This project is a direct outgrowth of our work in recognizing parametric models using probabilistic inverse theory . The general idea is that uncertain interpretations can be regularized by accumulating evidence over time in situations where multiple observations are available (e.g. a stationary observer in a mobile environment or vice-versa). As with our earlier work, a probabilistic identification framework is used to represent beliefs in different object hypotheses by conditional probability density functions. What is new is the use of Bayesian chaining rules to update the beliefs as new data are acquired. In this way decisions can be postponed until evidence for a clear winner emerges. We are currently investigating the application of the recognition strategy to an appearance-based recognition problem, whereby optical flow fields, resulting from movements between camera and object, are used to obtain signatures related to object structure. Preliminary results indicate that despite the ambiguity inherent in the interpretation of optical flow (i.e. the confounding of structure, motion, and imaging geometry), the sequential approach can be used to successfully recognize objects provided that reasonable constraints are applied movement.