Active Appearance Modeling is an apparently helpful technology developed to help robots identify individual human beings. Let's take a closer look at how this works.
It's hard enough just to get computers to identify faces, let alone individual faces. However, now even cameras know how to identify faces (OKAO Vision Lets Machines See You Smile).
The next problem is to identify a face regardless of how it is presented to the camera (front and side). The video shown below gives you an idea of how computer brains can do it.
(Active Appearance Modeling video)
The basic idea is to identify specific landmarks on a person's face, like the eyes, eyebrows, mouth, nose and so on. Then, a mesh can be created by connecting these landmarks. Finally, the computer is able to create a three-dimensional mesh model of an individual face.
Carnegie Mellon University researchers are pushing this idea even further. Their active appearance modeling software can identify faces that are partially occluded by objects.
CMU is even working on advanced algorithms to fit AAMs to low resolution images, like those created by cheap webcams, or in poor lighting conditions where digital cameras cannot record a clear image.
Technovelgy (that's tech-novel-gee!)
is devoted to the creative science inventions and ideas of sf authors. Look for
the Invention Category that interests
you, the Glossary, the Invention
Timeline, or see what's New.
A System To Defeat AI Face Recognition
'...points and patches of light... sliding all over their faces in a programmed manner that had been designed to foil facial recognition systems.'