All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

Building a Custom Screen Contact Detection Model for Privacy Protection

By

Two_hands

6mo ago· 20 min readen

Summary

The article details the author's 3-month journey building a custom computer vision model called EyesOff that detects when someone is looking at your screen to prevent shoulder surfing. The author explains why they couldn't use existing models like Eye-Contact-CNN1 due to licensing issues, and describes their process of training a specialized model using webcam footage to create a privacy protection application.

Key quotes

· 4 pulled
For the past 3 months, I have been working to create a model to detect whether or not someone is looking at a screen.
I am building this model for EyesOff. It's an application which detects people looking at your screen.
The aim is to keep you safe from shoulder surfing, utilising your webcam to give you the power to prevent snoopers.
The first model I considered for the app was the Eye-Contact-CNN1, which was trained to detect eye contact in children. However, due to its license I cannot use it.
Snippet from the RSS feed
For the past 3 months, I have been working to create a model to detect whether or not someone is looking at a screen. This blog recounts the steps I took to train such a model.

You might also wanna read