Shefalee Wardha
Published © GPL3+

Multi-Modal Biometric Attendance System

Edge Deployment on RPi & Intel Movidius NCS2 with MQTT

IntermediateFull instructions provided15 hours1,278

Things used in this project

Hardware components

Raspberry Pi 3 Model B
Raspberry Pi 3 Model B
I have done this project in RPi 4
×1
Camera Module V2
Raspberry Pi Camera Module V2
×1

Software apps and online services

OpenCV
OpenCV
OpenVINO™ toolkit
Intel OpenVINO™ toolkit
Python 3.6
MQTT
MQTT
FFServer
SMS Messaging API
Twilio SMS Messaging API

Hand tools and fabrication machines

DB Browser for SQLite
USB Hub
I have tried with 2 Movidius stick as seen in the write-up picture. If you want only one then connect it directly to RPi

Story

Read more

Custom parts and enclosures

OpenVINO Toolkit Download Proof

There is no custom electronics required for this project.

Schematics

Architecture Diagram

This is the architecture diagram. Since it is a software project, architecture diagram is suitable than circuit diagram.

Code

Multi-Modal Biometric Attendance System

Please go through Readme.md file for project details. To Execute: python ./face_recognition_demo.py -m_fd OV2019-models/face-detection-retail-0004.xml -m_lm OV2019-models/landmarks-regression-retail-0009.xml -m_reid OV2019-models/face-reidentification-retail-0095.xml -d_fd MYRIAD -d_lm MYRIAD -d_reid MYRIAD --verbose -fg "Face_Gallery/" You may modify the -d params if you want to change the device or add --run-detector if you want to retrain.

Credits

Shefalee Wardha

Shefalee Wardha

1 project • 0 followers

Comments