| 摘要 |
A model characterizes an error pattern that is functionally related to first and second patterns and to one or more model parameters, which may be unknown. The error pattern may be derived by deforming one or both of the first and second patterns, such as by applying a generally smooth, non-uniform deformation field. A likelihood for the model that the error pattern is zero, given the second pattern, is determined. If the model parameter(s) is unknown, the likelihood may be used to estimate (or infer) the parameter(s) that tend to maximize the likelihood for a plurality of stored patterns. The estimated parameters may, in turn, be employed to determine the likelihood as a measure of similarity between an observed pattern and the patterns that the model is capable of generating. In addition, the likelihood may be used to classify an observed pattern according to the likelihood that the observed pattern has relative to one or more models.
|
