A system for capturing a plantar image is provided, which is based on a depth sensor or 3D image capturing device connected to a portable structure having: first legs; a first frame that holds a glass pane; and an elastic membrane on which a patient places his or her foot, making contact with the glass pane positioned there below, in the manner of a floor, to capture the plantar image by means of the depth sensor disposed beneath the glass pane. Respective platforms provided with a pair of second legs can be joined to the first frame. A system is provided that includes a transparent floor in a portable structure that allows the assembly to be transported so as to be able to capture the patient's plantar image in any desired place.