-
公开(公告)号：US20060152585A1
公开(公告)日：2006-07-13
申请号：US10560448
申请日：2004-06-04
申请人： Alexandre Bourret , David Hands , Damien Bayart , Andrew Davis
发明人： Alexandre Bourret , David Hands , Damien Bayart , Andrew Davis
CPC分类号： H04N17/004 , G06T7/001 , H04N17/02
摘要： A method and system for automated video quality assessment which reduces the adverse effects of sub-field/frame misalignments between the reference and test sequences. More particularly, the invention provides for misalignments down to a sub-field/frame level to be handled by individually matching sub-field/frame elements of a test video field/frame with sub-field/frame elements from a reference video field/frame. The use of a matching element size that is significantly smaller than the video field/frame size enables transient sub-field/frame misalignments to be effectively tracked.
-
公开(公告)号：US07715592B1
公开(公告)日：2010-05-11
申请号：US09889041
申请日：2000-01-24
IPC分类号： G06K9/00
CPC分类号： H04N17/00 , H04N17/004
摘要： Two video signals, typically an original signal and a degraded version of the same signal, are analyzed firstly to identify perceptually relevant boundaries of elements forming video images depicted therein. These boundaries are then compared to determine the extent to which the properties of the boundaries defined in one image are preserved in the other, to generate an output indicative of the perceptual difference between the first and second signals. The boundaries may be defined by edges, color, luminance or texture contrasts, disparities between frames in a moving or stereoscopic image, or other means. The presence, absence, difference in clarity or difference in means of definition of the boundaries is indicative of the perceptual importance of the differences between the signals, and therefore of the extent to which any degradation of the signal will be perceived by the human viewer of the resulting degraded image. The results may also be weighted according to the perceptual importance of the image depicted—for example the features which identify a human face, and in particular those responsible for visual speech cues.
摘要翻译： 首先分析两个视频信号，通常是相同信号的原始信号和劣化版本，以识别形成其中描绘的视频图像的元素的感知相关边界。 然后比较这些边界以确定在一个图像中定义的边界的属性在另一个图像中被保留的程度，以产生指示第一和第二信号之间感知差的输出。 边界可以由边缘，颜色，亮度或纹理对比度，移动或立体图像中的帧之间的差异或其他方式来定义。 边界的定义方式的存在，不存在，明确性差异或差异表示信号之间的差异的感知重要性，并且因此指示信号的任何退化将被人的观察者 造成的退化图像。 结果还可以根据所描绘的图像的感知重要性加权，例如识别人脸的特征，特别是负责视觉语音提示的特征。
-
公开(公告)号：US20060274618A1
公开(公告)日：2006-12-07
申请号：US10558673
申请日：2004-06-04
申请人： Alexandre Bourret
发明人： Alexandre Bourret
IPC分类号： G11B20/00
CPC分类号： G06T9/00 , G06T7/0002 , G06T7/13 , G06T2207/10016 , G06T2207/20016 , G06T2207/30168 , H04N5/142 , H04N17/004
摘要： The present invention applies edge detector techniques as are known per se in the art to the field of automated video quality assessment by providing a method of and system for video quality assessment which employs any known edge detection algorithm as the basis of an edge detection stage for performing edge analysis of test video fields/frames in order to generate an edge parameter value that can then be used to contribute to an overall video quality value. The use of an edge detector stage contributes valuable information concerning image attributes which are perceptually significant to a human viewer to the quality assessment, thus rendering the result provided by the automated assessment more similar to that which would be performed by a human viewer undertaking a subjective assessment.
摘要翻译： 本发明通过提供一种用于视频质量评估的方法和系统来应用本领域本身已知的边缘检测器技术，该技术采用任何已知的边缘检测算法作为边缘检测阶段的基础， 对测试视频字段/帧进行边缘分析，以便生成边缘参数值，然后可以将其用于贡献整个视频质量值。 使用边缘检测器阶段提供关于图像属性的有价值的信息，这些信息对于人类观察者对于质量评估是感知上的重要的，从而使由自动评估提供的结果更接近由主观的人类观察者执行的结果 评定。
-
公开(公告)号：US07812857B2
公开(公告)日：2010-10-12
申请号：US10558673
申请日：2004-06-04
申请人： Alexandre Bourret
发明人： Alexandre Bourret
CPC分类号： G06T9/00 , G06T7/0002 , G06T7/13 , G06T2207/10016 , G06T2207/20016 , G06T2207/30168 , H04N5/142 , H04N17/004
摘要： Edge detector techniques, known per se in the art, are applied to the field of automated video quality assessment. Any known edge detection algorithm is used as the basis of an edge detection stage for performing edge analysis of test video fields/frames in order to generate an edge parameter value that can then be used to contribute to an overall video quality value. The use of an edge detector stage contributes valuable information concerning image attributes which are perceptually significant to a human viewer to the quality assessment, thus rendering the result provided by the automated assessment more similar to that which would be performed by a human viewer undertaking a subjective assessment.
摘要翻译： 本领域已知的边缘检测器技术被应用于自动化视频质量评估领域。 任何已知的边缘检测算法被用作用于执行测试视频场/帧的边缘分析的边缘检测级的基础，以便生成边缘参数值，然后可以使用边缘参数值来贡献整个视频质量值。 使用边缘检测器阶段提供关于图像属性的有价值的信息，这些信息对于人类观察者对于质量评估是感知上的重要的，从而使由自动评估提供的结果更接近由主观的人类观察者执行的结果 评定。
-
-
-
搜索结果
4 条记录 (耗时 0.04 秒)
