-
公开(公告)号：US09971940B1
公开(公告)日：2018-05-15
申请号：US15231445
申请日：2016-08-08
Applicant: Google Inc.
Inventor： Luciano Sbaiz , Jay Yagnik , King Hong Thomas Leung , Hanna Pasula , Thomas Chadwick Walters , Thomas Bugnon , Matthias Rochus Konrad
CPC classification number: G06K9/00758 , G06F21/10 , G06F2221/074 , G06K9/00718 , G06K9/00765 , G06K9/6215 , G06K9/6255 , G06K9/6269 , G06N3/04
Abstract: Provided content is determined to contain an asset represented by reference content by comparing digital fingerprints of the provided content and the reference content. The fingerprints of the reference content and the provided content are generated using a convolutional neural network (CNN). The CNN is trained using a plurality of frame triplets including an anchor frame representing the reference content, a positive frame which is a transformation of the anchor frame, and a negative frame representing content that is not the reference content. The provided content is determined to contain the asset represented by the reference content based on a similarity measure between the generated fingerprints. If the provided content is determined to contain the asset represented by the reference content, a policy associated with the asset is enforced on the provided content.
-
公开(公告)号：US09972060B2
公开(公告)日：2018-05-15
申请号：US15260252
申请日：2016-09-08
Applicant: Google Inc.
Inventor： Filip Pavetic , Matthias Rochus Konrad , Hanna Pasula
CPC classification number: G06T1/0021 , G06F21/10 , G06K9/00744 , G06K9/4604 , G06K9/6202 , G06T7/0081 , G06T7/11 , G06T7/20 , G06T7/408 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , H04N21/23418 , H04N21/2541 , H04N21/2743 , H04N21/8352
Abstract: A method and system generates and compares sub-fingerprints for videos. Sub-fingerprints of a video provide representations of characteristics of portions of video content of the video. Sub-fingerprints can be used to determine whether a video includes video content of another video effectively. The video can include other video content to visually appear different from the other video. When a sub-fingerprint of the video matches a fingerprint of the other video, the video includes video content of the other video. Motions of video content of the video can be tracked to identify regions of video frames that include image content that includes motion. Sub-images can created and used to create sub-fingerprints of the video.
-
公开(公告)号：US20180068410A1
公开(公告)日：2018-03-08
申请号：US15260252
申请日：2016-09-08
Applicant: Google Inc.
Inventor： Filip Pavetic , Matthias Rochus Konrad , Hanna Pasula
CPC classification number: G06T1/0021 , G06F21/10 , G06K9/00744 , G06K9/4604 , G06K9/6202 , G06T7/0081 , G06T7/11 , G06T7/20 , G06T7/408 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , H04N21/23418 , H04N21/2541 , H04N21/2743 , H04N21/8352
Abstract: A method and system generates and compares sub-fingerprints for videos. Sub-fingerprints of a video provide representations of characteristics of portions of video content of the video. Sub-fingerprints can be used to determine whether a video includes video content of another video effectively. The video can include other video content to visually appear different from the other video. When a sub-fingerprint of the video matches a fingerprint of the other video, the video includes video content of the other video. Motions of video content of the video can be tracked to identify regions of video frames that include image content that includes motion. Sub-images can created and used to create sub-fingerprints of the video.
-
-
Search Results
3
records
(took 0.019 seconds)
