How to Perform Face Recognition With VGGFace2 in Keras

Jason Brownlee has a fantastic tutorial showing how you can use computer vision to recognize faces.

Face recognition tutorial using keras, Mask CNN and VGGFace2 in python
Channing Tatum, Courtesy of wikipedia, used in the face recognition demo using keras and Masked-CNN with VGGFace2

This is much more difficult than face detection, since you need to detect a face and recognize it for this task.

Recently, deep learning convolutional neural networks have surpassed classical methods and are achieving state-of-the-art results on standard face recognition datasets. One example of a state-of-the-art model is the VGGFace and VGGFace2 model developed by researchers at the Visual Geometry Group at Oxford.

Dr Brownlee is a world recognized author on all things AI and ML.

His tutorial is composed of six steps:

Face Recognition
VGGFace and VGGFace2 Models
How to Install the keras-vggface Library
How to Detect Faces for Face Recognition
How to Perform Face Identification With VGGFace2
How to Perform Face Verification With VGGFace2

In order to follow this tutorial, you’ll need to have python installed (3.7 or higher), and install a few packages:

pip install git+
pip show keras-vggface
pip install mtcnn

To follow the tutorial, navigate to Jason’s walkthrough.

Other excellent topics you may enjoy include yolov3 keras, sagemaker airflow, elastic inference accelerator, watson discovery pricing and the amazon comprehend example.

Leave a comment if you’d like any more specialized content.

Be First to Comment

    Leave a Reply

    Your email address will not be published. Required fields are marked *