Google develops Neural Image Assessment to measure beauty and emotion in images

An image is worth a thousand words. Images tell stories that naturally appeal to humans. For instance, you may click multiple image of your pet and choose the one in which it’s striking a pose rather than one which has no blurs or noise. We don’t always choose images for their technical clarity and there are many times we prefer one image over the other because of its artistic appeal.
 
Well, what if an AI could predict which images you find attractive based on aesthetics rather than technicality?    
 
Google has developed a deep convolutional neural network in the form of NIMA - Neural Image Assessment, to better rate images as per their appeal to users. NIMA can predict which images users would find attractive and appealing, and then score them on a scale of 1-10 with high correlation to human perception.
 
Detailing NIMA in a blog post, Google wrote,” While technical quality assessment deals with measuring pixel-level degradations such as noise, blur, compression artifacts, etc., aesthetic assessment captures semantic level characteristics associated with emotions and beauty in images.”
 
So rather than typically classifying images as low or high quality based on technical factors, NIMA uses deep learning techniques to rate images based on their aesthetic appeal to humans.
 
According to Google NIMA will be useful for intelligent photo editing, optimising visual quality for increased user engagement, or minimizing perceived visual errors in an imaging pipeline. NIMA can also be useful for developing new storage or media sharing techniques. You can see how NIMA has been used to create better aesthetics in images, a great example of how NIMA scores can be used to enhance images.

---