Google has released a new paper that they presented at the recent Computer Vision and Pattern Recognition (CVPR) conference in Miami, FL. Called “Tour the World: building a web-scale landmark recognition engine”, it’s about a new tool they’ve built for image pattern matching to identify images of landmarks.
Our research builds on the vast number of images on the web the ability to search those images and advances in object recognition and clustering techniques. First we generated a list of landmarks relying on two sources 40 million GPS-tagged photos from Picasa and Panoramio and online tour guide webpages. Next we found candidate images for each landmark using these sources and Google Image Search which we then “pruned” using efficient image matching and unsupervised clustering techniques. Finally we developed a highly efficient indexing system for fast image recognition.
They’re adamant that this is not a new google product, just some research, but it’s not hard to imagine this being rolled into something like Picasa in the near future.