A processing system may obtain a first frame of a first variant associated with a reference copy of a video, where a plurality of variants comprises copies of the video encoded at different bitrates, determine a frame number of the first frame from a visual overlay containing the first frame number, calculate a first image distance between the first frame and a frame of the reference copy having the frame number, determine, from among a plurality of image distances for frames of each variant having the frame number, a closest image distance to the first image distance, the plurality of image distances comprising image distances between frames of the variants and the frame of the reference copy having the frame number, and identify the first frame as being from the first variant in accordance with a variant associated with the first closest image distance.