There are roughly three components of healthy internet browsing; a healthy connection, a healthy website and a healthy device. Many security measures are taken to ensure that a site can function properly and cannot be attacked or damaged by malicious parties. Perhaps one of the most famous Captcha testing.

Lately we have been constantly in Captcha tests. to recognize pedestrian crossings, traffic lights or vehicles we are working. So why are we constantly struggling with traffic like we’re in a driving school when there are thousands of different questions to ask?

Computers try to decipher the traffic thanks to us.

What we call the captcha test is a simple test used to distinguish between humans and computers. Turing test. The Turing test is a kind of test that is easy for humans but cannot be solved by the computer. The reason why we often see images related to traffic in captcha tests is that these images are difficult for computers to recognize.

Computers don’t perceive images the way we do. At the tests traffic lights, pedestrian crossings, bicycles, buses computers cannot recognize objects as soon as they see them. The shape, color, location and background of these objects can be complicated for computers.

While it may seem easy to say that a traffic light is green, the brightness, angle of the light, and other objects around it can cause the computer to stumble. That’s why when people are asked to separate these images, computers or software cannot access the Sites.

How do computers learn to distinguish things?

Thanks to artificial intelligence, computers can take things away from other things. to divorce can learn. Although the learning processes are clear, we do not yet know exactly how the head of artificial intelligence works. After learning, there is a complex artificial network.

First of all, we have one bot or artificial intelligence Unless we do, the information we can obtain is limited because artificial intelligence and bots are highly valuable and closely guarded trade secrets for businesses. They give no details other than very general information. Still, the general approach is more or less clear.

Let’s take a look at the neural network systems that have been popular in recent years.

especially popular in recent years. neural network systems Basically, two bots are produced. The first of these bots produces new bots and the second tests new bots. To explain the rest of the article without confusion, I’ll call them producer bots, trainer bots, and student bots.

manufacturer boots, The student produces bots and sends them to the trainer bot. The trainer doesn’t know what distinction we want the bot to make, but he has a quiz with answered questions in his hand. Student applies this test to bots. It sends the students back to the manufacturer with the test results.

When the kids come out of school, the productive boat, good results areas set aside and destroy others; Instead, another student builds bots based on successful examples. The process of creating and testing new bots continues as a while loop.

While the students who were lucky at first survived, the more or less desired job at a certain point was no longer a coincidence. a boat that can do it thanks to its structure arises. In subsequent iterations of that bot, the success rate needed to survive gets higher and higher.

Finally too Although we don’t know exactly how it works we get a successfully working artificial intelligence bot. We humans create the answer keys for the tests with millions of questions that will be applied to the billions of bots that will take these tests with the Captcha tests.

Computers, of course, have places to use what they learn.

Information from captcha tests, in the first phase Google Maps used to develop services like Google tries to keep its maps more accurate and up-to-date by matching the traffic-related images it uses in its Captcha tests with people’s responses. Similar, Captcha testing It is used both to ensure the security of websites and to improve map services.

Another point is, of course, autonomous driving systems. for the development of these systems. huge amount of data needs. One of the most effective ways to collect such big data is to already create control data by asking billions of people who surf the internet about images.

So in the end people struggle with so many traffic symbols to train bots in Captcha tests. So, in the future, by following more accurate maps, our self-driving cars will be.