Method of facial recognition

摘要

An original image of a target is provided. The original image is guidedly perturbed into a first plurality of recognizable uniquely perturbed images, each of the first plurality of recognizable uniquely perturbed images being recognizable as representing the target and distinguishable from the original image. The first plurality of recognizable uniquely perturbed images is guidedly perturbed into a second plurality of unrecognizable uniquely perturbed images, each of the second plurality of unrecognizable uniquely perturbed images being unrecognizable as representing the target. A contour is generated between the first plurality of recognizable uniquely perturbed images and the second plurality of unrecognizable uniquely perturbed images.