首页> 外国专利> APPARATUS AND METHOD FOR IDENTIFYING VIDEO WITH COPYRIGHTS USING FACE RECOGNITION BASED ON MACHINE LEARNING

APPARATUS AND METHOD FOR IDENTIFYING VIDEO WITH COPYRIGHTS USING FACE RECOGNITION BASED ON MACHINE LEARNING

机译:基于基于机器学习的面部识别来识别版权的视频的装置和方法

摘要

The present invention relates to a method for identifying a video with copyrights using face recognition based on machine learning, which includes the steps of: mechanically learning a plurality of actor face image data based on deep learning; and determining whether an unknown video is the video with copyrights by predicting casted actors from an unknown video by using a face learning module for each actor generated by the machine learning and comparing casted actor information which is predicted over a specific frequency in the predicted result with metadata about videos with a plurality of copyrights. Accordingly, the present invention can identify copyrighted materials by predicting the face of the actor included in the copyrighted materials.;COPYRIGHT KIPO 2017
机译:本发明涉及一种基于机器学习的使用面部识别来识别具有版权的视频的方法,该方法包括以下步骤:基于深度学习机械地学习多个演员面部图像数据;通过使用由机器学习生成的每个演员的面部学习模块,从未知视频中预测演员,从未知视频中确定演员,并比较预测结果中在特定频率上预测的演员信息,从而确定未知视频是否是具有版权的视频。有关具有多个版权的视频的元数据。因此,本发明可以通过预测包括在受版权保护的材料中的演员的面部来识别受版权保护的材料。; COPYRIGHT KIPO 2017

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号