Extraction of Video Fingerprints and Identification of Multimedia Using Video Fingerprinting

Abstract

A video fingerprinting algorithm extracts characteristic features from regions of interest in a media object, such as a video signal. The regions of interest contain the perceptually important parts of the video signal. A fingerprint may be extracted from a target media object, and the fingerprint the target media content may then be matched against multiple regions of interest of known reference fingerprints. This matching may allow identification of complex scenes, inserts, and different versions of the same content presented in, for example, different formats of the media object.

1 - 30 . (canceled) 
     
     
         31 . A method comprising:
 receiving, by a processor executing a fingerprint extraction algorithm, a frame of a media signal obtained from a media object;   extracting, by the processor, characteristic features of multiple regions of interest of the media object;   isolating, by the processor, each region of interest;   transforming, by the processor, each region of interest into a rectangular region;   calculating, by the processor, a fingerprint of each region of interest; and   matching, by the processor, each fingerprint with reference fingerprints.   
     
     
         32 . The method of  claim 31 , wherein the fingerprint of each region of interest provides information relating to an identity or other characteristics of each region of interest. 
     
     
         33 . The method of  claim 31 , wherein the matching of each fingerprint with reference fingerprints further comprises matching the fingerprint of each region of interest against multiple regions of reference content. 
     
     
         34 . The method of  claim 31 , further comprising selecting, by the processor, a required number of regions of interest that will be analyzed. 
     
     
         35 . The method of  claim 34 , wherein the selecting is based on a characteristic selected from a group of characteristic types consisting of size, stability, or length of these regions of interest. 
     
     
         36 . The method of  claim 31 , wherein an orientation of the rectangular region of interest is determined by orientation of its edges. 
     
     
         37 . The method of  claim 31 , wherein each rectangular region has an identical size and orientation. 
     
     
         38 . The method of  claim 37 , wherein each rectangular region having an identical size and orientation comprises converting each rectangular region to have the identical size and orientation through a method selected from a group consisting of image rotation, scale, or skew transformations. 
     
     
         39 . A computing device comprising:
 a processor;   a storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
 frame receiving logic executed by the processor for receiving a frame of a media signal obtained from a media object; 
 extracting logic executed by the processor for extracting characteristic features of multiple regions of interest of the media object; 
 isolating logic executed by the processor for isolating each region of interest; 
 transforming logic executed by the processor for transforming each region of interest into a rectangular region; 
 calculating logic executed by the processor for calculating a fingerprint of each region of interest; and 
 matching logic executed by the processor for matching each fingerprint with reference fingerprints. 
   
     
     
         40 . The computing device of  claim 39 , wherein the fingerprint of each region of interest provides information relating to an identity or other characteristics of each region of interest. 
     
     
         41 . The computing device of  claim 39 , wherein the matching logic for matching each fingerprint with reference fingerprints further comprises reference content matching logic executed by the processor for matching the fingerprint of each region of interest against multiple regions of reference content. 
     
     
         42 . The computing device of  claim 39 , further comprising selecting logic executed by the processor for selecting a required number of regions of interest that will be analyzed. 
     
     
         43 . The computing device of  claim 42 , wherein the selecting is based on a characteristic selected from a group of characteristic types consisting of size, stability, or length of these regions of interest. 
     
     
         44 . The computing device of  claim 39 , wherein an orientation of the rectangular region of interest is determined by orientation of its edges. 
     
     
         45 . The computing device of  claim 39 , wherein each rectangular region has an identical size and orientation. 
     
     
         46 . The computing device of  claim 45 , wherein each rectangular region having an identical size and orientation comprises converting logic executed by the processor for converting each rectangular region to have the identical size and orientation through a method selected from a group consisting of image rotation, scale, or skew transformations. 
     
     
         47 . A non-transitory computer-readable storage medium tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining the steps of:
 receiving, by the processor executing a fingerprint extraction algorithm, a frame of a media signal obtained from a media object;   extracting, by the processor, characteristic features of multiple regions of interest of the media object;   isolating, by the processor, each region of interest;   transforming, by the processor, each region of interest into a rectangular region;   calculating, by the processor, a fingerprint of each region of interest; and   matching, by the processor, each fingerprint with reference fingerprints.   
     
     
         48 . The medium of  claim 47 , wherein the fingerprint of each region of interest provides information relating to an identity or other characteristics of each region of interest. 
     
     
         49 . The medium of  claim 47 , wherein the matching of each fingerprint with reference fingerprints further comprises matching the fingerprint of each region of interest against multiple regions of reference content. 
     
     
         50 . The medium of  claim 47 , further comprising selecting, by the processor, a required number of regions of interest that will be analyzed.