Ayonix has embedded its 3D Face recognition technology into Axis IP camera(Camera model: Axis P1367).
Axis camera has ARM9 with 512MB ram. ARM9 is the most frequently used CPU for cameras and embedded devices. ARM is highly chosen for embedded platform because of its fast architecture as well as low power consumption. However, we should say that ARM 9 32bit processor is not so suitable to run a technology which needs heavy computation like 3D Face recognition. Ayonix R&D team worked hard to integrate Face recognition into the IP camera for long time. Camera resources are very limited, there is no GPU, CPU is 32bit single core. Therefore, Multi core 64bit Face recognition technology had to be redesigned from scratch. Redesigning engine for 32bit CPU limits Face recognition precision and increase FAR(False Acceptance rate) and FRR(False Rejection Rate)
Right now, camera does Face detection, Face tracker, Gender and Age analysis, Face expression, Face feature extraction, 3D face reconstruction and face matching. These run in 30fps in real world conditions. Accuracy is exactly the same as Windows environment.
This camera is the FIRST in the world. Some vendors put the face detection and tracking to the camera but there is no full Face recognition. It is computed outside the camera in a server machine. First time in the world, Ayonix achieved to run entire face recognition inside the camera without speed and performance loss.
Camera will help Face recognition to spread all over the world by reducing hardware costs significantly. Camera is available for system integrators, software companies as well as customers. By using this camera, our customers can connect 1000 cameras to single server to do face recognition. For more information about camera, you can read here