System and method for media segment identification
View Patent ↗A system and method for identifying media segments using audio augmented image cross-comparison is disclosed, in which a media segment identifying system analyses both audio and video content, producing a unique identifier to compare with previously identified media segments in a media segment database. The characteristic landmark-linked-image-comparisons are constructed by first identifying pairs of audio landmarks separated by a characteristic, or landmark, time. Digital images associated the audio landmarks are then compared, with the combination providing a characteristic landmark-linked-image-comparison. The audio landmarks are audio peaks that exceed predetermined thresholds. A landmark-time is the time between adjacent pairs of audio peaks. The pair of images associated with the audio peaks are reduced in pixel size and converted to gray scale. Corresponding pixels are compared to form a numeric comparison. One image may be mirrored before comparison to reduce the possibility of null comparisons.
1. A method of media segment identification, comprising:
providing a digital processor;
providing an identified media segment database, in functional connection to said digital processor, comprising one or more previously identified media segments, said previously identified media segments having an associated landmark-linked-image-comparison, said associated landmark-linked-image-comparison comprising a landmark-time and an image-cross-comparison, said image-cross-comparison being an image-comparison between a first and a second digital image, each associated with an audio peak and separated by said landmark-time, said audio peaks having a predetermined height greater than any audio level in said digital audio stream in a preceding, predetermined length of time, and wherein said image-cross-comparison comprises:
automatically selecting a first region of said first digital image;
automatically converting said selected first region to a first gray scale image; and
automatically comparing the value of each of the pixels of said first gray scale image to the value of a corresponding pixel in a second gray scale image, and recording a 1 if it is greater than or equal, and a 0 if it is less;
obtaining, by said digital processor, a current digital multimedia stream, having a current media segment comprising a digital image stream, and a digital audio stream;
automatically generating, by one or more software modules operable on said digital processor, a landmark-linked-image-comparison for said current media segment;
automatically comparing, by said software module, said obtained landmark-linked-image-comparison with said landmark-linked-image-comparisons in said media stream database; and
if said obtained landmark-linked-image-comparison matches one of said landmark-linked-image-comparisons in said identified media segment database, automatically tagging said current media segment as being equivalent to the identified media segment having said matched landmark-linked-image-comparison.
2. The method of claim 1 , wherein, said second gray scale image is said first gray scale image transposed about a vertical axis.
3. The method of claim 1 , wherein the pixels in said first gray scale image that are deemed to pixels in said second gray scale image are pixels that are displaced in second gray scale image.
4. The method of claim 3 , wherein the pixels in said first gray scale image are compared to pixels in said second gray scale image displaced by one row.
5. The method of claim 1 , wherein said first region is selected from a left half of said first digital image and said second gray scale image is a second region selected from a right half of said first digital image and converted to form said second gray scale image.