Face blurring as a visual anonymity feature allow obscuring all faces in YouTube video is available since 2012 to creators, updated last February to let blur any objects even as they move—has now been updated today again to now easily and accurately blur specific faces in videos.
The new Blur Faces tool, launched Monday, displays images of faces in the video, so creators can simply click an individual image to start blurring throughout their video. As Google explains, "it automatically handles motion and presents creators with a thumbnail that encapsulates all instances of individual recognized by face detection technology."
To Blur Faces, go to Enhance tool in the Video Manager or watch page of a video. While, the Blur Faces tool can be found under "Blurring Effects" tab of Enhancements.
Once the tool is open, it began process of breaking video into frames to start detecting faces on each frame individually using high-quality face detection. Creators can then apply these blurring edits by choosing to "Save" edits in-place to uploaded videos without losing views, likes, and comments. While, with "Save As New" and deleting original video, will remove originally unblurred video from YouTube.
Later, you can use Custom Blurring tool to further enhance the automated face blurring edits in the same interface before publishing.
The tool support a wide array of situations, like "users wearing glasses, occlusion —(face being blocked, for example by a hand), and people leaving video and coming back later."
"Once we've detected the faces in each frame of your video, we start matching face detections within a single scene of the video, relying on both the visual characteristics of the face as well as the face's motion. To compute motion, we use the same technology that powers our Custom Blurring feature. Face detections aren't perfect, so we use a few techniques to help us hone in on edge cases such as tracking motion through occlusions (see the water bottle in the above GIF) and near the edge of the video frame. Finally, we compute visual similarity across what we found in each scene, pick the best face to show as a thumbnail, and present it to you."
The following image shows how to get there.