Sunday, May 20, 2007

Image-based CAPTCHA

The brief overview of the most known implementations

  • Carnegie Mellon's PIX CAPTCHA - the so called "naming images CAPTCHA" - the user sees a few pictures, and has to select a word that is appropriate to all the shown pictures. The main problem of this type of CAPTCHAs is misspelling while writing the answer, and synonyms for the answer-word (for example: dog, hound, pooch). In the described case, this is solved by means of transferring all the variants of the answer to the client side.
  • Oli Warner's KittenAuth - in order to prove his humanity, the visitor has to select all animals of a specified species among the proposed pictures. But, the limited number of pictures allows to recreate the picture base manually.
  • Microsoft's Asirra - in outline, it is similar to KittenAuth - the user has to distinguish cats from dogs - but, it works with an extremely large array of pictures (photos of homeless animals from the specialized site), and a reconstruction of the picture base is impossible.
  • IMAGINATION - a CAPTCHA that requires two steps to be passed. At the first step, the visitor clicks elsewhere on the picture that is composed of a few images, and selects a single image. In the second step, the selected image is loaded. It is enlarged, but very distorted. Also, variants of the answer are loaded on the client side. The visitor should select a correct answer from the set of proposed words.

Why are the image-based CAPTCHAs NOT so widespread as the text-based ones?

I will not touch on the contrastive analysis of the possibility to crack them, you can find some thoughts/calculations here and here. I want to express my point of view as a web developer. So, why?
  • They are too large. A CAPTCHA should not take a dominant position on a web page. Is is only an ancillary element that serves to weed out bots under forms filling, getting some information, etc.
  • The traffic. A few pictures, each with a size of about 5-10 KB, would weigh a lot for a single page, in my opinion. Visitors using a low bandwidth network will be unpleasantly impressed, not to mention visitors using dial-up connections.
  • The inconsistency to the general conception of a website. A CAPTCHA with cats (or dolphins) will be appropriate on a leisure site, but will be irrelevant - for example - on a site of a medical institution. In this case, it is possible to gather a number of images of medical subjects, but - on the analogy of Asirra - it would be problematic to find a site with a large amount of photos of homeless doctors :).
  • The laborious process of the picture base creation.

I have to note that it is not a criticism in any way - I only want to find an answer for the above question. Let's sum up the aforesaid. An image-based CAPTCHA might be a good alternative to a text-based one if it would be a single, light-weight image based on a limited set of pictures.

The idea

Look at these two pictures:

It is easy to notice that the right image is slightly distorted, and it is not hard to outline a rough region where the distortion takes place. In order to notice it, the original image is not required. A human easy copes with this task even he sees an image the first time and does not know what the image depicts - the aforesaid does not apply to an expressionist's pictures :).

Now about bots. I have never worked with image recognition systems and my knowledge in this area is rather poor. Perhaps, the proposed variant is intricate to parse by special programs, perhaps not - it will be interesting to hear an expert's opinion.

Demo project (C#, ASP.Net) that illustrates the above conception of the image-based CAPTCHA.

No comments:

Post a Comment