An adequate analysis of the originality of the video is of a great importance in video processing field. This paper presents a method for feature matching between two video streams. One of the video streams is subjected for severe compression, noise and rotation. These two copies represent the same movie but only one of the versions is original. 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 unstructured frames from video stream. By involving color information as a feature together with intensity profile for frame blocks 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 of mean squares of the difference is done to verify the originality of the film.