This Google robot is a good photographer!

This image is one of the hundreds of million captured by Google Street View. A soft-robot picked it (along several others) and improved its rendering and framing to make it worth of a professional landscape photographer. Credit: Google

There are several “advices” on photographic forum on how to take a better photo and how to make a photo even better in post-processing. Yet, in the end, you look at several photos and you pick up one as the best one and it is difficult to put in words “why” it is really the best (at least for you). There is a lot a subjective judgement in classifying the beauty of a photo.

Google researchers have developed a (soft) robot and taught it to recognise good photos among the hundreds of million photos taken by StreetView and to post process them to make they look like professional photos. The results are (at least to me) quite impressive.

Although it is clear that the robot applies, in making its selection, some generally accepted criteria like the rule of thirds, focus on the foreground, presence of a line guiding the eye from the front of the image to the far distance, one has to admit that the choices made and the way the photo has been post processed goes beyond technicalities. Indeed, the robot used an aesthetic filter trained by AI deep learning algorithms.

To test the result of the work performed by the robot the Google team submitted in a blind test the photos produced by the robot mixed with several others taken by a variety of photographer and submitted them to professional photographers evaluation. The result indicates that 40% of the photos produced by the robot are ranked in the semi-pro to pro quality, quite impressive!

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.