There are 0 repository under lfw topic.
Real-Time Semantic Segmentation in Mobile device
center loss for face recognition
Deep Face Recognition in PyTorch
Official repository for MixFaceNets: Extremely Efficient Face Recognition Networks
face analysis project with tensorflow 2.0 || arcface
Face Recognition in real-world images [ICASSP 2017]
Demo of Face Recognition web service
Neural networks for facial recognition using Keras and the LFW Face Database.
A PyTorch Implementation of ShuffleFaceNet.
Some handy scripts for processing face datasets
This repo contains auto encoders and decoders using keras and tensor flow. It shows the exact encoding and decoding with the code part.
This project uses the Labeled Faces in the Wild (LFW) dataset, and the goal is to train variants of deep architectures to learn when a pair of images of faces is the same person or not. It is a pytorch implementation of Siamese network with 19 layers.
Low-Resolution Face Recognition Based on Identity-Preserved Face Hallucination (2019, ICIP)
work in Advanced Topics in Multimedia Analysis and Indexing
This is the Python version of evaluation.m for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17
128D Facenet Embedding Visualisation
Introduction of how to use LFW database according to its protocols
Multi-metric-learning-discriminative-for-face-verification-SPDML-with-Labled-FACE-In Wild-(LFW ) dataset-YFT
Face Recognition using FaceNet
Face Recognition with convolutional neural network (CNN) on Labeled Faces in the Wild (LFW) dataset
Train/validate VGGface2 dataset based on L2-constrained softmax loss.
Deep Siamese network for low-resolution face recognition (2021, APSIPA ASC)
Pytorch implementation of "A Better Autoencoder for Image: Convolutional Autoencoder" by Yifei Zhang
An image recognition process contained in the LFW database http://vis-www.cs.umass.edu/lfw/#download is carried out with extreme simplicity, taking advantage of the ease of sklearn to implement the SVM model. Cascading face recognition is also used to refine the images, obtaining accuracy greater than 70% in the test with images that do not appear in the training.
A coolection of tools for organizing directories, specifically converting the Labeled Faces of the Wild (cropped) to a common standard.