This Chrome extension blocks images that can trigger PTSD by hiding them from view when the page loads. To do this, we first created a Convolutional Neural Network trained on images of triggering items. For our proof of concept, we chose knives. This network achieved 84% accuracy over 10 epochs. We then created a chrome extension which utilizes tensorflow.js to classify images as they load on pages. These are sent to the page being loaded which then hides all images classified as such.
Built With
- css
- html
- javascript
- jupyter-notebook
- keras
- python
- tensorflow
Log in or sign up for Devpost to join the conversation.