Preventing reverse search engines from finding the origin of your image?

Question

I am planning to make a game, where I give the user an anime related image and they have to guess where its from.

However, most of the images, specially from popular anime are easy to use on Google reverse search to find and pin point the anime.

I've tried to see if I could make so it would not recognize the image but unhappily my tricks were not good enough.

Original image:

Grey-scale with horizontal flip:

Watermarking:

Puzzling the image with grey-scale:

Grey-scale with horizontal and vertical flip worked for this image but doesn't always work:

Also the above mentioned methods are rather easy for people to guess the anime.

I would like to know if there any good trick, that I could use on my images to make so it would not work on reverse search engines and yet not be so overcomplicated that I can implement on my program.

For example grey-scale, cropping, flipping are rather easy things to achieve in C#.

Answer 1

I think you were on the right track with your watermarking option, but you left too much of the original image in tact. Here are two images I tried that Google was unable to find:

Checkerboard

Reverse image search results

Mosaic

Reverse image search results

Another example

Reverse image search results

The first image returns a lot of "checkered flag" results, and the second returns lots of mosaic/collage images. Size does matter! I initially tried it with a much smaller checkerboard pattern (16px); Google was still able to identify that. These 32px squares seem to be a happy medium.

Based off of the information that DanS provided, I think this would be a dependable technique to fool Google (and easily automated!). I can only presume that someone who was able to identify this anime would still be able to do so from these images.

---

^{Ironically, the images I have created will eventually be indexed by Google and lead to this post, defeating the purpose!}

Answer 2

Google may use a different system but a large number of such services (tineye included) use perceptual hashes where the overall hash is close enough to be a match, rather than exact.

A whitepaper showed up a few years back which detailed the process. I haven't been able to find a link to it, but the basic system relies on a action chain to generate the hashes.

• Reduce the image to a small scale, usually 32x32 or 64x64
• Convert the image to greyscale
• Ramp up the contrast to a predefined value, to ensure a high level of difference between the black and white tones
• Calculate the pHash from the pixels in the resulting image

The process would be repeated for any uploaded image, and then cross checked with indexed hashes to find any near matches. In short, the image must be drastically changed across large portions to fool any system like this.

Answer 3

Just create a negative image of the original and invert it back with css. The user will see the image like normal, with same quality but when downloading it is inverted.

.myImageClass {

 filter: invert(100%);

}

The negative image will not be matched with the original (search result NL):

Also, tried it with reducing the colors to 256, Paint Shop Pro is king in doing this. The image will not directly matched to the original. If you combine this with method above, it could be excellent.

Answer 4

You can do something like this:

It is not 100% bulletproof, but it should throw off most image identification engines.

What I did was add black and white noise to the image as well as some displacement. Messing with the colors eg. only displacing one or two color channels would be even more effective, but complex to implement.

Answer 5

Try switching the file format you're saving in. Reverse image searches start by using some data that gets logged intrinsically into the image, which is probably why your obfuscation techniques haven't been working. JPEGs are particularly bad about this, PNGs not so much. With especially popular images, this might not work, however.

Ideally, find a way to show the image in an encapsulated form the user can't directly interact (copy -> paste) with. Unfortunately, I don't have the technical details on how this can be achieved currently, just that I've observed that the images used in Flash/Shockwave stuff has that property.

Secondarily: The plan as a whole - using copyrighted images without first seeking appropriate permissions from their owners, even assuming you provide attribution as soon as the puzzle is solved - puts you at risk of a takedown request or other sort of legal action, particularly if you're running the game in any volume. If it's possible to run the game using fanart (since you're more likely to get appropriate permission to use fanart than canonical content) it's probably better to do that.

Answer 6

You must confuse the search engine.

The best way to defeat automated image searching is by providing alternative images that cannot be identified or come from conflicting sources, and ones that confuse the specified pattern to be identified.

For example, if you provide an image composed of three images in alternating bands or strips and ask for the identification of the image composed from only every third band, so that, if isolated from the other bands, would appear as one image with gaps (where the other images' bands overlapped).

A human brain invokes "Closure" to perceptually connect the relevant images into one cohesive one that can be identified. The key is enough identifiable, but irrelevant detail in the rest of the image to confuse the engine.

Question two might be with the same image but asking for every third band starting with the second band. In effect, you could use one image with three different components and therefore three different answers.

Automated searches cannot attack such a spatial problem unless the unrelated bands are physically isolated from the search. Hard to do.

Answer 7

Stop there. Don't copy. Use original artwork. EDIT: Treat this as FYI.

By copying, you are indirectly trying to circumvent intellectual property protection. You are playing with fire.

There's also a flaw in your rationale and reasoning: Giving credit is NOT getting permission to use the image. It's not an "or" situation. It is copyright material. It does not matter if the result is placed up for sale or not. Your gain, financial or otherwise, is of no consequence to the offence. Even if the project was for academic or scientific research, you would need permission from, not credit given to, the copyright owners.

If your game fools a search, it probably won't survive a motivated lawyer pursuing an intellectual property violation enquiry.

Do not continue without getting written permission from the copyright owners for the "USE OF THEIR INTELLECTUAL PROPERTY."

You might be pleasantly surprised to discover that they give you permission based on your intended use for a game. Keep notes with dates and sketches. If you discover that the people you approached take your concept, sue them for broach of confidentiality. (That involves a separate NDA legal document and probably more time than it's worth.)

Don't guess. Don't hope. Find out before you put more effort into your miracle. It might be easier to say you're sorry than to ask permission but the way is legal, ethical, and more rewarding.