We present the results of an edge detection algorithm applied on Electromagnetic Induction Imaging provided by an Atomic radio-frequency Magnetometer operating in an unshielded environment and at room temperature. Atomic Magnetometers have been already used for Imaging Techniques in the last few years, but the image reconstruction and the object pattern recognition lacks nowadays in terms of quality: the effect of scattering of e.m. signals at low-frequency provides blurred images, and does not allow for a clean ray – optics response, as in the case of X rays. Our algorithm, based on solved Gaussian Noise Recognition, demonstrates excellent spatial resolution achieved despite low Signal-to-Noise-Ratio.