You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
Currently, the facial recognition library only verifies the identity of a person but does not provide any means to distinguish between a live person and a spoof (such as a photograph or a video). This poses a security risk in applications requiring robust authentication mechanisms.
Describe the solution you'd like
Integrate a liveliness detection feature into the facial recognition library. This feature should be able to distinguish between live persons and spoof attacks (e.g., photos, videos, masks) by analyzing facial movements, skin texture, and other biometric indicators. Ideally, the solution should work in real-time and be compatible with existing functionality of the library.
Additional context
Liveliness detection is becoming a standard requirement in many facial recognition applications, such as mobile banking, secure access control, and identity verification systems. Implementing this feature will enhance the security and reliability of the library, making it more competitive and suitable for a broader range of applications.
The text was updated successfully, but these errors were encountered:
As an expertise in machine CNN and OpenCv I can contribute and resolve your issue . we had made same app for attendance system with accuracy of 85 % so please assign this issue to me
Is your feature request related to a problem? Please describe.
Currently, the facial recognition library only verifies the identity of a person but does not provide any means to distinguish between a live person and a spoof (such as a photograph or a video). This poses a security risk in applications requiring robust authentication mechanisms.
Describe the solution you'd like
Integrate a liveliness detection feature into the facial recognition library. This feature should be able to distinguish between live persons and spoof attacks (e.g., photos, videos, masks) by analyzing facial movements, skin texture, and other biometric indicators. Ideally, the solution should work in real-time and be compatible with existing functionality of the library.
Additional context
Liveliness detection is becoming a standard requirement in many facial recognition applications, such as mobile banking, secure access control, and identity verification systems. Implementing this feature will enhance the security and reliability of the library, making it more competitive and suitable for a broader range of applications.
The text was updated successfully, but these errors were encountered: