Deploying DeadLetter Learning DeadCL DeadCL Tutorials DeadCL Syntax DeadCL MBS

Walk throughs

Author Keys Conversations Libraries Arrays

  Network Status Community Hub Contact Us



Facial ID
(Basic)

View tutorials overview

Introduction

By the time you've completed this tutorial you'll have successfully created a facial identification tool using DeadCL, an Apache server and that's about it.

Everything shown in blue must be substituted with your own values.

You can skip these steps using our Digital Ocean one click droplet here.

Prerequisites

- A sudo user and firewall on your server: in this example we're using Ubuntu 18.04LTS
- Apache Web Server: DeadLetter requires a web server of some description.
- Sub domain: this tutorial requires your web server to be configured with the sub-domain dld.yourdomain.com

Step One

Our first step is to SSH into your server, and navigate to where you'd like to place your Author Key.

            

sudo [email protected]0.0.0.0 sudo mkdir /var/www/html/dld/

Step Two

Next you'll need to copy our Author Key template.

            

cd /var/www/html/dld/ sudo curl -o AK.txt https://keys.deadletter.io/YOURDOMAIN.COM=dld=MY-AK.txt

Step Three

Jump into Nano (or your preferred text editor) and replace the filler content.

            

nano AK.txt


The Author Key should look something like this, be sure to set a URL for at least one Conversation file, this will be needed later on.
            

@Do-ID:NAME_YOURNAME $* [email protected]{YOUR-AUTHOR-KEY-NAME} trusted_Cnvrstn//@CON_FILE [email protected] ?bnd -- @_all @ = dld.domain.com domain.com =DOMAIN ?DRP -- [email protected]+Cnvrstn$ *END*

Step Four

Next we'll copy the Conversation file from Github - ensure the file is named according to your Author Key.

            

sudo curl -o CON_FILE.txt https://raw.githubusercontent.com/deadletter/AK_V1/master/CON_FILE

We'll need to edit a few setting, within our Conversation, so lets open it with Nano.

            

nano CON_FILE.txt


In order for the Conversation to operate you'll need to set the names of the individuals you wish to identify.

            

dld.keyset('NAME_YOURNAME') *CATCH-lib -R FS_2019 *Catch-lib -L @my_faces *input, @face.png NAME; FACE1, FACE2, FACE3 MATCH; INPUT, COMPARE 'NAME' COMPARE, input; {POST, "NAME" on MATCH} *END*



Step Five

We're almost done, to add a 'database of faces' we'll copy the template from Github - as a local Library.

            

sudo curl -o my_faces.txt https://raw.githubusercontent.com/deadletter/AK_V1/master/BFD_2019


The library should look something like this. Be sure to follow the template structure if you'd like to add more than three faces, remember to rename each KC to the individual's given (or chosen) name.

            

*lib - BFD_2019 *// Copyright 2018 Coffee Heist Basic data-base of faces for FS demo tutorials, Created FEBRUARY 7 2019 //* @; https://dld.domain.com/ FACE1; { F_0, @FACE1-0.png F_1, @FACE1-1.png F_2, @FACE1-2.png } FACE2; { F_0, @FACE2-0.png F_1, @FACE2-1.png F_2, @FACE2-2.png } FACE3; { F_0, @FACE3-0.png F_1, @FACE3-1.png F_2, @FACE3-2.png } /recall -- Oxford University Press *END*

Step Six

We're on the penultimate step, adding your data. At minimum you'll need three images per individual. (F_0) Front profile, (F_1) left profile & (F_2) right profile. You'll need to repeat this step for each file you're uploading.

            

scp path/to/file/to/copy [email protected]0.0.0.0:/var/www/html/dld/

Step Seven

Finally you'll need to submit your Author Key to DeadLetter by entering its address at: https://ak.deadletter.io

            

https://dld.domain.com/dld/ak.txt


It can take up to 28 hours for an Author key to be trusted by DeadLetter; if you'd like to learn more visit our Author Key walk-through, or start a conversation on our Community Hub.

Conclusion

This example of DeadLetter enables for quick development of facial recognition - with static imagery - along with a strong framework for expansion to motion picture.

NOTE: This is not intended as a production ready Conversation, simply an example of deadCL. For production deployments matching functionality should be performed by Pairs Interpretation 2019 (libs.deadletter.io/PI_2019) Library.

Possible uses

- Keyless Doors: with a few modifications, camera & an internet connected lock you could create a secure doorway.
- Attendance Records: keep track of classroom attendance with bio-meteric sensors.