NeoFace Facial Recognition

 
Neoface 1
Neoface 2
Neoface 3
Neoface

NeoFace uses a technology called ‘Adaptive Region Mixed Matching’, which focuses on segment regions with a high degree of similarity for matching.

Other makers' products make judgments based on a number of combined characteristics, such as the distance between the eyes and the nose, or the nose and the mouth. But this creates a problem, because if even one of these segments is missing, the accuracy drops dramatically.

In contrast, NeoFace divides the input image and the registered image into small segments, and focuses only on the segments that are highly similar. This enables the system to achieve higher authentication accuracy than our competitors' products, even if a part of the subject's face is hidden, for example by a mask or glasses.


NeoFace applications at a glance:

  • web based access
  • real-time CCTV monitoring and alerting
  • mobile/PDA applications
  • compact, remote and intelligent devices
  • office automation and reception applications
  • access control and integration
  • educational solutions.

Used around the world for immigration and border control.
Documents & Downloads

Compared with other biometrics systems such as fingerprint, palmprint and iris, face recognition has distinct advantages because of its non-contact process. They include:

  • face images can be captured from a distance without touching the person the person identified
  • indentification requires zero interaction
  • serves as a crime deterrent
  • images can be archived and used at a later date to identify an individual.

NEC's face recognition technology can be implemented as a functionally independent application or seamlessly integrated into new or existing biometrics security solutions. Features of NeoFace include:

  • 1:1 verification
  • 1:n identification
  • GLVQ based multiple matching face detection
  • recognition based on neural network technology
  • head, face and eye position detection
  • image resolutions up to 2,147, 483,647 x 2,147, 483,647 pixels
  • recognition regardless of vantage point and facial changes (glass, facial hair or expression)
  • extraction of similar facial areas
  • flexible integration into many types of video monitoring systems
  • supports diverse graphic and video formats as well as live cameras
  • matching speed of up to 1,000,000 faces per second
  • infrared camera support.

Contact us about this solution

Contact Us