![Image artifact reduction using a neural network](/abs-image/US/2005/04/28/US20050089215A1/abs.jpg.150x150.jpg)
基本信息:
- 专利标题: Image artifact reduction using a neural network
- 专利标题(中):使用神经网络减少图像伪像
- 申请号:US10692582 申请日:2003-10-25
- 公开(公告)号:US20050089215A1 公开(公告)日:2005-04-28
- 发明人: Carl Staelin , Mani Fischer
- 申请人: Carl Staelin , Mani Fischer
- 主分类号: H04N7/26
- IPC分类号: H04N7/26 ; G06K9/62 ; G06K9/36 ; G06K9/40
摘要:
A neural network is trained and used to reduce artifacts in spatial domain representations of images that were compressed by a transform method and then decompressed. For example, the neural network can be trained and used to reduce artifacts such as blocking and ringing artifacts in JPEG images.
摘要(中):
训练和使用神经网络来减少通过变换方法压缩然后解压缩的图像的空间域表示中的伪像。 例如,神经网络可以被训练并用于减少诸如JPEG图像中的阻塞和振铃伪像等伪像。
公开/授权文献:
- US07346208B2 Image artifact reduction using a neural network 公开/授权日:2008-03-18