How can I tell if a photo has been edited or manipulated? Are there techniques for distinguishing real photos from fakes?

Are there software tools that can help? Are there things I can do in Photoshop or other imaging software which will help reveal the truth?

  • 6
    \$\begingroup\$ "I can tell by the pixels." \$\endgroup\$
    – mattdm
    Commented Nov 8, 2012 at 5:16
  • 2
    \$\begingroup\$ Also: is the jpg compressed, artifact-full version of an image real or not? Is a straightened version (which rotates all the pixels and interpolated) real or not? For some curious reasons after all these centuries when the concepts of reality and truthness come out, they tun out to be .... complex. \$\endgroup\$
    – Francesco
    Commented Nov 8, 2012 at 7:45
  • \$\begingroup\$ @Francesco, that's why searching some software tool to identify that.. \$\endgroup\$
    – Gururaj T
    Commented Nov 8, 2012 at 7:50
  • 3
    \$\begingroup\$ I'm going to edit this to completely remove the bizarre out of context image and focus on the general. If you want to know more about this particular image, please post a new question but with some explanation of what it is supposed to represent and why you think it might be fake. \$\endgroup\$
    – mattdm
    Commented Nov 8, 2012 at 13:16
  • 1
    \$\begingroup\$ Ten years on... Now we have generative AI. The answers below all describe tricks for distinguishing "original" images from "edited" images. But, generative AI creates new, original images of scenes that never existed. And if the AI was trained on a collection of real photographs, then the images that it generates all will tend to look like real photographs. Like real, un-edited photographs of unreal things. Or even, with the right training data, of actual real people, in places they never actually visited, doing things they never actually did. \$\endgroup\$ Commented Nov 16, 2023 at 23:54

4 Answers 4


There are several ways to [attempt to] determine the veracity of an image, with respect to whether it represents a unique capture of a single scene:

Image data level inconsistencies

Certain processing operations result in telltale "signatures" embedded in the data which are often invisible to the eye but may be identified by statistical analysis. The best example of this is lossy image compression, e.g. JPEG. JPEG works in the frequency domain, removing frequencies that are below a certain threshold, depending on the level of compression. So if an image contains distinct areas with different patterns of missing frequencies, then it is highly likely that it is composed of separate images that were previously saved at different compression levels. This technique wont work in the case of high quality source images, or when the composite is saved at a much higher level of compression.

Repeated image content

A common method of removing objects works by copying the surrounding areas to cover something up. By identifying areas of an image that are identical to other areas is a sure sign of tampering. Even if the scene contains genuine repeated details they will differ in appearance due to scale/perspective/lighting/noise. A good example of this is the Iranian missile launch image, in which missiles are cloned to appear more numerous:

Inconsistent lighting/perspective

Some images are impossible due to inconsistencies in the lighting direction, i.e. if the scene is clearly lit from the left and one object casts a shadow to the left (toward the lightsource) then it is likely the object has been added artificially. Likewise with perspective, if you can see the top of one object but not another they are either not parallel, or one has been comped in. This type of analysis can be complicated when there are many lightsources, or if other parts of the scene are deceptive (surfaces are assumed to be flat when they are not). The moon landing photos have been implicated for having shadows in different directions, however shadow directions can differ when close to a lightsource, or when the surfaces receiving shadows are not parallel (such as the bumpy lunar surface). Likewise perspective analysis can fail when certain assumptions (such as objects are equal size, walls are parrellel etc.) are incorrect. Here is a famous example, the following image is not doctored:

It just looks wrong

This is the most common and at times the least reliable method. The brain is used to seeing real* image information from the eyes. Something in the image doesn't look real, it has failed some internal pattern matching. It could be a subtle inconsistency of lighting, it could be an apparent outline or some highly unusual shading. The first reason this approach is unreliable is that cameras don't work in the same way as the eye. The second reason is that people are now used to the idea that images are commonly manipulated, and will often look for inconsistencies that aren't there, they will overanalyse and anything that looks "odd" will be taken as evidence for manipulation.

Psychology / common sense

Finally you have to ask yourself if any motive exists for manipulation. Does the potential perpetrator have anything to gain? Is it even plausible that the photo is not real? The moon landings are another example of this - is it plausible that the number of people who must have been involved were able to remain silent for so long?

None of these techniques (except perhaps perspective inconsistency) apply to real, undoctored photographs of scenes which are themselves fake, or photographed in a way to deceive the viewer. A good example of this are the famous Cottingley_Fairies images. In this case the photographs were genuine, but the fairies were made of card!


While you can't know for sure, the site fotoforensics.com can provide some insight. Be sure to read the tutorial and check this link for your image:

From their analysis, I'd guess the photo has not been doctored.

I'm not associated with this site in anyway, although I do think it's pretty interesting stuff.

  • \$\begingroup\$ Also check this blog post. It discusses a recent photo and how they used the site mentioned by @Jeff. \$\endgroup\$
    – Roflo
    Commented Nov 8, 2012 at 14:05

Examination of hidden pixels and JPEG quantization tables may be used to determine whether a JPEG file has been altered from its original.

The JPEG compression algorithm

Note that only two steps are intentionally lossy: color downsampling and quantization. Other minor losses are the result of rounding errors. All other steps are lossless.

  1. Convert colorspace. If desired, downsample color information (Lossy). If not downsampled, loss of information is the result of rounding error.

  2. Segmentation. Divide each channel into 8x8 blocks (MCU = Minimal Coding Unit). (Lossless)

    If the image dimensions are not both divisible by 8, the image will need to be padded with extra pixels to form the MCUs. Examination of these hidden pixels may provide a clue to the source of the images. (See Foto Forensics: Hidden Pixels)

    Note: If color channels were downsampled, MCUs may effectively be 16x8, 8x16, or 16x16, in terms of the original image. However, the MCUs are still all 8x8 blocks.

  3. Discrete Cosine Transform (DCT) on each MCU. Loss of information is the result of rounding error.

  4. Quantization. The value in each cell of the MCU is divided by a number specified in a quantization table (DQT). Values are rounded down, many of which will become zero. This is the primary lossy portion of the algorithm.

    Different settings on different cameras and software use different quantization tables. If the DQT is not consistent with the claimed origin, the file is unlikely to be the original. (See JPEG Compression Quality from Quantization Tables)

    Estimating JPEG "quality" is an indirect way to infer the DQT. However, it is is not definitive. (See Foto Forensics: Estimate JPEG Quality)

  5. Zig-Zag Scan. Rearrange values in each MCU into a sequence of numbers following a zig-zag pattern. The zeros that occurred during quantization will be grouped together. (Lossless)

  6. DPCM = Differential Pulse Code Modulation. Convert the number sequences into a form that is easier to compress. (Lossless)

  7. RLE = Run Length Encoding. Consecutive zeros are compressed. (Lossless)

  8. Entropy/Huffman Coding. (Lossless)


  • On Windows, JPEG Snoop may be used to examine JPEG files.

  • Exiftool may also be used to view the quantization table:

    exiftool -v3 image.jpg | grep -v RST

.jpg can also prove real You can take a real picture of something on your android cell phone and click the 3 dots on top upper right side on picture on your screen under details it says .jpg (not sure of .jpg quality)

  • \$\begingroup\$ With all due respect, that proves nothing at all. \$\endgroup\$
    – Philip Kendall
    Commented Nov 15, 2023 at 8:45
  • \$\begingroup\$ This doesn't answer the question, "how can I detect if a photo is real or faked?" \$\endgroup\$
    – scottbb
    Commented Nov 16, 2023 at 21:39

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.