Invisible Geolocation Signature Extraction From a Single Image

Abstract

Geotagging images of interest are increasingly important to law enforcement, national security, and journalism. Today, many images do not carry location tags that are trustworthy and resilient to tampering; and the landmark-based visual clues may not be readily present in every image, especially in those taken indoors. In this paper, we exploit an environmental signature from the power grid, the electric network frequency (ENF) signal, which can be inherently captured in a sensing stream at the time of recording and carries useful time-location information. Compared to the recent art of extracting ENF traces from audio and video recordings, it is very challenging to extract an ENF trace from a single image. We address this challenge by first mathematically examining the impact of the ENF embedding steps such as electricity to light conversion, scene geometry dilution of radiation, and image sensing. We then incorporate the verified parametric models of the physical embedding process into our proposed entropy minimization method. The optimized results of the entropy minimization are used for creating a two-level ENF presence-classification test for region-of-capturing localization. It identifies whether a single image has an ENF trace; if yes, whether it is at 50 or 60 Hz. We quantitatively study the relationship between the ENF strength and its detectability from a single image. This paper is the first comprehensive work to bring out a unique forensic capability of environmental traces that shed light on an image's capturing location.

ENF Based Digital Multimedia Forensics: Survey, Application, Challenges and Future Work

“…Recently, the authors in [13] and [66] suggested that it is possible to detect and retrieve ENF from a single image captured by rolling shutter cameras under electric light. They showed that the sequential read-out time mechanism of a rolling shutter camera provides the resultant image to pick up instances of electric light signal entering at slightly various points in time, resulting in a brief section of ENF patterns.…”

“…Recently, the authors of [13] and [66] demonstrated that it is possible to obtain ENF traces from a solitary image captured with a rolling shutter camera. Their work tried to answer questions about the possibility of detecting ENF footprints in an image and whether the location of image capture operate at a frequency of 50 Hz or 60 Hz.…”

“…However, there are several unresolved research problems in the study of ENF in images. For instance, the method suggested in [13] and [66] is only effective for images that contain synthetically embedded ENF. Its effectiveness in realworld photos can be further improved by adopting a more sophisticated physical embedding model [43].…”