Gender-Aware Digital Signage in 30 Min

Build a digital signage system that detects who's watching and changes its content accordingly. Using AI face detection and gender estimation, the display automatically switches between different videos depending on the viewer — and plays an idle loop when nobody is around. Works on any PC or laptop with a camera.

Hardware:

1. Windows PC, Mac, Raspberry Pi, or any Linux device
2. USB or CSI Camera (not required for laptops with built-in camera)
3. Monitor or display screen (not required for laptops)

Software:

1. Grablo (grablo.co)

Want to skip the build and try it right away? Copy the pre-built project:

1. Install the Grablo software on your PC or device from grablo.co/download
2. Open this project in the Grablo Gallery and click "Copy to My Projects"
3. Go to My Projects, open the copied project, and connect to your device
4. Hit RUN and stand in front of the camera — the signage switches content based on who's watching

If you'd like to build it from scratch, follow the steps below.

Create a new project, name it "Gender-Aware Digital Signage," and select your device. Then create a dashboard with three widgets: a Camera widget for the live video feed, a Label showing the detected gender, and another Label displaying the current face area value. The camera takes up most of the screen, with the two labels on the side for monitoring.

This project uses 4 logics with 5 controls total. The first logic handles face detection — when the project starts, it initializes the camera, adds AI face detection to estimate gender, and continuously calculates the face area by multiplying face width by height. This face area acts as a simple proximity sensor: the closer the viewer, the larger the face appears on camera.

The second and third logics handle video playback. When the face area exceeds 5,000 pixels (meaning someone is close enough) and the AI estimates the viewer as male, it stops any currently playing video and starts the male-targeted video. A separate logic does the same for female viewers. Both use a 3-second hold time to prevent rapid switching when detection fluctuates between frames.

The fourth logic plays an idle video loop. When the face area drops below 5,000 pixels for 3 consecutive seconds — meaning the viewer walked away — it switches back to a default idle video.

Launch Your Project

1. Open your project
2. Connect to your device
3. Hit RUN!
4. Stand in front of the camera and watch the content change

Expected Results

1. The camera feed appears on the dashboard
2. When you approach the camera, the AI detects your face and estimates gender
3. The appropriate video starts playing within a few seconds
4. Walk away, and after 3 seconds the display switches back to the idle video
5. The Gender and Face Area labels update in real time

Now that you have a working gender-aware signage system, here are some ideas to take it further:

1. Add age estimation to play different content for different age groups
2. Use multiple cameras to cover different viewing angles
3. Add a viewer counter to track daily demographics
4. Connect to an external display via HDMI for a full signage setup
5. Combine gender and time-of-day to serve different content throughout the day

Troubleshooting

1. Face not detecting: Ensure good lighting and position the camera at eye level. Avoid strong backlighting or shadows on the face.
2. Gender estimation inaccurate: The AI works best with clear, frontal face views. Side profiles or partially covered faces reduce accuracy.
3. Video switching too fast: Increase the 3-second hold time in the logic conditions to prevent flickering.
4. Camera feed not showing: For USB cameras, try a different port. For CSI cameras on Raspberry Pi, check the ribbon cable connection.