Automatically recovering human poses from visual input is useful but challenging due to variations in image space and the high dimensionality of the pose space. In this paper, we assume that a human silhouette can be extracted from monocular visual input. We compare three shape descriptors that are used in the encoding of silhouettes: Fourier descriptors, shape contexts and Hu moments. An examplebased approach is taken to recover upper body poses from these descriptors. We perform experiments with deformed silhouettes to test each descriptor?s robustness against variations in body dimensions, viewpoint and noise. It is shown that Fourier descriptors and shape context histograms outperform Hu moments for all deformations.