Fingerprinting to match videos having varying aspect ratios

A method for generating a combined fingerprint of a video, the method executed by at least one computer system comprising a processor and a computer-readable storage medium, the method comprising:

• generating a first transformed video by applying a first aspect correction method to the video;
• generating a first fingerprint using the first transformed video, the first fingerprint having a first half and a second half;
• retrieving a second fingerprint from the computer-readable storage medium, the second fingerprint based on a second aspect correction method and having a first half and a second half;
• combining the first half of the first fingerprint with the second half of the second fingerprint to generate the combined fingerprint;
• and
• storing the combined fingerprint in the computer-readable storage medium.

A system for generating a combined fingerprint of a video, the system contained within a computer program product embodied on a non-transitory computer-readable storage medium and executed by a processor, the system further comprising:

• a combined fingerprint generator, wherein the combined fingerprint generator comprises:
• a transformation strategy comprising a first and a second aspect correction method;
• and
• a video transformation module that takes as input the first and second aspect correction method and the video and creates as output a first and second transformed video;
• a fingerprint generator that takes as input a first and a second transformed video and creates as output a first and a second fingerprint, the first and second fingerprints each having a first half and a second half;
• wherein the combined fingerprint generator further comprises a combination module for combining a first half of the first fingerprint with a second half of the second fingerprint to generate a combined fingerprint;
• a fingerprint database for storing the combined fingerprint.