Computational ghost imaging relies on the decomposition of an image into patterns that are summed together with weights that measure the overlap of each pattern with the scene being imaged. These tasks rely on a computer. Here we demonstrate that the computational integration can be performed directly with the human eye. This builds upon the known persistence time of the human eye and we use our ghost imaging approach as an alternative to evaluate the temporal response of the eye. We verify that the image persistence time is of order 20 ms, followed by a further 20 ms exponential decay. These persistence times are consistent with previous studies but can now potentially be extended to include a more precise characterisation of visual stimuli and provide a new experimental tool for the study of visual perception.