Micah K. Johnson

Exposing digital forgeries by detecting inconsistencies in lighting

When creating a digital composite of, for example, two people standing side-by-side, it is often difficult to match the lighting conditions from the individual photographs. Lighting inconsistencies can therefore be a useful tool for revealing traces of digital tampering. Borrowing and extending tools from the field of computer vision, we describe how the direction of a point light source can be estimated from only a single image. We show the efficacy of this approach in real-world settings.

Exposing Digital Forgeries in Complex Lighting Environments

The availability of sophisticated digital imaging technology has given rise to digital forgeries that are increasing in sophistication and frequency. We describe a technique for exposing such fakes by detecting inconsistencies in lighting. We show how to approximate complex lighting environments with a low-dimensional model and, further, how to estimate the models parameters from a single image. Inconsistencies in the lighting model are th.en used as evidence of tampering.

Ground truth dataset and baseline evaluations for intrinsic image algorithms

The intrinsic image decomposition aims to retrieve “intrinsic” properties of an image, such as shading and reflectance. To make it possible to quantitatively compare different approaches to this problem in realistic settings, we present a ground-truth dataset of intrinsic image decompositions for a variety of real-world objects. For each object, we separate an image of it into three components: Lambertian shading, reflectance, and specularities. We use our dataset to quantitatively compare several existing algorithms; we hope that this dataset will serve as a means for evaluating future work on intrinsic images.

Exposing digital forgeries through chromatic aberration

Virtually all optical imaging systems introduce a variety of aberrations into an image. Chromatic aberration, for example, results from the failure of an optical system to perfectly focus light of different wavelengths. Lateral chromatic aberration manifests itself, to a first-order approximation, as an expansion/contraction of color channels with respect to one another. When tampering with an image, this aberration is often disturbed and fails to be consistent across the image. We describe a computational technique for automatically estimating lateral chromatic aberration and show its efficacy in detecting digital tampering.

Exposing digital forgeries through specular highlights on the eye

When creating a digital composite of two people, it is difficult to exactly match the lighting conditions under which each individual was originally photographed. In many situations, the light source in a scene gives rise to a specular highlight on the eyes. We show how the direction to a light source can be estimated from this highlight. Inconsistencies in lighting across an image are then used to reveal traces of digital tampering.

Digital Image Authentication From JPEG Headers

It is often desirable to determine if an image has been modified in any way from its original recording. The JPEG format affords engineers many implementation trade-offs which give rise to widely varying JPEG headers. We exploit these variations for image authentication. A camera signature is extracted from a JPEG image consisting of information about quantization tables, Huffman codes, thumbnails, and exchangeable image file format (EXIF). We show that this signature is highly distinct across 1.3 million images spanning 773 different cameras and cell phones. Specifically, 62% of images have a signature that is unique to a single camera, 80% of images have a signature that is shared by three or fewer cameras, and 99% of images have a signature that is unique to a single manufacturer. The signature of Adobe Photoshop is also shown to be unique relative to all 773 cameras. These signatures are simple to extract and offer an efficient method to establish the authenticity of a digital image.

Retrographic sensing for the measurement of surface texture and shape

We describe a novel device that can be used as a 2.5D “scanner” for acquiring surface texture and shape. The device consists of a slab of clear elastomer covered with a reflective skin. When an object presses on the skin, the skin distorts to take on the shape of the objects surface. When viewed from behind (through the elastomer slab), the skin appears as a relief replica of the surface. A camera records an image of this relief, using illumination from red, green, and blue light sources at three different positions. A photometric stereo algorithm that is tailored to the device is then used to reconstruct the surface. There is no problem dealing with transparent or specular materials because the skin supplies its own BRDF. Complete information is recorded in a single frame; therefore we can record video of the changing deformation of the skin, and then generate an animation of the changing surface. Our sensor has no moving parts (other than the elastomer slab), uses inexpensive materials, and can be made into a portable device that can be used “in the field” to record surface shape and texture.

Video face replacement

We present a method for replacing facial performances in video. Our approach accounts for differences in identity, visual appearance, speech, and timing between source and target videos. Unlike prior work, it does not require substantial manual operation or complex acquisition hardware, only single-camera video. We use a 3D multilinear model to track the facial performance in both videos. Using the corresponding 3D geometry, we warp the source to the target face and retime the source to match the target performance. We then compute an optimal seam through the video volume that maintains temporal consistency in the final composite. We showcase the use of our method on a variety of examples and present the result of a user study that suggests our results are difficult to distinguish from real video footage.

Multi-scale image harmonization

Traditional image compositing techniques, such as alpha matting and gradient domain compositing, are used to create composites that have plausible boundaries. But when applied to images taken from different sources or shot under different conditions, these techniques can produce unrealistic results. In this work, we present a framework that explicitly matches the visual appearance of images through a process we call image harmonization, before blending them. At the heart of this framework is a multi-scale technique that allows us to transfer the appearance of one image to another. We show that by carefully manipulating the scales of a pyramid decomposition of an image, we can match contrast, texture, noise, and blur, while avoiding image artifacts. The output composite can then be reconstructed from the modified pyramid coefficients while enforcing both alpha-based and seamless boundary constraints. We show how the proposed framework can be used to produce realistic composites with minimal user interaction in a number of different scenarios.

Detecting Photographic Composites of People

The compositing of two or more people into a single image is a common form of manipulation. We describe how such composites can be detected by estimating a cameras intrinsic parameters from the image of a persons eyes. Differences in these parameters across the image are used as evidence of tampering.