Information Security Stack Exchange is a question and answer site for information security professionals. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Would using the "flaws" in human perception of an optical illusion graphic allow a system to differentiate between humans and machines (using these pictures like a CAPTCHA)?

Some examples are where a human might count "dots" (that are not really there) or choose which parts of a picture have matching colors (when the colors don't actually match due to the illusion).

Some example pictures: All cars same size

All the cars above are the same size, but humans see one as larger.

Orange circle same size

The orange circles above are the same size, but humans see one as larger.

squares same color

The squares above are same color, but humans see the bottom one as lighter. Cover the line the arrow is pointing at with your finger and you will now see the squares as a computer would.

If a computer were asked to pick out the largest car or circle or the lighter square from these pictures, it would have more difficulty than a human would.

share|improve this question
    
I don't yet fully understand, since "flaws" could somehow be simulated by a machine IMHO. – Mok-Kong Shen Mar 6 at 12:09
6  
I have enough trouble solving the ridiculous lets-fuzz-a-bunch-of-unrelated-words-to-oblivion CAPTCHA that are currently fashionable, without also having to squint, unfocus my eyes or do a handstand, thank you very much. Nevermind those who do not have good vision, or an appropriate screen or who just do not see those illusions the same way as others. Please, stop trying to invent more "solutions" that exclude people... – thkala Mar 6 at 15:17
    
It not obligatory that machines have to solve CAPTCHAs for the bad boys. Look at this: en.wikipedia.org/wiki/CAPTCHA#Cheap_or_unwitting_human_labor – Noir Mar 6 at 18:23

This will probably not work for a long time because there is nothing inherent in these "flaws" which cannot be reproduced by a machine.

The first problem you need to solve is to create an algorithm which produces such images which are easy to solve for most humans but hard to solve for current image recognition. Once you have this system in place to protect important sites it gets attractive enough to break it. And then it is only a question of time, i.e. the efforts to break the captcha are related to how much can be gained by breaking it.

share|improve this answer

Optical illusions are caused by shortcuts used by the human visual system in order to optimize data processing or throw away useless information. They are well known phenomena and there's nothing that makes them any more difficult to solve than regular image recognition. In fact, I would say that understanding a complex scene, such as counting the number of children in a given image of a playground, would be significantly more difficult than recognizing which of two lines "looks longer".

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

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