Image and audio recognition and search platform

Abstract

The present disclosure relates to receiving video and audio from a plurality of devices, performing image recognition on the video and audio recognition on the audio, receiving an input image or input audio, and identifying video clips and audio clips containing a match to the input image or input audio.

1 . A method of video searching, comprising:
 obtaining a plurality of video clips from a plurality of devices, each video clip associated with one or more of time information indicating a time when the video clip was captured and location information indicating a location where the video clip was captured;   performing image recognition on the plurality of video clips;   receiving an input image; and   identifying all clips in the plurality of video clips that match the input image.   
     
     
         2 . The method of  claim 1 , wherein the image recognition comprises facial recognition and the input image comprises an image of a face. 
     
     
         3 . The method of  claim 2 , further comprising indicating time information for all clips in the plurality of video clips that match the image of the face. 
     
     
         4 . The method of  claim 2 , further comprising indicating location information for all clips in the plurality of video clips that match the image of the face. 
     
     
         5 . The method of  claim 2 , further comprising:
 generating a video comprising all clips in the plurality of video clips that match the image of the face.   
     
     
         6 . The method of  claim 2 , wherein the step of receiving an image of a face comprises receiving a photograph. 
     
     
         7 . The method of  claim 6 , further comprising:
 generating a video comprising all clips in the plurality of video clips that match the image of the face.   
     
     
         8 . The method of claim  65 , further comprising indicating time information for all clips in the plurality of video clips that match the image of the face. 
     
     
         9 . The method of  claim 8 , further comprising:
 generating a video comprising all clips in the plurality of video clips that match the image of the face.   
     
     
         10 . The method of  claim 6 , further comprising indicating location information for all clips in the plurality of video clips that match the image of the face. 
     
     
         11 . The method of  claim 10 , further comprising:
 generating a video comprising all clips in the plurality of video clips that match the image of the face.   
     
     
         12 . A method of audio searching, comprising:
 obtaining a plurality of audio clips from a plurality of devices, each audio clip associated with one or more of time information indicating a time when the audio clip was captured and location information indicating a location where the audio clip was captured;   performing audio recognition on the plurality of audio clips;   receiving input audio; and   identifying all clips in the plurality of audio clips that match the input audio.   
     
     
         13 . The method of  claim 12 , wherein the audio recognition comprises voice recognition and the input audio comprises a voice recording. 
     
     
         14 . The method of  claim 13 , further comprising indicating time information for all clips in the plurality of audio clips that match the voice in the voice recording. 
     
     
         15 . The method of  claim 14 , further comprising:
 generating audio comprising all clips in the plurality of audio clips that match the voice in the voice recording.   
     
     
         16 . The method of  claim 13 , further comprising indicating location information for all clips in the plurality of audio clips that match the voice in the voice recording. 
     
     
         17 . The method of  claim 16 , further comprising:
 generating audio comprising all clips in the plurality of audio clips that match the voice in the voice recording.