Usually the creator of the algorithm does this by “training” it with photos of faces. The detection phase of facial recognition starts with an algorithm that learns what a face is. This process is used for verification, such as in a security feature on a newer smartphone, or for identification, which attempts to answer the question “Who is in this picture?” And this is where the technology steps into the creepier side of things. Recognition is the attempt to confirm the identity of a person in a photo.Although analysis can suffer from glitches, particularly involving misidentification, that’s generally problematic only when the faceprint is added to a recognition database. Analysis (aka attribution) is the step that maps faces-often by measuring the distance between the eyes, the shape of the chin, the distance between the nose and mouth-and then converts that into a string of numbers or points, often called a “faceprint.” Goofy Instagram or Snapchat filters use similar technology (video).On its own, it isn’t nefarious-face detection only focuses on finding a face, not the identity behind it. If you’ve ever used a camera that detects a face and draws a box around it to auto-focus, you’ve seen this technology in action.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |