Hacker News new | ask | show | jobs
by mthoms 507 days ago
This is very cool.

I'm curious about how you process the video feed; Do you stitch it back together as one long image and then perform OCR? Or just look at every N frames?

I've been looking for an open source library that helps with taking a scrolling video and then stitching it into an image but I haven't had much luck.