Google turned AI into an art critic

Google introduced the Neural Image Assessment (NIMA) system, which uses a neural network to evaluate photos, but   not   only their   technical specifications, but   and   aesthetic beauty.

How it works

Artificial Intelligence in   Google was trained on   photos that experts have already appreciated. Experts assessed   general view of the image, and   put up points for   each specific criterion. The system has analyzed photo ratings   - and   externally passed the exam   art history.

What are the successes

FROM   Using special algorithms, NIMA estimated more than 2,000 real images. Experts also looked at the images and   evaluated them   by   scale from   1 to   10 points. AT   resulting in ratings of AI   more than   80% converged with   opinion of critics.

Where useful

AT   Google says that NIMA will be useful in   applications for working with   photos. For example, she can quickly sort images by selecting the best. Also, the system is useful when editing a photo: the neural network will be able to adjust the parameters of exposure, brightness, contrast, saturation , etc.

Source: The Verge