Automatically align face images πŸ™ƒβ†’πŸ™‚. Can also do windowing and warping.

Overview

Automatic Face Alignment (AFA)

Carl M. Gaspar & Oliver G.B. Garrod

You have lots of photos of faces like this:

But you want to line up all of the faces like this:

Perhaps you would also like to window the faces to show only inner facial features like this:

All of the above can be done using AFA like this:

import alignfaces as afa

faces_path = "/Users/Me/faces_for_my_study/"
afa.get_landmarks(faces_path)
aligned_path = afa.align_procrustes(faces_path)
afa.get_landmarks(aligned_path)
the_aperture, aperture_path = afa.place_aperture(aligned_path)

To better understand how to write a script for your specific purposes, we direct you to demo 1. Demo 1 also describes how AFA alignment works.

All of these functions depend on reliable detection of facial landmarks, which is provided by the DLIB library. Alignment is based on generalized Procrustes analysis (GPA), which extensively unit tested.

Additional functions (warping)

Automatic landmark detection means that it is also easy to separate shape and texture in order to produce various kinds of warped images.

AFA provides functions for two types of face-warping manipulations common in face perception research.

Morphing between faces

To learn how to do this please see demo 2.

Enhanced average of facial identity

To learn how to do this please see demo 3.

Setup

It is highly recommended that you have conda installed, preferably miniconda rather than full fat anaconda.

If you do have conda, then do the following to install:

=3.9" scikit-image conda activate myenv pip install "alignfaces @ git+https://[email protected]/SourCherries/auto-face-align.git" ">
conda create --name myenv conda-forge::dlib "python>=3.9" scikit-image

conda activate myenv

pip install "alignfaces @ git+https://[email protected]/SourCherries/auto-face-align.git"

This will create a new virtual environment called myenv. You can use another name for that. You'll need to activate this environment using conda activate myenv whenever you want to use AFA. To deactivate, simply type conda deactivate myenv.

Windows users may encounter a problem with plotting. That is a general issue with Matplotlib on Windows. To fix, simply type the following while your myenv is activated:

conda install freetype=2.10.4

How well does this work?

In addition to unit-testing critical computations, I evaluated both landmark estimation (DLIB) and the outcome of the entire alignment procedure using various face databases. The results are described here.

Citation

If you use this package for your research, please cite the following preprint:

Gaspar, C. M., & Garrod, O. G. B. (2021, November 8). A Python toolbox for Automatic Face Alignment (AFA). Retrieved from psyarxiv.com/erc8a

DOI:

10.31234/osf.io/erc8a

License

This module is under an Apache-2.0 license.

Owner
Carl Michael Gaspar
Scientist focussed on human visual perception and neuroscience.
Carl Michael Gaspar
NuPIC Studio is an allΒ­-in-Β­one tool that allows users create a HTM neural network from scratch

NuPIC Studio is an allΒ­-in-Β­one tool that allows users create a HTM neural network from scratch, train it, collect statistics, and share it among the members of the community. It is not just a visual

HTM Community 93 Sep 30, 2022
DA2Lite is an automated model compression toolkit for PyTorch.

DA2Lite (Deep Architecture to Lite) is a toolkit to compress and accelerate deep network models. ⭐ Star us on GitHub β€” it helps!! Frameworks & Librari

Sinhan Kang 7 Mar 22, 2022
Code & Data for Enhancing Photorealism Enhancement

Code & Data for Enhancing Photorealism Enhancement

Intel ISL (Intel Intelligent Systems Lab) 1.1k Jan 08, 2023
a pytorch implementation of auto-punctuation learned character by character

Learning Auto-Punctuation by Reading Engadget Articles Link to Other of my work 🌟 Deep Learning Notes: A collection of my notes going from basic mult

Ge Yang 137 Nov 09, 2022
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein

Hannes StΓ€rk 355 Jan 03, 2023
LQM - Improving Object Detection by Estimating Bounding Box Quality Accurately

Improving Object Detection by Estimating Bounding Box Quality Accurately Abstract Object detection aims to locate and classify object instances in ima

IM Lab., POSTECH 0 Sep 28, 2022
Torch implementation of SegNet and deconvolutional network

Torch implementation of SegNet and deconvolutional network

Fedor Chervinskii 5 Jul 17, 2020
Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation

GPT2-Pytorch with Text-Generator Better Language Models and Their Implications Our model, called GPT-2 (a successor to GPT), was trained simply to pre

Tae-Hwan Jung 775 Jan 08, 2023
Prototypical python implementation of the trust-region algorithm presented in Sequential Linearization Method for Bound-Constrained Mathematical Programs with Complementarity Constraints by Larson, Leyffer, Kirches, and Manns.

Prototypical python implementation of the trust-region algorithm presented in Sequential Linearization Method for Bound-Constrained Mathematical Programs with Complementarity Constraints by Larson, L

3 Dec 02, 2022
Based on the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral

Geometry-aware Instance-reweighted Adversarial Training This repository provides codes for Geometry-aware Instance-reweighted Adversarial Training (ht

Jingfeng 47 Dec 22, 2022
Awesome Weak-Shot Learning

Awesome Weak-Shot Learning In weak-shot learning, all categories are split into non-overlapped base categories and novel categories, in which base cat

BCMI 162 Dec 30, 2022
This is a yolo3 implemented via tensorflow 2.7

YoloV3 - an object detection algorithm implemented via TF 2.x source code In this article I assume you've already familiar with basic computer vision

2 Jan 17, 2022
Experiment about Deep Person Re-identification with EfficientNet-v2

We evaluated the baseline with Resnet50 and Efficienet-v2 without using pretrained models. Also Resnet50-IBN-A and Efficientnet-v2 using pretrained on ImageNet. We used two datasets: Market-1501 and

lan.nguyen2k 77 Jan 03, 2023
How to Train a GAN? Tips and tricks to make GANs work

(this list is no longer maintained, and I am not sure how relevant it is in 2020) How to Train a GAN? Tips and tricks to make GANs work While research

Soumith Chintala 10.8k Dec 31, 2022
Training BERT with Compute/Time (Academic) Budget

Training BERT with Compute/Time (Academic) Budget This repository contains scripts for pre-training and finetuning BERT-like models with limited time

Intel Labs 263 Jan 07, 2023
This repo provides a demo for the CVPR 2021 paper "A Fourier-based Framework for Domain Generalization" on the PACS dataset.

FACT This repo provides a demo for the CVPR 2021 paper "A Fourier-based Framework for Domain Generalization" on the PACS dataset. To cite, please use:

105 Dec 17, 2022
Instance Semantic Segmentation List

Instance Semantic Segmentation List This repository contains lists of state-or-art instance semantic segmentation works. Papers and resources are list

bighead 87 Mar 06, 2022
This codebase proposes modular light python and pytorch implementations of several LiDAR Odometry methods

pyLiDAR-SLAM This codebase proposes modular light python and pytorch implementations of several LiDAR Odometry methods, which can easily be evaluated

Kitware, Inc. 208 Dec 16, 2022
Implementation of Squeezenet in pytorch, pretrained models on Cifar 10 data to come

Pytorch Squeeznet Pytorch implementation of Squeezenet model as described in https://arxiv.org/abs/1602.07360 on cifar-10 Data. The definition of Sque

gaurav pathak 86 Oct 28, 2022