The tool wasn’t very accurate when it was first introduced. It would only blur the faces the algorithm could detect. An improvement was made to the tool in February 2016, which supported blurring of objects even if they moved around in the video. The latest update to the Blur Faces tool improves it even further, as Stevens writes in his announcement: Steven claims that Google’s face recognition algorithm is capable of recognizing the same person in different instances of the video. Here is how YouTubers can access the tool: The user may have to wait a while before Google’s algorithm is done with your video. The algorithm works by breaking the video into several chunks of frames, and detect faces on each of these frames individually. Once the faces have been detected on every individual frame, they are matched in order to compute who those faces belong to. During this time, the user is free leave the page and do something else on YouTube. Once the processing is complete, the tool lists faces of the different people present in the video. The user can choose to blur one, multiple, or all the faces in the video. The video is embedded on the same page, so that the user can preview the output. Finally, once the user selects the save button, the process will be complete. The user will also have the option to save the blurred video as a new video. RELATED STORIES YOU NEED TO CHECK OUT:
YouTube app won’t work on Xbox One [FIX] YouTube videos pause at start on Windows 10 [Fix]
Name *
Email *
Commenting as . Not you?
Save information for future comments
Comment
Δ
