Make higher accuracy for Face Verification model

[ThongNguyen551]

Hi anyone, I am new and I am doing a real-time face recognition based on FaceNet. I already run the videostream for tracking and detection but don't know how to increase the accuracy. Particularly, when I downloaded the code and followed the guideline from this link https://github.com/richmondu/facenet/tree/master/usage, I run the real_time_face_recognition.py and the camera verified me as Rico which is the name in dataset. I still did not train my own dataset.

• Anyone please tell me is this model using k-NN model to calculate the L2 distance?
• If yes, please guide me where and how I can modify the code to be more accuracy? Thanks very much

[fybaft2012]

Hey ThongNguyen551, Have you found the solution about using pre-trained face embedding in real face recognition task? Actually, I tried use the same way posted at https://www.pyimagesearch.com/2018/06/18/face-recognition-with-opencv-python-and-deep-learning/ (k-nearest neighbor) and https://www.pyimagesearch.com/2018/09/24/opencv-face-recognition/ (linear SVM classifier)

First of which used KNN clustering method, and second used the linear SVM classifier. However both of them gave the poor performance with my own pre-trained face embedding model instead of dilb face embedding model.