We propose and evaluate a class of objective functions that rank hypotheses for feature labels. Our approach takes into account the representation cost and quality of the shapes themselves, and balances the geometric requirements against the photometric evidence. This balance is essential for any system using underconstrained or generic feature models. We introduce examples of specific models allowing the actual computation of the terms in the objective function, and show how this framework leads naturally to control parameters that have a clear semantic meaning. We illustrate the properties of our objective functions on synthetic and real images.