Organizing photos and tagging them with keywords isn’t a new concept, but the Roll uses EyeEm’s Vision technology to automate everything. Keywords, from seasons to what’s in the photos, are automatically added to each photo, making the entire camera roll easily searchable. The technology is similar in concept to what Google has employed in Google Photos, to help users organize and better locate the large amounts of photos.
But arguably the most interesting feature from the app is the programing that rates each photo. The platform will recognize similar photos and group them together – putting the “best” photo on top. The rating system is also used to suggest what photos to keep and share.
So how can a computer decide what a “good” photograph is, when “good” is largely subjective?
Appu Shaji, head of research and development at EyeEm, says he believes two factors contribute to the success of a photograph: the story behind it and the way that story is told.
“While it’s difficult for a computer to answer a philosophical question (although it might be interesting to hear what they would say), we can attempt to transfer the details of a human mental process to a computer, and ask the computer to recreate it,” Shaji wrote.
To create the program, EyeEm developers worked closely with researchers and photo curators, selecting “good” photos to train the software to recognize them. Rather than sticking only with technical concepts, like exposure and the Rule of Thirds, the group also looked for images that had strong stories.
With the information, the team at EyeEm developed an algorithm to help identify strong images automatically.
“Of course, technology can never replace your personal taste and judgments,” Shajj said. “But we sincerely believe that we are entering a fascinating stage in which technology can power curation, enabling human stories to be discovered within the firehose of photographic data–starting with your very own camera roll.”
The Roll is available for iOS only, but is currently free in the App Store.