Image Forensics

The trustworthiness of photographs has an essential role in many areas, including: forensic investigation, criminal investigation, intelligence services, medical imaging, and journalism. The art of making image fakery has a long history. But, in todays digital age, it is possible to very easily change the information represented by an image without leaving any obvious traces of tampering. Despite this, no system yet exists which accomplishes effectively and accurately the image tampering detection task. The digital information revolution and issues concerned with multimedia security have also generated several approaches to digital forensics and tampering detection. Generally, these approaches could be divided into active and passiveblind

approaches. The area of active methods simply can be divided into the data hiding approach (e.g., watermarks) and the digital signature approach. We focus on blind methods, as they are regarded as a new direction and in contrast to active methods, they work in absence of any protecting techniques and without using any prior information about the image. To detect the traces of tampering, blind methods use the image function and the fact that forgeries can bring into the image specific detectable changes (e.g., statistical changes). When digital watermarks or signatures are not available, the blind approach is the only way how to make the decision about the trustworthiness of the investigated image. Image forensics is a (burgeoning detectors. Topics Detecting traces of resampling When two or more images are spliced (joined at the end) together , to create high quality and consistent image forgeries, almost always geometric transformations such as scaling, rotation or skewing are needed. Geometric transformations typically require a resampling and interpolation step. Thus, having available sophisticated resampling/interpolation detectors is very valuable.

)increasing rapidly research field and promise a significant improvement in forgery

detection in the neverending competition between image forgery creators and image forgery

The unique stature of photographs as a definitive recording of events is being diminished due, in part, to the ease with which digital images can be manipulated and altered. Although good forgeries may leave no visual clues of having been tampered with, they may, nevertheless, alter the underlying statistics of an image. For example, we describe how resampling (e.g., scaling or rotating) introduces specific statistical correlations, and describe how these correlations can be automatically detected in any portion of an image. This technique works in the absence of any digital watermark or signature. We show the efficacy of this approach on uncompressed TIFF images, and JPEG and GIF images with minimal compression. We expect this technique to be among the first of many tools that will be needed to expose digital forgeries.

 Detecting nearduplicated image regions In a common type of digital image forgery, called copymove forgery, a part of the image is copied and pasted into the another part of the same image, typically with the intention to hide an object or a region . The copymove forgery brings into the image several nearduplicated image regions. Detecting nearduplicated image regions In this work we focused on detecting a common type of digital image forgery, called copy-move forgery. In copy-move forgery, a part of the image is copied and pasted into another part of the same image, with the intention to hide an object or a region of the image. Duplicated regions may not always match exactly. This could be caused by a lossy compression algorithm, such as JPEG, or by possible use of the retouch tool. Our method is based on blur moment invariants, which allows successful detection of copy-move forgery, even when blur degradation, additional noise, or arbitrary contrast changes are present in the duplicated regions.

The main steps of the method are:

tiling the image with overlapping blocks, blur moment invariants representation of the overlapping blocks, principal component transformation, k-d tree representation, blocks similarity analysis, near-duplicated regions map creation. An example of the method's output is shown in the image below. Shown are the original version of the test image (top-left), its forged version (top-right), the modified region (bottom-left) and the constructed duplication map (bottom-right).

Noise inconsistencies analysis A commonly used tool to conceal traces of tampering is addition of locally random noise to the altered image regions. This operation may cause inconsistencies in the images noise . Therefore, the detection of various noise levels in an image may signify tampering.

When two or more images are spliced together, to create high quality and consistent image forgeries, almost always geometric transformations such as scaling or rotation are needed. These procedures are typically based on a resampling and interpolation step. In this paper, we show a blind method capable of finding traces of resampling and interpolation. Unfortunately, the proposed method, as well as other existing interpolation/resampling detectors, is very sensitive to noise. The noise degradation causes that detectable periodic correlations brought into the signal by the interpolation process become corrupted and difficult to detect. Therefore, we also propose a simple method capable of dividing an investigated image into various partitions with homogenous noise levels. Adding locally random noise may cause inconsistencies in the imagepsilas noise. Hence, the detection of various noise levels in an image may signify tampering.