Mihaela Grigore
  • 👋About
  • 👩‍🏭Personal projects
    • Computer Vision | Deep Learning with Tensorflow & Keras (ResNet50, GPU training)
    • Computer Vision | Convolutional Neural Networks with PyTorch
    • Computer Vision | Facial Recognition with Keras, FaceNet, Inception, Siamese Networks
    • NLP | Topic modeling on tweets
    • NLP | Sentiment analysis of tweets: TextBlob, VADER and Flair
    • Time series | Exploration on Crypto price dataset
    • Data scraping | Social Media Scraping: Twitter Developer API for Academics
    • Data Scraping | Collecting historical tweets without Twitter API
  • ✍️Notes
    • Machine Learning in Production
      • Feature transforms
      • Feature selection
      • Data journey
    • NLP
      • Information Retrieval
    • Computer Vision
    • Time series
      • Stationarity
    • Data
      • Labeling
    • Python
      • ndarray slicing with index out of bounds
  • 📚Readings & other media
    • Computer Vision
      • Selection of research articles
    • NLP
      • Handwriting Text
      • Information Retrieval
      • Mono- / multilingual
      • Topic Modeling
      • Language Models
    • Time Series
    • Generative Adversarial Netoworks (GAN)
    • Python
      • Python basics
Powered by GitBook
On this page
  1. Personal projects

Computer Vision | Facial Recognition with Keras, FaceNet, Inception, Siamese Networks

PreviousComputer Vision | Convolutional Neural Networks with PyTorchNextNLP | Topic modeling on tweets

Last updated 3 years ago

See

This repo contains one notebook, where I use Keras and customize a pretrained Inception model which I then use for building a Siamese Network that performs face recognition.

Facial recognition is the task of looking at an image showing the face of a person and being able to identify that person from a collectiong of images already present in our database.

- the system has a database of n persons (images for each of them, most often just 1)
- the system receives as input a new, unseen, image of a person
- and should be able to recognize if this is any of the n persons already present in the database.

To build such a system, I'm using:

- Siamese Networks
- the Triplet loss function, described in the FaceNet article by Schroff et al 2015
- Transfer learning, to save training time by making use of pretrained convolutional neural networks.
- Keras interface for the TensorFlow library and Keras Applications pretrained models.

How to use this repo: Open the Jupyter Notebook in this folder. You can clone it, download it or just read it here. There is also a link at the top of the Notebook which takes you to the same Notebook on Kaggle.

👩‍🏭
project repository on GitHub.