Engadget: Microsoft is getting its own AI-powered photo search. “Microsoft’s upcoming Photos app is getting AI image search so that it can spot and classify objects, much like Google Photos and Apple Photos can. Spotted by Windows Central, the latest Insider Preview version of the app now has a search bar that you can use to enter terms like ‘flower,’ ‘wine bottle,’ and ‘bar.’ It will then use a cloud-based image recognition algorithm to pick and sort out those items in your photo collection, much as the rival apps do.”
Phys.org: Colorizing images with deep neural networks . “For decades, image colorization has enjoyed an enduring interest from the public. Though not without its share of detractors, there is something powerful about this simple act of adding color to black and white imagery, whether it be a way of bridging memories between the generations, or expressing artistic creativity. However, the process of manually adding color can be very time consuming and require expertise, with typical professional processes taking hours or days per image to perfect. A team of researchers has proposed a new technique to leverage deep networks and AI, which allows novices, even those with limited artistic ability, to quickly produce reasonable results.”
New-to-Me: Beijing Silvermine. “Beijing Silvermine is an archive of half a million negatives salvaged over the last seven years from a recycling plant on the edge of Beijing. Assembled by the French collector and artist Thomas Sauvin, Beijing Silvermine offers a unique photographic portrait of the Chinese capital and the life of its inhabitants in the decade following the Cultural Revolution.”
Lifehacker: How to Tell if a Photo Has Been Doctored. “Nearly every photo online has been edited in some way, whether through cropping, filtering, compressing, color-correcting, or other generally innocuous touch-ups. But a lot of people attempt to pass off doctored images as true ones, leading to hoaxes, crackpot theories, and more than one trip to Snopes for some fact-checking. You can do the world a service by helping those around you identify real photos against fake ones. Here’s how…” This is beginner level, but a useful start. Some of the comments are interesting.
Digital Trends: Snap A Photo, Get A Recipe: Pic2recipe Uses A.I. To Predict Food Ingredients. “Scrolling through food photography can bring on the desire to recreate a dish at home, but what if the ingredients aren’t listed? Could there be a way to find out just by analyzing the image? That’s what researchers at the Massachusetts Institute of Technology asked when they set out to create a deep learning algorithm that could predict a recipe based just on a photo. The research, published on July 20, resulted in a program called Pic2Recipe that could accurately predict a dish’s recipe based on a photo, with a 65 percent success rate.”
New York Public Library: Surveyor Geotagging Tool Puts NYPL Photos on the Map. “Today, we’re proud to release Surveyor, our new website for crowdsourced geotagging of NYPL’s photo collections. With Surveyor, we invite everyone who is interested in the history of New York City to try and determine the locations depicted in these mostly unlabelled photos. With your help, we will create a database containing the geographic locations of our photos, and this data will be available for everyone to use and download. We’ll start small, with around 2,500 photos from five collections, but we will add more of the Library’s photo collections later (you can find a list of these collections on Surveyor’s About page).”
SUNY Polytechnic Institute: SUNY Poly Receives Grant to Archive Refugee Projects. “SUNY Polytechnic Institute (SUNY Poly) today announced that stories told by Central New York refugee community members and recorded by SUNY Poly faculty and staff will now be preserved and archived for access by communities across the state and the nation thanks to a grant from the New York State Regional Bibliographic Database Grant program.”