It is Necessary to Look into the Eyes to Understand Made-up Images 1
0 0
0 0
Read Time:1 Minute, 36 Second

In almost every period of human history, some kind of forgery exists. Today, however, deep fakes and fake landscapes that look realistic is featured. It’s getting harder and harder to distinguish these invalid images. Scientists, on the other hand, have a recommendation for understanding false images.

Thanks to the formula developed by scientists, we can see the faces we look at. knowing whether it is fake or real might be possible. To understand the difference between the landscapes created by artificial intelligence and real humans, the eyes are the place to look.

The truth is hidden in the eyes:

It is Necessary to Look into the Eyes to Understand Made-up Images 2

researcher at the State University of New York Hui Guo’s according to his work, the secret to understanding invalid images lies in the eyes, especially in the case of irises. To understand the difference, all we have to do is zoom in on the images.

When we get closer to the landscape before us structure of pupil and iris helps to understand whether the image is real or not. While real irises and pupils are round, artificial intelligence images become distorted.

In research group articles “Irises are almost round in shape in healthy adults. Compared to real faces, GAN-made images we observed visible marks and inconsistencies in the eye area..

It is possible to distinguish invalid sights:

It is Necessary to Look into the Eyes to Understand Made-up Images 3

To test this theory, scientists used the sights in the images. separating them according to eye forms uploaded 1000 real and 1000 fake face photos to the system after developing a software. Evaluating eye conditions, the program succeeded in separating the images in a solid form by only looking at this criterion.

According to the researchers, one day, thanks to this study, false images can be used to take precautions to prevent it from being used as if it were real. It is believed that these measures will be very useful, especially on platforms that are open to manipulation, such as social media.

Happy
Happy
0 %
Sad
Sad
0 %
Excited
Excited
0 %
Sleepy
Sleepy
0 %
Angry
Angry
0 %
Surprise
Surprise
0 %

Average Rating

5 Star
0%
4 Star
0%
3 Star
0%
2 Star
0%
1 Star
0%

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.