We all have our own taste when it comes to the art of photography and imagery – and that’s where artificial intelligence (AI) comes into play. Google is currently utilising convolution neural networks in an attempt to enable artificial intelligence to recognise photos that appear engaging from the perspective of a human’s eyes.
Google’s blog post reports that, “Our proposed network can be used to not only score images reliably and with high correlation to human perception, but also it is useful for a variety of labor intensive and subjective tasks such as intelligent photo editing, optimizing visual quality for increased user engagement, or minimizing perceived visual errors in an imaging pipeline.”
With artificial intelligence in this case, the company’s aim is to allow users to find the highest quality images that they would personally rate as good-looking. As well as this, they also want to improve the way users take pictures by giving real-time feedback. The technology is trained on a collection of data that works around images which human users have already rated. Following up, the artificial intelligence involved then intends to replicate the average rating in accordance with what humans have rated when it comes to judging photos.
At the moment, this new technology is not available on any Google products as of yet, but the research team boasted the result that they have managed to obtain from their work. Artificial intelligence is an area that tech companies are putting a lot of effort into lately. Software firm Adobe rolled out updates to Lightroom to help users edit photos with artificial intelligence so that the finished product looks aesthetically likeable.
Do you think artificial intelligence will help the human race?
Source: | Google |
Via: | UberGizmo |
Images: | Google |