Developed in Python using Tensorflow framework, built a pipeline consisting of image preprocessing steps, detecting and extracting faces using FaceBoxes model, creating embeddings using FaceNet model, making it ready for particular tasks like facial recognition, verification, automatic person tagging.
- Python - version > 3.7
- TensorFlow - version 2.4.0
- Scikit-Learn - version 0.22.1
- Numpy - version 1.19.5
- Open-CV - version 4.5.1
To run the code in local, first download the the pretrainded weights for FaceBoxes from here and FaceNet weights from here and place it in the Pretrainded-Models.
- Facial Recognition using Tensorflow.
- FaceBoxes-TensorFlow
- Florian Schroff, Dmitry Kalenichenko, James Philbin, FaceNet: A Unified Embedding for Face Recognition and Clustering, 2015.
- Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li, FaceBoxes: A CPU Real-time Face Detector with High Accuracy, 2018.