A processing system may obtain a downscaled version of a reference copy of a video, comprising a plurality of downscaled versions of a plurality of frames of the reference copy of the video, obtain a first recorded frame of a first variant of a plurality of variants associated with the reference copy of the video, where the plurality of variants comprises a plurality of copies of the video encoded at different bitrates, generate a first downscaled version of the first recorded frame, calculate a first plurality of image distances between the first downscaled version of the first recorded frame and the plurality of downscaled versions of the plurality of frames of the reference copy of the video, and determine a first frame index of the first recorded frame in accordance with a first least image distance from among the first plurality of image distances that is calculated.