| 摘要 |
The present invention relates to a method and system for evaluating the class of a test datum in a data space having a dimension D, where D = 3, each datum belonging to at least one class grouping together a plurality of data. The method comprises a step of projecting a set of reference data of the data space into a space having a dimension Q, where Q < D, the class of each reference datum being known. The method also comprises a step of calculating a measurement of similarity of the test datum to each of the reference data. The method also comprises a step of partitioning the projection space into a plurality of unconnected regions, each containing the projection of a single reference datum. The method finally comprises a step of evaluating the class of the test datum, said class being evaluated as being the same class as one of the reference data contained in one of the regions containing the reference data closest to the test datum in terms of the measurement of similarity. Said regions are indeed the regions most likely to contain a projection of the test datum. The invention can be used as a decision aid in discrimination, recognizing shapes, and detecting anomalies. |
