This paper introduces a model-based approach to reconstruct three-dimensional defect profiles from eddy-current nondestructive evaluation signals. The method casts the defect characterization problem as an exercise in maximization of an appropriate cost function. The method uses an edge-based finite-element forward model to simulate the underlying physical process and a genetic search algorithm to solve the optimization (maximization) problem. The paper presents techniques to reduce the computation cost for evaluating the cost function as well as local search methods to speed the genetic search process. Test results confirm the validity of the approach.