3Face recognition

Face become the most attractive biometric and face recognition systems for personal identification are increasingly used in a wide range of applications. Development of recognition algorithms and methods made possible usage of identification and verification systems in commercial field. However these systems do not achieve comparable recognition rates under uncontrolled and unconstrained conditions. Face recognition under these conditions is still a challenging problem in spite of recent advances in well-constrained face recognition.

Biometric systems for personal identification, which are developed by several vendors, achieve very high face recognition accuracy. The most of these applications require [3]:

  • recognition systems which can recognize several faces from one video frame or one image
  • high recognition rate
  • illumination invariance
  • stability under changing of face expressions and pose
  • recognition in real time, etc.

So we can see there is several factors which can affect performance and accuracy of system for face recognition [1]: