A novel approach, which is based on combining the competence of interest point detectors to capture primitives and the capability of geometric constraints to discriminate between spatial configurations of these primitives is presented. In the proposed approach, the geometric constraints are enforced by means of barycentric coordinates, a mathematical tool that has been utilized in the relevant literature as a neighborhood constraint. In the context of our research, however, these coordinates are utilized as a geometric description of a group of interest points. Using this description, local appearance descriptor based potential matches are intended to be filtered and evaluated according to their geometric consistency. This method is applicable to one-to-one image matching in its current form, and to classification tasks after extensions for appearance generalization.