Smart Face Recognition System using Python & PHP build with dlib 99.38% accurate

The objective of this project is to build smart face recognition system that can be easily implemented from multiple clients Android, Web App & using IP Cameras real-time wireless face recognition can be achieved in ATMs,  banks, offices etc. The main idea is to create a backend python server & service that will process the bank API and predict the confidence of image provided. Further, the results will be sent back again to bank API with the confidence of prediction.

Demo: https://www.vsltech.co.in/facerec/
*Ignore SSL Error: Chrome: (Advance-Proceed Unsafe) Firefox: (Add Exception-Allow Security Certificate)

Read this post for jumpstart: http://www.vslcreations.com/2017/10/howwhere-to-start-image-processing-for.html

How to install face_recognition?

• 1. Install pip: https://www.saltycrane.com/blog/2010/02/how-install-pip-ubuntu/
• sudo apt-get install python-pip python-dev build-essential
• 2. Install dependencies for dlib version >19.4: https://www.learnopencv.com/install-dlib-on-ubuntu/
• sudo apt-get install build-essential cmake pkg-config
  sudo apt-get install libx11-dev libatlas-base-dev
  sudo apt-get install libgtk-3-dev libboost-python-dev
• sudo pip install dlib
• 3. Or you can build from source but pip install works fine. Don't install in virtualenv else you have to keep your server 24X7 in virtualenv which will conflict when we will execute python code from PHP.
• 4. Install face_recognition using pip: https://github.com/ageitgey/face_recognition
  
• sudo pip install face_recognition

 

How to configure LAMP & SSL?

• 1. Install LAMP: http://howtoubuntu.org/how-to-install-lamp-on-ubuntu
• sudo apt-get install apache2
  sudo apt-get install libapache2-mod-php
• 2. SSL is required when you are trying to access devices from browsers like chrome. Install OpenSSL: https://www.digitalocean.com/community/tutorials/how-to-create-a-self-signed-ssl-certificate-for-apache-in-ubuntu-16-04 
• sudo openssl req -x509 -nodes -days 365 -newkey rsa:2048 -keyout /etc/ssl/private/apache-selfsigned.key -out /etc/ssl/certs/apache-selfsigned.crt
• sudo openssl dhparam -out /etc/ssl/certs/dhparam.pem 2048
• 3. Configure your IP details in the default config for SSL check the link.
• 4. Don't forget to allow SSL in your firewall ufw.
• 5. Assign static IP to your server, also you can get your DNS free from here: https://www.noip.com/
• 6. Now, you can browse your server from https://<YOUR_IP> or DNS if mapped. You will get alert from browsers for your self-signed SSL because your organization is not authorized to provide SSL to resolve this you can buy 3rd party SSLs or buy authorization online.

Private GitHub: https://github.com/vsltech/smartfacerecognition

Buy for $50USD only
Pay via PayPal: https://www.paypal.me/vslcreations

Contact for other payment options via email@vslcreations.com. After successful payment reply with your email id to get git access or link to download source codes.

Configure Code- SmartFaceRecognition

• register.php:  Simple javascript that contains front-end restrictions for file upload. This will upload an image with the adhar_id name & save to known_people directory.
• login.php: Initialize camera from the device & onclick of capture button save the image to unknown_people directory. Onlclick of login button executes detect.py that will do the face recognition & return image name: adhar_id from known_people directory then session for adhar_id is set to do the profile stuff. After recognition, it deletes unknown.jpg file to avoid conflicts with multi-user usage.
• 
  
  
• profile.php: Get the session adhar_id then you can connect to your HRM database & do whatever profiling you want.

• 1. Buy repository: https://github.com/vsltech/smartfacerecognition
• 2. Unzip smartfacerecognition.zip
• 3. Copy to www: sudo cp -R  smartfacerecognition /var/www/html
• 4. Change permission of folder to write also for files to be uploaded & stored in you known_people & unknown_people directories: 
• cd /var/www/html
• sudo chmod -R 777 smartfacerecognition

Now, you can test your fully-functional Smart FaceRecognition System from Android or any device. This can be easily added to any API calls or backend-service you are trying to build.

You can create .iso of your server & share the fully configured package with anyone or run on your Windows System using Vmware/VirtualBox, read this post: http://www.vslcreations.com/2017/11/how-to-build-more-than-4gb-live-system.html

Read Detailed Report: https://www.slideshare.net/VishalAditya/smart-face-recognition-system-analysis

Credits: Mayuresh

21:56