Openface - Revision history

Onnowpurbo: /* Overview Workflow */

2018-05-24T23:18:38Z

Overview Workflow

← Older revision		Revision as of 23:18, 24 May 2018
Line 29:		Line 29:
	* Deteksi wajah dengan model pre-trained dari dlib atau OpenCV.		* Deteksi wajah dengan model pre-trained dari dlib atau OpenCV.
	* Transformasikan wajah untuk neural network. OpenFace menggunakan dlib real-time pose estimation dengan OpenCV affine transformation untuk membuat semua mata dan bibir berada pada lokasi yang sama untuk semua gambar.		* Transformasikan wajah untuk neural network. OpenFace menggunakan dlib real-time pose estimation dengan OpenCV affine transformation untuk membuat semua mata dan bibir berada pada lokasi yang sama untuk semua gambar.
	* ~~Use a~~ deep neural network ~~to represent (or embed) the face on a~~ 128-~~dimensional unit~~ hypersphere. ~~The embedding is a generic representation for anybody's face~~. ~~Unlike other face representations~~, ~~this~~ embedding ~~has the nice property that a larger distance between two face embeddings means that the faces are likely not of the same person~~. ~~This property makes~~ clustering, ~~similarity detection~~, ~~and classification tasks easier than other face recognition techniques where the Euclidean distance between features is not meaningful~~.		* Menggunakan deep neural network untuk menggambarkan wajah dalam unit 128-dimensi hypersphere. Embedding ini adalah representasi genetik dari wajah semua orang. Tidak seperti representasi wajah lainnya, embedding mempunyai sifat yang baik sehingga semakin jauh jarak embedding berarti wajah tersebut kemungkinan besar bukan dari orang yang sama. Sifat ini membuat proses clustering, dan juga deteksi, dan tugas klasifikasi menjadi mudah di bandingkan dengan teknik pengenalan wajah lainnya dimana jarak euclidean antar fitur tidak banyak berarti.
	* ~~Apply your favorite~~ clustering ~~or classification techniques to the features to complete your recognition task~~. ~~See below for our examples for classification and similarity detection, including an online web demo~~.		* Terakhir adalah menggunakan berbagai teknik clustering dan classifikasi yang kita sukai untuk menyelesaikan tugas pengenalan wajah.
			* Selesai.

	==Referensi==		==Referensi==

Onnowpurbo: /* Gunakan Dengan Bertanggung Jawab */

2018-05-24T23:13:44Z

Gunakan Dengan Bertanggung Jawab

← Older revision		Revision as of 23:13, 24 May 2018
Line 23:		Line 23:


	Overview		==Overview Workflow==

	~~The following~~ overview ~~shows the~~ workflow ~~for a single input image of Sylvestor Stallone from the publicly available LFW dataset.~~		Berikut ini adalah overview workflow pendeteksian wajah seseorang yang sudah ada di contoh opencv

	* ~~Detect faces with a~~ pre-trained ~~models from~~ dlib or OpenCV.		* Deteksi wajah dengan model pre-trained dari dlib atau OpenCV.
	* ~~Transform the face for the~~ neural network. ~~This repository uses~~ dlib's real-time pose estimation ~~with~~ OpenCV's affine transformation ~~to try to make the eyes and bottom lip appear in the same location on each image~~.		* Transformasikan wajah untuk neural network. OpenFace menggunakan dlib real-time pose estimation dengan OpenCV affine transformation untuk membuat semua mata dan bibir berada pada lokasi yang sama untuk semua gambar.
	* Use a deep neural network to represent (or embed) the face on a 128-dimensional unit hypersphere. The embedding is a generic representation for anybody's face. Unlike other face representations, this embedding has the nice property that a larger distance between two face embeddings means that the faces are likely not of the same person. This property makes clustering, similarity detection, and classification tasks easier than other face recognition techniques where the Euclidean distance between features is not meaningful.		* Use a deep neural network to represent (or embed) the face on a 128-dimensional unit hypersphere. The embedding is a generic representation for anybody's face. Unlike other face representations, this embedding has the nice property that a larger distance between two face embeddings means that the faces are likely not of the same person. This property makes clustering, similarity detection, and classification tasks easier than other face recognition techniques where the Euclidean distance between features is not meaningful.
	* Apply your favorite clustering or classification techniques to the features to complete your recognition task. See below for our examples for classification and similarity detection, including an online web demo.		* Apply your favorite clustering or classification techniques to the features to complete your recognition task. See below for our examples for classification and similarity detection, including an online web demo.


	==Referensi==		==Referensi==

Onnowpurbo at 23:02, 24 May 2018

2018-05-24T23:02:40Z

← Older revision		Revision as of 23:02, 24 May 2018
Line 8:		Line 8:
	Dibuat oleh Brandon Amos, Bartosz Ludwiczuk, dan Mahadev Satyanarayanan.		Dibuat oleh Brandon Amos, Bartosz Ludwiczuk, dan Mahadev Satyanarayanan.

	* Source tersedia di GitHub pada cmusatyalab/openface.		* Open Source, denan source code tersedia di GitHub pada cmusatyalab/openface.
	* Ada dokumentasi API		* Ada dokumentasi API
	* Bergabung pada group cmu-openface atau gitter chat untuk diskusi dan masalah instanasi.		* Bergabung pada group cmu-openface atau gitter chat untuk diskusi dan masalah instanasi.
Line 16:		Line 16:
	==Apakah pengenalan wajah menyelesaikan sebuah masalah?==		==Apakah pengenalan wajah menyelesaikan sebuah masalah?==

	Tidak! Akurasi dari makalah penelitian baru saja mulai melampaui akurasi manusia pada beberapa ~~tolok ukur~~. Keakuratan sistem pengenalan wajah ~~sumber terbuka~~ tertinggal di belakang state-of-the-art. ~~Lihat perbandingan akurasi kami pada tolok ukur LFW~~ yang ~~terkenal~~.		Tidak! Akurasi dari berbagai makalah penelitian tampaknya baru saja mulai melampaui akurasi manusia pada beberapa standard. Keakuratan sistem pengenalan wajah open source memang masih tertinggal di belakang state-of-the-art.

			==Gunakan Dengan Bertanggung Jawab==

			OpenFace tidak mendukung penggunaan aplikasi ini untuk melanggar privacy dan keamanan. Openface digunakan untuk membantuk mereka yang kesulitan dalam pengenalan untuk mengenali dunia sekeliling mereka.

	~~Please use responsibly!~~

	~~We do not support the use of this project in applications that violate privacy and security. We are using this to help cognitively impaired users sense and understand the world around them.~~
	Overview		Overview

	The following overview shows the workflow for a single input image of Sylvestor Stallone from the publicly available LFW dataset.		The following overview shows the workflow for a single input image of Sylvestor Stallone from the publicly available LFW dataset.

	Detect faces with a pre-trained models from dlib or OpenCV.		* Detect faces with a pre-trained models from dlib or OpenCV.
	Transform the face for the neural network. This repository uses dlib's real-time pose estimation with OpenCV's affine transformation to try to make the eyes and bottom lip appear in the same location on each image.		* Transform the face for the neural network. This repository uses dlib's real-time pose estimation with OpenCV's affine transformation to try to make the eyes and bottom lip appear in the same location on each image.
	Use a deep neural network to represent (or embed) the face on a 128-dimensional unit hypersphere. The embedding is a generic representation for anybody's face. Unlike other face representations, this embedding has the nice property that a larger distance between two face embeddings means that the faces are likely not of the same person. This property makes clustering, similarity detection, and classification tasks easier than other face recognition techniques where the Euclidean distance between features is not meaningful.		* Use a deep neural network to represent (or embed) the face on a 128-dimensional unit hypersphere. The embedding is a generic representation for anybody's face. Unlike other face representations, this embedding has the nice property that a larger distance between two face embeddings means that the faces are likely not of the same person. This property makes clustering, similarity detection, and classification tasks easier than other face recognition techniques where the Euclidean distance between features is not meaningful.
	Apply your favorite clustering or classification techniques to the features to complete your recognition task. See below for our examples for classification and similarity detection, including an online web demo.		* Apply your favorite clustering or classification techniques to the features to complete your recognition task. See below for our examples for classification and similarity detection, including an online web demo.

Onnowpurbo at 11:46, 24 May 2018

2018-05-24T11:46:49Z

← Older revision		Revision as of 11:46, 24 May 2018
Line 2:		Line 2:
	* https://github.com/TadasBaltrusaitis/OpenFace/wiki		* https://github.com/TadasBaltrusaitis/OpenFace/wiki
	* https://cmusatyalab.github.io/openface/		* https://cmusatyalab.github.io/openface/
			* https://blog.algorithmia.com/understanding-facial-recognition-openface/

	OpenFace adalah implementasi pengenalan wajah menggunakan Python dan Torch dengan deep neural network dan berdasarkan pada CVPR 2015 paper FaceNet: A Unified Embedding for Face Recognition and Clustering oleh Florian Schroff, Dmitry Kalenichenko, dan James Philbin di Google. Torch memungkinkan jaringan dieksekusi pada CPU atau dengan CUDA.		OpenFace adalah implementasi pengenalan wajah menggunakan Python dan Torch dengan deep neural network dan berdasarkan pada CVPR 2015 paper FaceNet: A Unified Embedding for Face Recognition and Clustering oleh Florian Schroff, Dmitry Kalenichenko, dan James Philbin di Google. Torch memungkinkan jaringan dieksekusi pada CPU atau dengan CUDA.

Onnowpurbo at 10:45, 24 May 2018

2018-05-24T10:45:16Z

← Older revision		Revision as of 10:45, 24 May 2018
Line 12:		Line 12:
	* Bergabung pada group cmu-openface atau gitter chat untuk diskusi dan masalah instanasi.		* Bergabung pada group cmu-openface atau gitter chat untuk diskusi dan masalah instanasi.

	Penelitian ini di dukung oleh National Science Foundation (NSF) ~~under grant number CNS-1518865. Additional support was provided by the~~ Intel ~~Corporation~~, Google, Vodafone, NVIDIA, ~~and the~~ Conklin Kistler family fund~~. Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and should not be attributed to their employers or funding sources~~.		Penelitian ini di dukung oleh National Science Foundation (NSF) dengan dukungan tambahan dari Intel, Google, Vodafone, NVIDIA, dan Conklin Kistler family fund.

	~~Isn't face recognition a solved problem~~?		==Apakah pengenalan wajah menyelesaikan sebuah masalah?==

			Tidak! Akurasi dari makalah penelitian baru saja mulai melampaui akurasi manusia pada beberapa tolok ukur. Keakuratan sistem pengenalan wajah sumber terbuka tertinggal di belakang state-of-the-art. Lihat perbandingan akurasi kami pada tolok ukur LFW yang terkenal.

	No! Accuracies from research papers have just begun to surpass human accuracies on some benchmarks. The accuracies of open source face recognition systems lag behind the state-of-the-art. See our accuracy comparisons on the famous LFW benchmark.
	Please use responsibly!		Please use responsibly!

Onnowpurbo at 10:24, 24 May 2018

2018-05-24T10:24:01Z

@@ Line 1: / Line 1: @@
-Sumber: https://github.com/TadasBaltrusaitis/OpenFace/wiki
+Sumber:
+* https://github.com/TadasBaltrusaitis/OpenFace/wiki
+* https://cmusatyalab.github.io/openface/
-OpenFace 2.0: Facial Behavior Analysis Toolkit Tadas Baltrušaitis, Amir Zadeh, Yao Chong Lim, and Louis-Philippe Morency, IEEE International Conference on Automatic Face and Gesture Recognition, 2018
+OpenFace adalah implementasi pengenalan wajah menggunakan Python dan Torch dengan deep neural network dan berdasarkan pada CVPR 2015 paper FaceNet: A Unified Embedding for Face Recognition and Clustering oleh Florian Schroff, Dmitry Kalenichenko, dan James Philbin di Google. Torch memungkinkan jaringan dieksekusi pada CPU atau dengan CUDA.
-Convolutional experts constrained local model for facial landmark detection A. Zadeh, T. Baltrušaitis, and Louis-Philippe Morency. Computer Vision and Pattern Recognition Workshops, 2017
+Dibuat oleh Brandon Amos, Bartosz Ludwiczuk, dan Mahadev Satyanarayanan.
-Constrained Local Neural Fields for robust facial landmark detection in the wild Tadas Baltrušaitis, Peter Robinson, and Louis-Philippe Morency. in IEEE Int. Conference on Computer Vision Workshops, 300 Faces in-the-Wild Challenge, 2013.
+* Source tersedia di GitHub pada cmusatyalab/openface.
-Eye gaze tracking
+* Ada dokumentasi API
-Rendering of Eyes for Eye-Shape Registration and Gaze Estimation Erroll Wood, Tadas Baltrušaitis, Xucong Zhang, Yusuke Sugano, Peter Robinson, and Andreas Bulling in IEEE International. Conference on Computer Vision (ICCV), 2015
+Penelitian ini di dukung oleh National Science Foundation (NSF) under grant number CNS-1518865. Additional support was provided by the Intel Corporation, Google, Vodafone, NVIDIA, and the Conklin Kistler family fund. Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and should not be attributed to their employers or funding sources.
-Cross-dataset learning and person-specific normalisation for automatic Action Unit detection Tadas Baltrušaitis, Marwa Mahmoud, and Peter Robinson in Facial Expression Recognition and Analysis Challenge, IEEE International Conference on Automatic Face and Gesture Recognition, 2015
+Isn't face recognition a solved problem?
-For inquiries about the commercial licensing of the OpenFace toolkit please visit https://www.flintbox.com/public/project/50632/
+No! Accuracies from research papers have just begun to surpass human accuracies on some benchmarks. The accuracies of open source face recognition systems lag behind the state-of-the-art. See our accuracy comparisons on the famous LFW benchmark.
-Final remarks
+Please use responsibly!
-I did my best to make sure that the code runs out of the box but there are always issues and I would be grateful for your understanding that this is research code and a research project. If you encounter any problems/bugs/issues please contact me on github or by emailing me at tadyla@gmail.com for any bug reports/questions/suggestions. I prefer questions and bug reports on github as that provides visibility to others who might be encountering same issues or who have the same questions.
+We do not support the use of this project in applications that violate privacy and security. We are using this to help cognitively impaired users sense and understand the world around them.
-Copyright
+Overview
-Copyright can be found in the Copyright.txt
+The following overview shows the workflow for a single input image of Sylvestor Stallone from the publicly available LFW dataset.
-You have to respect boost, TBB, dlib, OpenBLAS, and OpenCV licenses.
+    Detect faces with a pre-trained models from dlib or OpenCV.
@@ Line 96: / Line 40: @@
 * https://github.com/TadasBaltrusaitis/OpenFace/wiki

Onnowpurbo: Created page with "Sumber: https://github.com/TadasBaltrusaitis/OpenFace/wiki Over the past few years, there has been an increased interest in automatic facial behavior analysis and understand..."

2018-05-22T00:28:54Z

Created page with "Sumber: https://github.com/TadasBaltrusaitis/OpenFace/wiki Over the past few years, there has been an increased interest in automatic facial behavior analysis and understand..."

New page

Sumber: https://github.com/TadasBaltrusaitis/OpenFace/wiki

Over the past few years, there has been an increased interest in automatic facial behavior analysis and understanding. We present OpenFace – a tool intended for computer vision and machine learning researchers, affective computing community and people interested in building interactive applications based on facial behavior analysis. OpenFace is the ﬁrst toolkit capable of facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation with available source code for both running and training the models. The computer vision algorithms which represent the core of OpenFace demonstrate state-of-the-art results in all of the above mentioned tasks. Furthermore, our tool is capable of real-time performance and is able to run from a simple webcam without any specialist hardware

OpenFace is an implementation of a number of research papers from the Multicomp group, Language Technologies Institute at the Carnegie Mellon University and Rainbow Group, Computer Laboratory, University of Cambridge. The founder of the project and main developer is Tadas Baltrušaitis.

Special thanks goes to Louis-Philippe Morency and his MultiComp Lab at Carnegie Mellon University for help in writing and testing the code, Erroll Wood for the gaze estimation work, and Amir Zadeh and Yao Chong Lim on work on the CE-CLM model.
Functionality

The system is capable of performing a number of facial analysis tasks:

Facial Landmark Detection

Sample facial landmark detection image

Facial Landmark and head pose tracking (links to YouTube videos)

Multiple Face Tracking Multiple Face Tracking

Facial Action Unit Recognition

Gaze tracking (image of it in action)

Facial Feature Extraction (aligned faces and HOG features)

Sample aligned face and HOG image
Installation

Windows

Ubuntu

Mac

Docker image Somewhat outdated version, but easy to use as no installation needed
Use

Command line interface

GUI for Windows

Messaging server (Coming soon)
Citation

If you use any of the resources provided on this page in any of your publications we ask you to cite the following work and the work for a relevant submodule you used.
Overall system

OpenFace 2.0: Facial Behavior Analysis Toolkit Tadas Baltrušaitis, Amir Zadeh, Yao Chong Lim, and Louis-Philippe Morency, IEEE International Conference on Automatic Face and Gesture Recognition, 2018
Facial landmark detection and tracking

Convolutional experts constrained local model for facial landmark detection A. Zadeh, T. Baltrušaitis, and Louis-Philippe Morency. Computer Vision and Pattern Recognition Workshops, 2017

Constrained Local Neural Fields for robust facial landmark detection in the wild Tadas Baltrušaitis, Peter Robinson, and Louis-Philippe Morency. in IEEE Int. Conference on Computer Vision Workshops, 300 Faces in-the-Wild Challenge, 2013.
Eye gaze tracking

Rendering of Eyes for Eye-Shape Registration and Gaze Estimation Erroll Wood, Tadas Baltrušaitis, Xucong Zhang, Yusuke Sugano, Peter Robinson, and Andreas Bulling in IEEE International. Conference on Computer Vision (ICCV), 2015
Facial Action Unit detection

Cross-dataset learning and person-specific normalisation for automatic Action Unit detection Tadas Baltrušaitis, Marwa Mahmoud, and Peter Robinson in Facial Expression Recognition and Analysis Challenge, IEEE International Conference on Automatic Face and Gesture Recognition, 2015
Commercial license

For inquiries about the commercial licensing of the OpenFace toolkit please visit https://www.flintbox.com/public/project/50632/
Final remarks

I did my best to make sure that the code runs out of the box but there are always issues and I would be grateful for your understanding that this is research code and a research project. If you encounter any problems/bugs/issues please contact me on github or by emailing me at tadyla@gmail.com for any bug reports/questions/suggestions. I prefer questions and bug reports on github as that provides visibility to others who might be encountering same issues or who have the same questions.
Copyright

Copyright can be found in the Copyright.txt

You have to respect boost, TBB, dlib, OpenBLAS, and OpenCV licenses.

Furthermore you have to respect the licenses of the datasets used for model training - https://github.com/TadasBaltrusaitis/OpenFace/wiki/Datasets

© 2018 GitHub, Inc.
Terms
Privacy
Security
Status
Help

Contact GitHub
API
Training
Shop
Blog
About

Press h to open a hovercard with more details.

==Referensi==

* https://github.com/TadasBaltrusaitis/OpenFace/wiki