This project is based on Siamese Neural Networks & Triplet Loss Functions
1. DeepFace: Closing the Gap to Human-Level Performance in Face Verification
2. FaceNet: A Unified Embedding for Face Recognition and Clustering
Standard deep learning classification required huge amount of dataset to predict with good accuracy. So, we have used the data used in the given research papers to implement the model. For every new image the image is added to our model without retraining our model. This way of learning is called One-shot learning.
- Numpy
- Pandas
- OpenCV
- Tensorflow
- Keras
- H5py
- Matplotlib