Schlieren images abound in flow visualisation literature. By and large, these images have been used for the qualitative analysis of flow, such as the study of refraction patterns of shock waves and convection of plumes. Quantitative approaches, while present in literature, are limiting, typically requiring significant knowledge of both the flow and schlieren apparatus. This work proposes a radically alternate approach for extracting quantitative information from schlieren images. The method uses a scaled, derivative enhanced Gaussian process model to obtain true density estimates from two corresponding schlieren images with the knife-edge at horizontal and vertical orientations.