Video fingerprinting to identify video content

A non-transitory computer-readable medium having instructions stored thereon that, if executed by a computing device, cause the computing device to perform operations comprising:

• transforming an electronic video signal;
• computing statistics for video frames in the electronic video signal;
• and
• forming a fingerprint of the video as a change in the statistics over the video frames, wherein a calibration signal is used to align the video before computing the fingerprint.

An apparatus comprising a processor configured to:

• transform an electronic video signal;
• compute statistics for video frames in the electronic video signal;
• and
• form a fingerprint of the video as a change in the statistics over the video frames, wherein a calibration signal is used to align the video before computing the fingerprint.

A method of video fingerprinting comprising:

• computing, using a processor, values associated with luminance for a first video portion in an electronic video signal;
• computing, using the processor, values associated with luminance for a second video portion in the electronic video signal;
• determining, using the processor, changes in luminance between the first video portion and the second video portion;
• and
• forming, using the processor, a fingerprint to identify the electronic video signal based at least in part on data associated with the changes, wherein the fingerprint provides an index used to look up identifying metadata for the video in a metadata database, wherein the identifying metadata is associated with the index in the metadata database, and wherein a calibration signal is used to align the electronic video before forming the fingerprint.