With the widespread deployment of wireless sensor networks and the nascent Internet of Things (IoT), enabling devices to be connected in wider, and denser ecosystems, improved wireless security has become of paramount importance. Limited power and computational resources of these devices, however, render sophisticated algorithms and protocols not suitable for all the devices. Radio Frequency (RF) fingerprinting has the potential to enhance the security and with increasing popularity of deep learning, RF fingerprinting approaches have attracted attention with new techniques proposed. In this paper we present a novel waveform domain-based approach operating on images generated from captured raw samples for device identification. The use of images, as opposed to raw sample sequences, enables the capture of information from theoretically infinite number of raw samples without impacting the structure and the complexity of the subsequent deep learning processing. We use a simple Dense Neural Network (DNN) model which is implemented and trained on waveform images generated from the captured raw samples. The efficacy of the proposed approach is demonstrated using over-the-air signals captured from 12 Zigbee devices, with the proposed approach achieving near 99% identification accuracy.