AI identifies individual photographers by analysing huge trove of WWII photos

An AI has been developed using a trove of historical photos from WW2 that is able to recognise the identity of photographers based on the content of photos taken by them.

 Researchers from both Aarhus and Tampere University used AI to trawl through photographs taken by 23 well-known Finnish photographers during the Second World War.

The photographs used in the study are part of the publicly available Finnish Wartime Photograph Archive containing around 160,000 photographs from Finnish Winter, Continuation, and Lapland Wars captured in 1939-1945.

They wanted their AI to be able to automatically detect people and objects in a variety of scenes and even photographers on the basis of characteristics in the image much faster than a manual reviewing process.

The EU’s Accessibility Directive, which came into effect in September, requires textual descriptions of image contents to be added to all public images on the Web.

It is hoped the automatic analysis could serve as a tool for providing content-based textual descriptions of public photographic archives as is now required.

“We were quite surprised by the accuracy with which the AI can recognise photographers based on characteristics in the photos, such as content and framing,” said Alexandros Iosifidis, associate professor at Aarhus University.

The photographs analysed in the study show that some photographers have very distinct and easily recognisable characteristics, while others are more difficult for the AI to recognise.

On average, the AI model achieved a classification accuracy of around 41 per cent depending on the photographer.

The most recognisable photographer was Heikki Roivainen, a Finnish professor of botany who worked as an official war photographer during the Continuation War; the second of two wars fought between Finland and the Soviet Union during WW2.

“Big data analysis of the contents of photograph collections has been a long-time dream for me and I am very fascinated about the results in this project. That an AI can recognize the framing and various aspects of contents in photographs has many applications in a wide range of fields within humanities and social sciences,” Tampere University’s Anssi Männistö said.

AI also provides the opportunity to link photo archives of this kind to war-related research in social sciences, as it can make observations that would otherwise not be possible at a large-scale.