A method of configuring an anti-spoofing system to detect if a spoofing attack has been attempted, in which an image processing component of the anti-spoofing system is trained to process 2D verification images according to a set of image processing parameters, in order to extract depth information from the 2D verification images. The configured anti-spoofing system comprises an anti-spoofing component which uses an output from the processing of a 2D verification image by the image processing component to determine whether an entity captured in that image corresponds to an actual human or a spoofing entity. The image processing parameters are learned during the training from a training set of captured 3D training images of both actual humans and spoofing entities, each 3D training image comprising 2D image data and corresponding depth data, by: processing the 2D image data of each 3D training image according to the image processing parameters, so as to compute an image processing output for comparison with the corresponding depth data of that 3D image; and adapting the image processing parameters in order to match the image processing outputs to the corresponding depth data, thereby training the image processing component to extract depth information from 2D verification images.