes are stored in several ordered data structures (e.g. btrees). The nearest neighbours of a test point are then efficiently searched in each structure and placed into a set of candidate neighbours. Finally, the distance from each candidate to the test point is measured in the original multidimensional space, and the nearest one(s) are chosen.