Algorithms Are Learning to ID Pixelated Faces

The new tech can identify faces or numbers even if they’ve been blurred out. Most Popular Getty Yagi Studio Sep 13, 2016 Blurring or pixelating information to obscure it may not work anymore thanks to machine learning researchers from the University of Texas at Austin and Cornell University. The researchers developed an algorithm that could identify faces and numbers even after they were blurred out. The researchers developed the algorithm using open-source machine-learning software. Said co-author Vitaly Shmatikov to Quartz: “We’re using this off-the-shelf, poor man’s approach. Just take a bunch of training data, throw some neural networks on it, throw standard image recognition algorithms on it, and even with this approach…we can obtain pretty good results.” Advertisement – Continue Reading Below The algorithm is built using a very simple…


Link to Full Article: Algorithms Are Learning to ID Pixelated Faces