More and more frequently, clients (or potential clients) ask me if our semantic search engine is also able to search for images. The first few times, I was surprised and did not understand exactly why they were asking this. Now however, my answer is immediate, and it is: no, it is not able to because images contain little text, therefore making it difficult to apply semantic technology

With time, I have also come to understand that the question is almost spontaneous because people understand the difficulty in semantic text analysis. So, they think that if we have been able to solve this complex problem, then maybe we are also able to take on the problem of image recognition. Unfortunately, the only thing these two problems have in common is their extreme complexity and nothing else.

I find this subject quite intriguing and today, when I read that Google’s Labs had released an instrument to search for images similar to an image selected by the user, I couldn’t resist and immediately tested it out.

The results were interesting, but they demonstrate that ” the  almighty Google” is quite far from having solved this problem. They have employed several clever algorithms (for example, if you search for “French fries” and you select one of the proposed images, a good result is obtained), but it is clear that they are mostly based on predominant colors and on some macro elements (even the text on the page which contains the image seems to be of great influence), without any understanding of what the image actually contains. To prove it, try these examples).

The thing works pretty good with some images, with others, not at all (and often, the results are quite humorous, as in this case and in this one). Seeing as though it’s  free (at least for now :-), if you want to search for images which are similar to one that interests you… then, you can try it out and hope to be lucky.

With the arrival of spring, it seems like even search engines specialized in Q&A are “coming out of hibernation” . These engines give responses to users’ questions (differing from normal search engines which provide a list of web pages in response to a search). First Wolfram Alpha and now, even True Knowledge (in development for many years) are both trying to find their place in the sun.

For the average Internet user, a search engine based on Q&A seems like something magical because, theoretically, one can ask a question and quickly receive a precise response. In reality, however, a system which actually functions in this manner would be impossible. To be able to set up such a service would require difficult and complex problem-solving, which I doubt will ever possible to do (and it really irks me to see that for years, unscrupulous people and companies continue to say just the opposite, disillusioning the user and building up expectations which will never be able to  be satisfied).

What is presently possible is the implementation of a similar search engine which is able to answer, with a good precision rate, a significant number of frequently asked questions which are common to the Web world. It will require an enormous amount of work (and lots of money), top-notch technology (semantic, of course!) and very strong motivation (because of its complex nature and fuzzy problems), but it can be done.

It won’t be a “Google killer”, as many would hope - maybe it won’t even be a competitor- but it will be a great complement for specific fields and explicit needs (those which are common). Developing a system of this kind, which will be useful in everyday applications, requires great investments. In a period such as the present, I don’t know if it can be that easy to find the necessary resources (without substantial investments, there is a great risk that the system will have only a marginal utility because it would be able to respond to only a small fraction of the FAQ).

We’ll just have to wait and see what happens in the next few months: on paper, it looks like it will be an interesting period for these types of services.