Ez-face

JustinRatliff

USA
robot video thumbnail

EZ-Face is the first in what I plan to develop into a suite of supporting application for ARC and other robotics applications. EZ-Face performs multiple face recognition. It has a interface for training faces and assigning names. When the application sees faces that are recognized the names are displayed and visually you'll see boxes around the faces with the names assigned. If a face is detected but not recognized there will be a display of a box around the face with no name. The more pictures of a face you train, the easier it is for the application to recognize a face.

User-inserted image

This is a stand alone application developed in C# under Visual Studio.NET 2013. You should have .NET framework 4.5 and it is for Windows7 and Windows8.x systems.

This project showcase explains the technology behind the application and highlights development milestones.

Technology: Developed in .NET Visual Studio 2013 (you can use express versions with the source code) Designed to work with ARC but could be integrated into other software or robotic systems Is a standalone application Is open source, source code is included Uses emgu cv wrapper for .NET (Open CV)

Resources: (Things I found helpful in creating the application) ARC Telnet interface tutorial (Enable Telnet as the first part Shows, this is used to test communications manually to ARC via TCP/IP): https://synthiam.com/Tutorials/Help.aspx?id=159 If you do not have Telnet installed on your system go to this site: http://technet.microsoft.com/en-us/library/cc771275 ARC SDK Tutorial 52: https://synthiam.com/Community/Questions/4952&page=1 ARC script for listening to the TCP/IP port for variables: https://synthiam.com/Community/Questions/5255

Acknowledgements: DJ Sures, for making EZ-Robot and ARC so robust Rich, for his help with ARC scripting Sergio, for his emgu cv examples

Basic Usage Direction (after download and install): 1.) Open ARC and load the included EZ-Face example 2.) Click on the Script start button (this sets up the communications from the ARC side of things) 3.) Open the EZ-Face application 4.) Refresh your camera list (click the button) 5.) Select your camera (in the drop down list) 6.) Click the "1. Detect and recognize" button 7.) Train at least one face 8.) Change the local address and port number as needed (the local IP address may not be your computer's address - you can enter "localhost" and leave the port set to 6666 unless you changed that setting in ARC) 9.) Click File and select Save User Settings (to store your changes) 10.) Click Connection (this opens the communication line to ARC from the EZ-Face app side 11.) Allow EZ-Face to recognize the face you trained - then with your computer speakers turned on ARC should speak "Hello (the name of the face you trained)" 12.) If the example work - integrate in your EZ-Robot applications as you see fit

Tips: 1.) If after training several faces if you get false recognition of faces (faces recognized with the wrong name) - to correct this you should train the incorrectly recognized faces with the correct name. After a couple of training pictures are stored the accuracy of the face recognition will improve. 2.) Do not train faces with one camera, then switch to another camera for face recognition - recognition accuracy will drop.

Using Two Cameras: What I found worked best was to start ARC, select the camera I wanted and started the camera feed, then I started EZ-Face. If I reverses the process (even though I was selecting a different camera) I would get a black image in ARC.

2.26.14 Update: I still have several improvements I want to make before I upload the first public version of the application.

3.2.14 Update: The first public version is ready for release and is posted at the link below. This version has many user improvements to allow you store many settings, including http and port address, camera device, logging of faces in a text file (up to 1mb of data before the file auto deletes), face variable output to ARC, face training and more.

3.3.14 Update: I updated the script, version 3.3.14 has the HTTP server panel (which is not used - you don't need to start it) but it does show you your computer's IP address so you can enter it in EZ-Face. Remember to save your settings under the File Menu. I also changed the script so it will no only speak for variable values greater than "" or NULL.
EZ-Face3.3.14.EZB

3.7.14 Update: I updated the EZ-Face application: "localhost" is now the default address, new option for auto connect, functions to receive commands from ARC or other 3rd party application to stop and start the camera feed within EZ-Face. There is also a new ARC project with several new scripts to test out the functions. Please go to my site to download the latest version. You will also find a video there that demonstrations the new functions and provides directions for setup and usages.

Download: The latest version will be published here: http://www.j2rscientific.com/software For support and reporting any errors please use the ContactUs feature from http://www.j2rscientific.com with the subject line "EZ-Face".

I welcome any and all feedback!
Thank you

By — Last update

ARC Pro

Upgrade to ARC Pro

Get access to the latest features and updates before they're released. You'll have everything that's needed to unleash your robot's potential!

#17  

I just had a good laugh at my EZ-Face app. I had already trained it with DJ Sures face, so I was going to add the actor Steve Guttenburg from Short Circuit and EZ-Face didn't miss a beat to detect Dr. Newton Crosby PH.D. as DJ Sures! :D :)

I'm finding that the functionality maxes out for me at 4-5 faces for solid reliability. After that, the face trained the most (mine) starts to look like other people, where it detect Isaac Asimov as me at first, then it registers him correctly. All though I have not tried just capturing tons of images of every face, so that could effect the learning as well. I (we'll) learn more as we play it. I know it really had a tough time understand the Isaac Asimov at different ages (young vs old). So if you time travel or your robot does not see someone for a long time that might be important to know. :)

I know for sure teaching faces based only on a picture of a picture, like I did for DJ Sures and Asimov, that it will work, but not's not great method.

I'm looking forward to sharing this in a couple of days.

#18  

Incredible! Sarah Connor just might get terminated after all.

#19  

This is one of the most exciting user projects I have heard about in quite a while. I am anticipating playing with it with baited breath. Also really excited you are open sourcing it. I am trying to find the time to learn C#, and theway I learned VB6 was by examining other peoples apps that did similar things to what I wanted to do. I found that much more effective than tutorials or books that started with "Hello World" and then went through dozens of simple apps that I wasn't interested in.

Brazil
#20  

Amazing! When do you plan to release the download so we can test ? I just can't wait! Thank you!

#21  

I cant agree more @ thetechguru ! With " a higher resolution? " for the face variable more faces may be recognized!

#22  

@thetechguru Playing around with other code is one of the best ways to learn coding. Something else that makes coding easier to learn is a good way to manage code snippets so it's easier to use them. Once I started using the free Snippet Manager I have not looked back. You can create searchable code archives for anything. Even ARC scripts! http://www.snippetmanager.net/

Back in the day I learned BASIC on the Commadore 64. Then I went to Quick BASIC for IBM systems. Then pbasic for micro controllers. Then Visual Basic.Net and once I learned that I thought I'd never, ever learn C#. But over time I've turned into one of those c# is better than VB snobs.

@tevans My goal is to release it by 3/3/14

PRO
Synthiam
#23  

Wow that's great:) It's also flattering you used my face in the detector with alan turing! I'm excited to try your project out!

#24  

It's here!:D:D:):D:D

Download: The latest version will be published here: http://www.j2rscientific.com/software For support and reporting any errors please use the ContactUs feature from http://www.j2rscientific.com with the subject line "EZ-Face".

3.2.14 Update: The first public version is ready for release and is posted at the link above. This version has many user improvements to allow you store many settings, including http and port address, camera device, logging of faces in a text file (up to 1mb of data before the file auto deletes), face variable output to ARC, face training and more.

Please use my site for support questions so I can track issues. Also I don't want to be a pest by being a forum hog.

Thank you!