Face detection using deep learning.

Overview

Face Detection Docker Solution Using Faster R-CNN



Dockerface is a deep learning face detector. It deploys a trained Faster R-CNN network on Caffe through an easy to use docker image. Bring your videos and images, run dockerface and obtain videos and images with bounding boxes of face detections and an easy to use face detection annotation text file.

The docker image is large for now because OpenCV has to be compiled and stored in the image to be able to use video and it takes up a lot of space.

Technical details and some experiments are described in the Arxiv Tech Report.

Citing Dockerface

If you find Dockerface useful in your research please consider citing:

@ARTICLE{2017arXiv170804370R,
   author = {{Ruiz}, N. and {Rehg}, J.~M.},
    title = "{Dockerface: an easy to install and use Faster R-CNN face detector in a Docker container}",
  journal = {ArXiv e-prints},
archivePrefix = "arXiv",
   eprint = {1708.04370},
 primaryClass = "cs.CV",
 keywords = {Computer Science - Computer Vision and Pattern Recognition},
     year = 2017,
    month = aug,
   adsurl = {http://adsabs.harvard.edu/abs/2017arXiv170804370R},
  adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}

Instructions

Install NVIDIA CUDA (8 - preferably) and cuDNN (v5 - preferably)

https://developer.nvidia.com/cuda-downloads
https://developer.nvidia.com/cudnn

Install docker

https://docs.docker.com/engine/installation/

Install nvidia-docker

wget -P /tmp https://github.com/NVIDIA/nvidia-docker/releases/download/v1.0.1/nvidia-docker_1.0.1-1_amd64.deb
sudo dpkg -i /tmp/nvidia-docker*.deb && rm /tmp/nvidia-docker*.deb

Go to your working folder and create a directory called data, your videos and images should go here. Also create a folder called output.

cd $WORKING_DIR
mkdir data
mkdir output

Run the docker container

sudo nvidia-docker run -it -v $PWD/data:/opt/py-faster-rcnn/edata -v $PWD/output/video:/opt/py-faster-rcnn/output/video -v $PWD/output/images:/opt/py-faster-rcnn/output/images natanielruiz/dockerface:latest

Now we have to recompile Caffe for it to work on your own machine.

cd caffe-fast-rcnn
rm -rf build
mkdir build
cd build
cmake -DUSE_CUDNN=1 ..
make -j20 && make pycaffe
cd ../..

Finally use this command to process a video

python tools/run_face_detection_on_video.py --gpu 0 --video edata/YOUR_VIDEO_FILENAME --output_string STRING_TO_BE_APPENDED_TO_OUTPUTFILE_NAME --conf_thresh CONFIDENCE_THRESHOLD_FOR_DETECTIONS

Use this command to process an image

python tools/run_face_detection_on_image.py --gpu 0 --image edata/YOUR_IMAGE_FILENAME --output_string STRING_TO_BE_APPENDED_TO_OUTPUTFILE_NAME --conf_thresh CONFIDENCE_THRESHOLD_FOR_DETECTIONS

Also if you are looking to conveniently process all images in one folder use this command

python tools/facedetection_images.py --gpu 0 --image_folder edata/IMAGE_FOLDER_NAME --output_folder OUTPUT_FOLDER_PATH --conf_thresh CONFIDENCE_THRESHOLD_FOR_DETECTIONS

The default confidence threshold is 0.85 which works for high quality videos or images where the faces are clearly visible. You can play around with this value.

The columns contained in the output text files are:

For videos:

frame_number x_min y_min x_max y_max confidence_score

For images:

image_path x_min y_min x_max y_max confidence_score

Where (x_min,y_min) denote the coordinates of the upper-left corner of the bounding box in image intrinsic coordinates and (x_max, y_max) denote the coordinates of the lower-right corner of the bounding box in image intrinsic coordinates. (ref. https://www.mathworks.com/help/images/image-coordinate-systems.html) confidence_score denotes the probability output of the model that the detection is correct (it is a number included in [0,1])

Voila, that easy!

After you're done with the docker container you can exit.

exit

You want to restart and re-attach to this same docker container so as to avoid compiling Caffe again. To do this first get the id for that container.

sudo docker ps -a

It should be the last one that was launched. Take note of CONTAINER ID. Then start and attach to that container.

sudo docker start CONTAINER_ID
sudo docker attach CONTAINER_ID

You can now continue processing videos.

Nataniel Ruiz and James M. Rehg
Georgia Institute of Technology

Credits: Original dockerface logo made by Freepik from Flaticon is licensed by Creative Commons BY 3.0, modified by Nataniel Ruiz.

Owner
Nataniel Ruiz
PhD candidate at Boston University doing Computer Vision and ML. M.S. from Georgia Tech, BA/M.S. from Ecole Polytechnique
Nataniel Ruiz
dataset for ECCV 2020 "Motion Capture from Internet Videos"

Motion Capture from Internet Videos Motion Capture from Internet Videos Junting Dong*, Qing Shuai*, Yuanqing Zhang, Xian Liu, Xiaowei Zhou, Hujun Bao

ZJU3DV 98 Dec 07, 2022
A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

This repository contains the similarity metrics designed and evaluated in the paper, and instructions and code to re-run the experiments. Implementation in the deep-learning framework PyTorch

Steffen 86 Dec 27, 2022
Dynamical movement primitives (DMPs), probabilistic movement primitives (ProMPs), spatially coupled bimanual DMPs.

Movement Primitives Movement primitives are a common group of policy representations in robotics. There are many different types and variations. This

DFKI Robotics Innovation Center 63 Jan 06, 2023
Image-to-Image Translation with Conditional Adversarial Networks (Pix2pix) implementation in keras

pix2pix-keras Pix2pix implementation in keras. Original paper: Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) Paper Author

William Falcon 141 Dec 30, 2022
NPBG++: Accelerating Neural Point-Based Graphics

[CVPR 2022] NPBG++: Accelerating Neural Point-Based Graphics Project Page | Paper This repository contains the official Python implementation of the p

Ruslan Rakhimov 57 Dec 03, 2022
HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement

HiFi++ : a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement This is the unofficial implementation of Vocoder part of

Rishikesh (ऋषिकेश) 118 Dec 29, 2022
Parsing, analyzing, and comparing source code across many languages

Semantic semantic is a Haskell library and command line tool for parsing, analyzing, and comparing source code. In a hurry? Check out our documentatio

GitHub 8.6k Dec 28, 2022
A toolkit for developing and comparing reinforcement learning algorithms.

Status: Maintenance (expect bug fixes and minor updates) OpenAI Gym OpenAI Gym is a toolkit for developing and comparing reinforcement learning algori

OpenAI 29.6k Jan 08, 2023
Algo-burn - Script to configure an Algorand address as a "burn" address for one or more ASA tokens

Algorand Burn Address This is a simple script to illustrate how a "burn address"

GSD 5 May 10, 2022
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

The official code for the NeurIPS 2021 paper Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

13 Dec 22, 2022
UPSNet: A Unified Panoptic Segmentation Network

UPSNet: A Unified Panoptic Segmentation Network Introduction UPSNet is initially described in a CVPR 2019 oral paper. Disclaimer This repository is te

Uber Research 622 Dec 26, 2022
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-local Spatial-Temporal Similarity

This repository is the official PyTorch implementation of Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-local Spatial-Temporal Similarity

hippopmonkey 4 Dec 11, 2022
Fast Differentiable Matrix Sqrt Root

Fast Differentiable Matrix Sqrt Root Geometric Interpretation of Matrix Square Root and Inverse Square Root This repository constains the official Pyt

YueSong 42 Dec 30, 2022
Open CV - Convert a picture to look like a cartoon sketch in python

Use the video https://www.youtube.com/watch?v=k7cVPGpnels for initial learning.

Sammith S Bharadwaj 3 Jan 29, 2022
Collection of generative models in Pytorch version.

pytorch-generative-model-collections Original : [Tensorflow version] Pytorch implementation of various GANs. This repository was re-implemented with r

Hyeonwoo Kang 2.4k Dec 31, 2022
PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time

PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time The implementation is based on SIGGRAPH Aisa'20. Dependencies Python 3.7 Ubuntu

soratobtai 124 Dec 08, 2022
Patient-Survival - Using Python, I developed a Machine Learning model using classification techniques such as Random Forest and SVM classifiers to predict a patient's survival status that have undergone breast cancer surgery.

Patient-Survival - Using Python, I developed a Machine Learning model using classification techniques such as Random Forest and SVM classifiers to predict a patient's survival status that have underg

Nafis Ahmed 1 Dec 28, 2021
Sign Language is detected in realtime using video sequences. Our approach involves MediaPipe Holistic for keypoints extraction and LSTM Model for prediction.

RealTime Sign Language Detection using Action Recognition Approach Real-Time Sign Language is commonly predicted using models whose architecture consi

Rishikesh S 15 Aug 20, 2022
Codes for paper "Towards Diverse Paragraph Captioning for Untrimmed Videos". CVPR 2021

Towards Diverse Paragraph Captioning for Untrimmed Videos This repository contains PyTorch implementation of our paper Towards Diverse Paragraph Capti

Yuqing Song 61 Oct 11, 2022
Hitters Linear Regression - Hitters Linear Regression With Python

Hitters_Linear_Regression Kullanacağımız veri seti Carnegie Mellon Üniversitesi'

AyseBuyukcelik 2 Jan 26, 2022