Typical image based face feature extractors

This repository contains a few of typical algorithms to extacting face image features.

texture-based

ORB [python], SIFT [python], SURF [python], Image Gradient [MatLab], LBP [MatLab], LPQ [MatLab], HOG [MatLab], BISF [MatLab], DFT [python], FFT [python].

deep learning based

These models are based on Keras, made available alongside pre-trained weights. These models can be used for prediction, feature extraction, and fine-tuning by modifing.

• [VGG16, VGG19]: Very Deep Convolutional Networks for Large-Scale Image Recognition (ICLR 2015).
• [Xception]: Xception: Deep Learning with Depthwise Separable Convolutions (CVPR 2017).
• [ResNet50, ResNet101, ResNet152]: Deep Residual Learning for Image Recognition (CVPR 2015).
• [NasNetMobile]:Learning Transferable Architectures for Scalable Image Recognition (CVPR 2018) .
• [MobileNet] : MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
• [MobileNetV2] : MobileNetV2: Inverted Residuals and Linear Bottlenecks (CVPR 2018).
• [InceptionV3] : Rethinking the Inception Architecture for Computer Vision (CVPR 2016).
• [InceptionResNetV2]:Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (AAAI 2017) .
• [EfficientNet] : EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (ICML 2019) .
• [DenseNet121, DenseNet169, DenseNet201]: Densely Connected Convolutional Networks (CVPR 2017).

image quality based

FIQA_NSS [MatLab], Steganalysis [MatLab], IQM [python].