We develop and evaluate in this paper a multi-classifier framework for atlas-based segmentation, a popular segmentation method in biomedical image analysis. An atlas is a spatial map of classes (e.g., anatomical structures), which is usually derived from a reference individual by manual segmentation. An atlas-based classification is generated by registering an image to an atlas, that is, by computing a semantically correct coordinate mapping between the two. In the present paper, the registration algorithm is an intensity-based non-rigid method that computes a free-form deformation (FFD) defined on a uniform grid of control points. The transformation is regularized by a weighted smoothness constraint term. Different atlases, as well as different parameterizations of the registration algorithm, lead to different and somewhat independent atlas-based classifiers. The outputs of these classifiers can be combined in order to improve overall classification accuracy. In an evaluation study, biomedical images from seven subjects are segmented 1) using three individual atlases; 2) using one atlas and three different resolutions of the FFD control point grid; 3) using one atlas and three different regularization constraint weights. In each case, the three individual segmentations are combined by Sum Rule fusion. For each individual and for each combined segmentation, its recognition rate (relative number of correctly labeled image voxels) is computed against a manual gold-standard segmentation. In all cases, classifier combination consistently improved classification accuracy. The biggest improvement was achieved using multiple atlases, a smaller gain resulted from multiple regularization constraint weights, and a marginal gain resulted from multiple control point spacings. We conclude that multi-classifier methods have a natural application to atlas-based segmentation and the potential to increase classification accuracy in real-world segmentation problems.