Google introduces machine learning technique to create pro-level photos from Google Street View images

Taking digital photography to the next level, Google has introduced a new machine learning-based technique to create pro-level landscape photos from 'Google Street View' images. The technique is based on "experimental deep-learning system" which uses machine learning for artistic content creation, according to Google research blog.

Using 'Google Street View', several landscape panoramas were taken and then, post-processing operations were carried out to create an aesthetically pleasing image.

The research approach relied on a collection of professional quality photos of which the subjective aesthetics were broken down into multiple aspects automatically, each of which is learned individually by the machine.

Google used 40,000 panoramas from areas like the Alps, Banff and Jasper National Parks in Canada, Big Sur in California and Yellowstone National Park to conduct the "Turing-test" like experiment, which was then judged by professional photographers.

The team mixed the machine creations with other photos and about 40 percent of them were rated at "semi-pro" to "pro" levels by the judges.

Google recently acquired  Benguluru-based artificial intelligence (AI) firm Halli Labs that will help in building solutions for adding new users to the Internet in developing countries like India. The price of the deal was not disclosed by the company. A Google spokesperson said: “We are excited that the Halli Labs team is joining Google. They will be joining our team that is focused on building products that are designed for the next billion users coming online, particularly in India”.

With inputs from IANS