Facebook IDs Faces Almost As Well As We Can
While the future of mankind is unknowable, illustrator Nickolay Lamm (NickolayLamm.com) has produced a set of imaginative evolutionary changes to the human face over the next 100,000 years. This far future look was inspired by conversations Lamm had with Dr. Alan Kwan, an expert in computational genomics from Washington University, St Louis, Missouri. Kwan bases his speculation on phylogenomics, which determines the evolutionary relationships of life forms by comparing large datasets of gene sequences. Here are four possible facial configurations that humans may evolve through over the next hundred millennia. First off, we begin with a "normal" male and female of today.
20,000 A.D. -- Humans have a larger head and forehead that is subtly too large. The yellow ring around the eyes represents a communications lens -- the "Google Glass" of the future. The contact lenses relay hi-resolution visual information on an array of bioluminescent biobots (bacteria-based robots) and gives humans a removable and toggleable heads-up display and video communications. Hair is finer but grows denser because its role of containing heat loss from the enlarged head remains unchanged.
60,000 A.D. -- Head size increases to accommodate a larger brain. Pigmented skin is engineered to better deal with effects of radiation among space colonies. The genetic construction of thicker eyelids and more pronounced arch alleviates the effects of low or zero-gravity that has been found to disrupt and disorient the eyesight of today’s astronauts. Wearable technology continues but remains in subtle forms and limited permanence. Miniature bone-conduction devices implanted above the ear now work with the communications lenses.
100,000 A.D. -– Facial engineering is now heavily biased towards features that we find fundamentally appealing: strong, regal lines, straight nose, intense eyes, and placement of facial features that adhere to the golden ratio and left/right perfect symmetry. By today’s standards the eyes are now unnervingly large (but awfully big “windows to the soul”). Genetically boosted layer of cells behind the retina (the tapetum lucidum) enhance night vision and gives humans a cat-like glowing “green eye” look.
Facebook could soon have a facial recognition feature that’s just short of our own abilities. The social network’s researchers have created DeepFace, an algorithm that can identify faces almost as well as humans can.
Built by Yaniv Taigman and colleagues at Facebook’s artificial intelligence lab, DeepFace improves on most facial recognition systems’ major flaw: if faces in the photos are off-center, the software struggles to pinpoint a match.
Taigman’s team designed a 3-D model of a face from a photo that can be rotated into the ideal position for the algorithm to find a match. Then, a simulated neural network computes a numerical description of the repositioned face. If DeepFace finds enough similarities between two photos, it detects a match.
“This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers,” researchers explained. “Thus, we trained it on the largest facial dataset to date, an identity- labeled dataset of four million facial images belonging to more than 4,000 identities, where each identity has an average of over a thousand samples.”
The researchers achieved a 97.25 percent accuracy rate for positive matches. That falls just shy of the 97.5 percent accuracy rate humans are capable of achieving. However, DeepFace remains solely a research project. Researchers will present their work at the IEEE Conference on Computer Vision and Pattern Recognition in June.
Credit: Facebook, DeepFace