DEV Community

Luis Beltran
Luis Beltran

Posted on

1 1

[Azure Trial Hackathon - Face Mask Detector]

Overview of My Submission

This project consists of a mobile application that detects if a person wears a mask or not in a video. It combines the output of 2 Azure AI Cognitive Services:

  1. Azure Video Analyzer
  2. Azure Custom Vision

The application is written in C# using Xamarin, which allows to deliver a cross-platform mobile application that can run in Windows, Android, and iOS among other platforms.

App details:

  • You can record a local video
  • You can upload the video to Azure Video Analyzer
  • You can see a list of videos from Azure Video Analyzer service
  • You can access the details of a video

Azure Video Analyzer service doesn't tell you if you are wearing a mask or not, but it will return frames from the video. That's where Azure Custom Vision enters: Using Object Detection capabilities from Custom Vision project, I could label "mask" zones and "no-mask" zones. Then, I send the frame from Video Analyzer to Custom Vision so it can tell me if the person is wearing a mask or not.

Submission Category:

AI Aces

Link to Code on GitHub

Code

Additional Resources / Info

Image 1: Application Menu
Application Menu

Image 2: Recording a video
Recording a video

Image 3: Wearing a mask
Wearing a mask

Image 4: Accessing the video list
Accesing the video list

Image 5: Accessing video details: No mask / Mask detection
Accessing video details: No mask / Mask detection

Image 6: Adding mask and no mask tags
Adding mask and no mask tags

Image 7: Prediction
Prediction

Sentry image

See why 4M developers consider Sentry, “not bad.”

Fixing code doesn’t have to be the worst part of your day. Learn how Sentry can help.

Learn more

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

👋 Kindness is contagious

Please leave a ❤️ or a friendly comment on this post if you found it helpful!

Okay