The ONLY Text Detection (OCR) API You Will Ever Need

This video illustrates how to take a video and extract the text (optical character recognition) and coordinate bounding boxes of that text for each frame so we can understand what text is displayed in our video content as well as where and when. This approach uses the Google Cloud Video Intelligence API which leverages state of the art deep learning models and allows us to avoid building this code entirely from scratch. --Outline-- Intro 0:00 - 0:53 Download GitHub Repo 0:53 - 1:21 Install Node & NPM 1:21 - 1:39 Download Dependencies 1:39 - 2:03 Script Explanation 2:03 - 2:59 Upload Video to GCP 2:59 - 3:48 Paste GSUTIL URI 3:48 - 4:45 Create Service Account 4:45 - 5:36 Execute Script with Env Variable 5:36 - 6:58 Install http-server 6:58 - 7:40 Start HTTP Server 7:40 - 7:54 Reveal Bounding Boxes 7:54 - 9:33 #ocr #computervision --GitHub Repository-- https://github.com/aioverlords/Video-Intelligence-Text --Google Video Intelligence API-- https://cloud.google.com/video-intelligence _ Subscribe https://www.youtube.com/channel/UCiO0K2xt5irIN6x13FNzYTg?sub_confirmation=1 _ New Here? My name is Tim Draper and I live in Boston, MA. I work for a marketing technology startup and love to teach others about emerging technology around artificial intelligence internet of things and google cloud platform. _ Contact YouTube: YouTube comments are by far the best way to get a response from me! Email: thetimdraper[at]gmail.com *If you contact me, also drop a comment on a video just letting me know that you reached out. _ Need Help with Something? I offer micro consulting sessions to quickly solve your problems over a screen share. https://calendly.com/session-with-tim