This paper presents a method for descriptive feature matching between two video streams of the same scene. The second video is a corrupted copy of the first video. Examples of reliable recognition of an original scene that is subjected for compression and noise are presented. The algorithm is invariant to image scale and rotation, providing robust matching across a substantial range of video signals. This paper shows an approach to using descriptive features for randomly chosen frames from video stream. By involving color information as a feature we increase the robustness of the identification process. The median of low frequencies is measured, followed by an average of spectral information from the same frame to identify clusters belonging to a scene in a film. Finally, a comparison analysis is done to verify the originality of the film.