Avenger Face Detection

Source Code

Learn about the project in GitHub

Video

Here are the project presentation and the recognition performance in stream.

Description

This project is dedicated to recognizing faces of five Avengers, either individually or in a group image. We have implemented four methods:

1. VGG feature vector extractor coupled with a linear neural network classifier.
2. A finely-tuned VGG16 model. (Transfer Learning)
3. A finely-tuned ResNet model. (Transfer Learning)
4. A finely-tuned Inception-ResNet-V1 model. (Transfer Learning)

The standout performer is our fourth method, achieving an impressive 99.7% accuracy for individual Avenger recognition and 90% in scenarios involving all five Avengers.