Accurate object detection and location systems are essential for many robotic applications, including autonomous grasping and manipulation systems. In some cases, the target object may be obscured from view, in clutter, packaging, or debris. Millimeter-wave radar (mmWave) is a potential alternative to visual sensing in such scenarios, owing to its ability to penetrate typical low-density non-metallic materials. However, this approach requires accurate spatial calibration of the radar signal, over the robot workspace. We propose to achieve this with reference to visual data, which provides ground-truth locations for initial training of the system. Specifically, we describe a commodity mmWave radar system for detecting and localizing static metallic objects, over a 2-D workspace. We compare similarity, affine, and thin-plate spline (TPS) models of the spatial transformation from radar estimates to actual locations. Experiments were performed with a frequency modulated continuous wave (FMCW) multiple-input multiple-output (MIMO) device, using a starting frequency of 60 GHz and a bandwidth of 3.4 GHz. It is shown that the spline model performs best, achieving an average spatial error of 7 mm, which is an order of magnitude lower than that of the uncalibrated system.