The project is a comprehensive study on the state-of-the-art deep learning models for face recognition, specifically focusing on the FaceNet model. It utilises triplet loss function introduced in FaceNet paper to transfer learn two CNNs that are based on the architecture of ResNet50 and InceptionNet. The objective of the project is to implement the FaceNet paper model using Python and TensorFlow, utilizing the LFW (Labeled Faces in the Wild) dataset, which comprises over 13,000 images of over 5,000 individuals.
- Network Used: ResNet50 and InceptionNet
- Original Paper: FaceNet, ResNet, InceptionNet
- FaceNet: A Unified Embedding for Face Recognition and Clustering by Florian Schroff, Dmitry Kalenichenko and James Philbin
- Deep Residual Learning for Image Recognition by Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun
- Going deeper with convolutions by Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke and Andrew Rabinovich