Most facial recognition algorithms you find on the internet and research papers suffer from photo attacks. These methods work really well at detecting and recognizing faces on images, videos and video streams from webcam. However they can’t distinguish between real life faces and faces on a photo. This inability to recognize faces is due to the fact that these algorithms work on 2D frames.
So Idea used here is Eye Blinking of person
1-- Used keras model for preediction of face imp-- pip install dlib,face_recognition,numpy,os.......(check in file)
SO the the program runs as follows: 1--Detect faces in each frame generated by the webcam.
2--For each detected face, detect eyes.
3--For each detected eyes, detect if eyes are open or closed.
4--If at some point it was detected that the eyes were open then closed then open, we conclude the person has blinked and the program displays its name (in the case of a facial recognition door opener, we would authorize the person to enter).
LENET KERAS MODEL: LeNet-5 layers: Convolution #1. Input = 32x32x1. Output = 28x28x6 conv2d SubSampling #1. Input = 28x28x6. Output = 14x14x6. SubSampling is simply Average Pooling so we use avg_pool Convolution #2. Input = 14x14x6. Output = 10x10x16 conv2d SubSampling #2. Input = 10x10x16. Output = 5x5x16 avg_pool Fully Connected #1. Input = 5x5x16. Output = 120 Fully Connected #2. Input = 120. Output = 84 output 10