How to recognition only one face?
doanbh opened this issue · comments
Good job and good project. Can you help me how to recognition only face?
I don't want to recognition many people at once.
Currently, the performance is not very good. I want to ask if it is possible to capture image from camera and send to server
and recognition on Python Server to ease the app. On the web I used SocketIO to do this. Do not know with Flutter can do this?
@doanbh For just single face, use map instead of multimap.
Face-Recognition-Flutter/lib/main.dart
Line 93 in 5ab50ad
@doanbh As far as the performance is concerned, sending real-time images to server would make it slower and inference time of mobile face net model is quite low. The actual lag is due to the processes before it.
@Rajatkalsotra Many thank you for your help. In your opinion, it seems that using the face net model handled under the app is better than sending it to the server. But it cannot detect face anti-spoofing. Do you have any way?
@doanbh You're welcome. For anti-spoofing you can perform liveness detection by training your classification model and then convert it into tflite.
Can you tell me more specifically what should I do? I'm having a problem, if the user uses a photo for facial recognition, it's also being accepted.
@doanbh Train a simple classfication model (real /fake image) and convert it into tflite. Refer the following link:
https://www.pyimagesearch.com/2019/03/11/liveness-detection-with-opencv/
@doanbh For just single face, use map instead of multimap.
Face-Recognition-Flutter/lib/main.dart
Line 93 in 5ab50ad
Many thank, but I use Map, it's not working. I want to identify only one person at a time. Let me know how?