SlideWave
Hand gesture recognition built with CNNs to navigate slides hands-free.
A computer vision project that uses a convolutional neural network to recognize hand gestures in real time and map them to PowerPoint controls. Built to explore how deep learning can replace physical input devices, the model was trained on a custom gesture dataset and translates movements like swipes and pinches into slide navigation commands.
Built quickly to test a hypothesis. The goal was to get from idea to something I could actually use inside of a weekend — letting the AI do the heavy lifting on boilerplate while I focused on the shape of the experience.
A surprising amount of what used to take a month can now happen in a few evenings — as long as you have strong taste and know when to throw work away. The bottleneck has moved from implementation to judgment.