Detection of Copy-Move Forgery in Digital Images
a Jessica Fridrich,
b David Soukal, and a Jan Lukáš
a Department of Electrical and Computer Engineering,
b Department of Computer Science
SUNY Binghamton, Binghamton, NY 13902-6000
professionalism{fridrich, dsoukal1, bk89322}@binghamton.edu斑痕
Abstract
英语自我介绍(带翻译)Digital images are easy to manipulate and edit due to availability of powerful image processing and editing software. Nowadays, it is possible to add or remove important features from an image without leaving any obvious traces of tampering. As digital cameras and video cameras replace their analog counterparts, the need for authenticating digital images, validating their content, and detecting forgerie
s will only increa. Detection of malicious manipulation with digital images (digital forgeries) is the topic of this paper. In particular, we focus on detection of a special type of digital forgery – the copy-move attack in which a part of the image is copied and pasted somewhere el in the image with the intent to cover an important image feature. In this paper, we investigate the problem of detecting the copy-move forgery and describe an efficient and reliable detection method. The method may successfully detect the forged part even when the copied area is enhanced/retouched to merge it with the background and when the forged image is saved in a lossy format, such as JPEG. The performance of the propod method is demonstrated on veral forged images.
1. The Need for Detection of Digital Forgeries
乖戾的
The availability of powerful digital image processing programs, such as PhotoShop, makes it relatively easy to create digital forgeries from one or multiple images. An example of a digital forgery is shown in Figure 1. As the newspaper cutout shows, three different photographs were ud in creating the composite image: Image of the White Hou, Bill Clinton, and Saddam Husin. The White Hou was rescaled and blurred to create an illusion of an out-of-focus background. Then, Bill Clinton and Saddam were cut off from two different images and pasted on the White Hou image. Care was taken to bring in the speaker stands with microphones while prerving the correct shado
ws and lighting. Figure 1 is, in fact, an example of a very realistic-looking forgery.
Another example of digital forgeries was given in the plenary talk by Dr. Tomaso A. Poggio at Electronic Imaging 2003 in Santa Clara. In his talk, Dr. Poggio showed how engineers can learn the lip movements of any person from a short video clip and then digitally manipulate the lips to arbitrarily alter the spoken content. In a nice example, a video gment showing a TV anchor announcing evening news was altered to make the anchor appear singing a popular song instead, while prerving the match between the sound and lip movement.
character是什么意思
The fact that one can u sophisticated tools to digitally manipulate images and video to create non-existing situations threatens to diminish the credibility and value of video tapes and images prented as evidence in court independently of the fact whether the video is in a digital or analog form. To tamper an analogue video, one can easily digitize the analog video stream, upload it into a computer, perform the forgeries, and then save the result in the NTSC format on an ordinary videotape. As one can expect, the situation will only get wor as the tools needed to perform the forgeries will move from rearch labs to commercial software.烟蒂
Figure 1 Example of a digital forgery.
Despite the fact that the need for detection of digital forgeries has been recognized by the rearch community, very few publications are currently available. Digital watermarks have been propod as a means for fragile authentication, content authentication, detection of tampering, localization of changes, and recovery of original content [1]. While digital watermarks can provide uful information about the image integrity and its processing history, the watermark must be prent in the image before the tampering occurs. This limits their application to controlled environments that include military systems or surveillance cameras. Unless all digital acquisition devices are equipped with a watermarking chip, it will be unlikely that a forgery-in-the-wild will be detectable using a watermark.
It might be possible, but very difficult, to u unintentional camera “fingerprints” related to nsor noi, its color gamut, and/or its dynamic range to discover tampered areas in images. Another possibility for blind forgery detection is to classify textures that occur in natural images using statistical measures and find discrepancies in tho statistics between different portions of the image ([2], [3]). At this point, however, it appears that such approaches will produce a large number of misd detections as well as fal positives.
In the next ction, we introduce one common type of digital forgeries – the copy-move forgery – and show a few examples. Possible approaches to designing a detector are discusd in Section 3. In Section 4, we describe the detection method bad on approximate block matching. This
approach proved to be by far the most reliable and efficient. The method is tested in the last
Section 5 on a few forgeries. In the same ction, we summarize the paper and outline future rearch directions.
2. Copy-Move Forgery
Becau of the extraordinary difficulty of the problem and its largely unexplored character, the authors believe that the rearch should start with categorizing forgeries by their mechanism, starting with the simple ones, and analyzing each forgery type parately. In doing so, one will build a diver Forensic Tool Set (FTS). Even though each tool considered parately may not be reliable enough to provide sufficient evidence for a digital forgery, when the complete t of tools is ud, a human expert can fu the collective evidence and hopefully provide a decisive answer. In this paper, the first step towards building the FTS is taken by identifying one very common class of forgeries, the Copy-Move forgery, and developing efficient algorithms for its detection.
男生英文名字大全
In a Copy-Move forgery, a part of the image itlf is copied and pasted into another part of the same image. This is usually performed with the intention to make an object “disappear” from the image by covering it with a gment copied from another part of the image. Textured areas, such as grass, foliage, gravel, or fabric with irregular patterns, are ideal for this purpo becau the copied areas will likely blend with the background and the human eye cannot easily discern any suspicious artifacts. Becau the copied parts come from the same image, its noi component, color palette, dynamic range, and most other important properties will be compatible with the rest of the image and thus will not be detectable using methods that look for incompatibilities in statistical measures in different parts of the image. To make the forgery even harder to detect, one can u the feathered crop or the retouch tool to further mask any traces of the copied-and-moved gments.
Examples of the Copy-Move forgery are given in Figures 2–4. Figure 2 is an obvious forgery that was created solely for testing purpos. In Figure 3, you can e a less obvious forgery in which a truck was covered with a portion of the foliage left of the truck (compare the forged image with its original). It is still not too difficult to identify the forged area visually becau the original and copied parts of the foliage bear a suspicious similarity. Figure 4 shows another Copy-Move forgery that is much harder to identify visually. This image has been nt to the authors by a third party who did not
disclo the nature or extent of the forgery. We ud this image as a real-life test for evaluating our detection tools. A visual inspection of the image did not reveal the prence of anything suspicious.
Figure 2 Test image “Hats”.
小学生英语手抄报
Figure 3 Forged test image “Jeep” (above) and its original version (below).
Figure 4 Test image “Golf” with an unknown original.
3. Detection of Copy-Move Forgery
Any Copy-Move forgery introduces a correlation between the original image gment and the pasted one. This correlation can be ud as a basis for a successful detection of this type of forgery. Becau the forgery will likely be saved in the lossy JPEG format and becau of a possible u of the retouch tool or other localized image processing tools, the gments may not match exactly but only approximately. Thus, we can formulate the following requirements for the detection algorithm:
1.The detection algorithm must allow for an approximate match of small image gments
2.It must work in a reasonable time while introducing few fal positives (i.e., detecting
incorrect matching areas).
3.Another natural assumption that should be accepted is that the forged gment will likely
be a connected component rather than a collection of very small patches or individual pixels.
In this ction, two algorithms for detection of the Copy-Move forgery are developed – one that us an exact match for detection and one that is bad on an approximate match.
Before describing the best approach bad on approximate block matching that produced the best balance between performance and complexity, two other approaches were investigated – Exhaustive arch and Autocorrelation.
3.1 Exhaustive arch
This is the simplest (in priciple) and most obvious approach. In this method, the image and its circularly shifted version (e Figure 5) are overlaid looking for cloly matching image gments. Let us assume that x ij is the pixel value of a grayscale image of size M×N at the position i, j. In the exhaustive arch, the following differences are examined:
| x ij – x i+k mod(M) j+l mod(N) |, k = 0, 1, …, M–1, l = 0, 1, …, N–1 for all i and j.
It is easy to e that comparing x ij with its cyclical shift [k,l] is the same as comparing x ij with its cyclical shift [k’,l’], where k’=M–k and l’=N–l.Thus, it suffices to inspect only tho shifts [k,l] with 1≤k ≤M/2, 1≤l ≤N/2, thus cutting the computational complexity by a factor of 4.
名师精讲
day after tomorrow
Figure 5 Test image “Lenna” and its circular shift.
For each shift [k,l], the differences ∆x ij= | x ij – x i+k mod(M) j+lmod(N)|, are calculated and
