This paper presents a method of visual servoing to a face whose position/orientation is estimated by model-based matching. The proposed method utilizes a model-based matching method and an evolutionary search technique of 1-Step Genetic Algorithm (1-Step GA) for real-time recogniton of dynamic images. We demonstrate the capability of the proposed method by applying it to the visual servoing to 3-D position/orientation (6DOF) of moving human face.