AVmod is a Audiovisual modulator developed with Deep Fake
Built and deployed a real-time facial-recognition attendance system that automated employee check-in/check-out and achieved 97% accuracy.
AVmod is a Audiovisual modulator developed with Deep Fake
My Project contains 8,664 photos featuring 100 distinct actors, Utilizing cosine similarity calculations, the model effectively identifies and retrieves the most akin images that bear resemblance to the inputted facial features, enabling precise face matching capabilities. I have used keras-vgg_face to efficiently extract the features of face.
To associate your repository with the keras-vggface topic, visit your repo's landing page and select "manage topics."