In order to obtain more useful information on the accuracy of forecasts that contain high-amplitude, small-scale features, the traditional paradigm of "point-to-point" verification is expanded to the verification of "events" or objects. Here, events are defined as significant and interesting meteorological phenomena. The main challenge is to develop objective methods to outline, extract, characterize, and classify events found within forecast and observed fields. Image processing tools, such as edge detection, will be used to locate events. Attributes will be assigned to each event based upon, for example, shape, structure, horizontal extent, amplitude, etc. Events will be classified based upon these attributes using data mining algorithms. New measures of accuracy can then be obtained by examining, for example, the similarity of forecast and observed events. Results from this work in progress will be reported at the conference.