公开(公告)号：US20080063274A1

公开(公告)日：2008-03-13

申请号：US11942606

申请日：2007-11-19

申请人： Michael Cohen ,  Ying-Qing Xu ,  Heung-Yeung Shum ,  Jue Wang

发明人： Michael Cohen ,  Ying-Qing Xu ,  Heung-Yeung Shum ,  Jue Wang

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： G11B27/034 ,  G06K9/00711 ,  G06T15/02 ,  H04N5/262

摘要： The techniques and mechanisms described herein are directed to a system for stylizing video, such as interactively transforming video to a cartoon-like style. Briefly stated, the techniques include determining a set of volumetric objects within a video, each volumetric object being a segment. Mean shift video segmentation may be used for this step. With that segmentation information, the technique further includes indicating on a limited number of keyframes of the video how segments should be merged into a semantic region. Finally, a contiguous volume is created by interpolating between keyframes by a mean shift constrained interpolation technique to propagate the semantic regions between keyframes.

摘要翻译： 这里描述的技术和机制针对用于对视频进行风格化的系统，诸如将视频交互地变换成卡通样式。 简而言之，技术包括确定视频内的一组体积对象，每个体积对象是一段。 平均移位视频分割可用于该步骤。 利用该分割信息，该技术还包括在片段的有限数量的关键帧上指示片段如何被合并到语义区域中。 最后，通过平均偏移约束插值技术在关键帧之间进行内插以在关键帧之间传播语义区域来创建连续体积。

公开(公告)号：US20050226502A1

公开(公告)日：2005-10-13

申请号：US10814851

申请日：2004-03-31

申请人： Michael Cohen ,  Ying-Qing Xu ,  Heung-Yeung Shum ,  Jue Wang

发明人： Michael Cohen ,  Ying-Qing Xu ,  Heung-Yeung Shum ,  Jue Wang

IPC分类号： G06K9/00 ,  G06K9/34 ,  H04N5/262

CPC分类号： G11B27/034 ,  G06K9/00711 ,  G06T15/02 ,  H04N5/262

摘要： The techniques and mechanisms described herein are directed to a system for stylizing video, such as interactively transforming video to a cartoon-like style. Briefly stated, the techniques include determining a set of volumetric objects within a video, each volumetric object being a segment. Mean shift video segmentation may be used for this step. With that segmentation information, the technique further includes indicating on a limited number of keyframes of the video how segments should be merged into a semantic region. Finally, a contiguous volume is created by interpolating between keyframes by a mean shift constrained interpolation technique to propagate the semantic regions between keyframes.

摘要翻译： 这里描述的技术和机制针对用于对视频进行风格化的系统，诸如将视频交互地变换成卡通样式。 简而言之，技术包括确定视频内的一组体积对象，每个体积对象是一段。 平均移位视频分割可用于该步骤。 利用该分割信息，该技术还包括在片段的有限数量的关键帧上指示片段如何被合并到语义区域中。 最后，通过平均偏移约束插值技术在关键帧之间进行内插以在关键帧之间传播语义区域来创建连续体积。

公开(公告)号：US07483553B2

公开(公告)日：2009-01-27

申请号：US10812754

申请日：2004-03-29

申请人： Ying-Qing Xu ,  Heung-Yeung Shum ,  Michael Cohen ,  Lin Liang ,  Hua Zhong

发明人： Ying-Qing Xu ,  Heung-Yeung Shum ,  Michael Cohen ,  Lin Liang ,  Hua Zhong

IPC分类号： G06K9/00

CPC分类号： G06T11/00

摘要： Caricature exaggeration systems, engines, and methods create a drawing of a facial image, compare relationships among facial features in the drawing to corresponding relationships in facial images and corresponding caricatures in a database, and automatically exaggerate at least one relationship among facial features in the drawing based on the facial images and the corresponding caricatures in the database.

摘要翻译： 漫画夸张系统，引擎和方法创建面部图像的图形，比较绘图中的面部特征与面部图像中的对应关系和数据库中相应漫画的关系，并自动夸大图中面部特征之间的至少一个关系 基于面部图像和数据库中的相应漫画。

公开(公告)号：US20050212821A1

公开(公告)日：2005-09-29

申请号：US10812754

申请日：2004-03-29

申请人： Ying-Qing Xu ,  Heung-Yeung Shum ,  Michael Cohen ,  Lin Liang ,  Hua Zhong

发明人： Ying-Qing Xu ,  Heung-Yeung Shum ,  Michael Cohen ,  Lin Liang ,  Hua Zhong

IPC分类号： G09G5/00

CPC分类号： G06T11/00

摘要： Caricature exaggeration systems, engines, and methods create a drawing of a facial image, compare relationships among facial features in the drawing to corresponding relationships in facial images and corresponding caricatures in a database, and automatically exaggerate at least one relationship among facial features in the drawing based on the facial images and the corresponding caricatures in the database.

摘要翻译： 漫画夸张系统，引擎和方法创建面部图像的图形，比较绘图中的面部特征与面部图像中的对应关系和数据库中相应漫画的关系，并自动夸大图中面部特征之间的至少一个关系 基于面部图像和数据库中的相应漫画。

公开(公告)号：US07397948B1

公开(公告)日：2008-07-08

申请号：US10796736

申请日：2004-03-08

申请人： Michael Cohen ,  Bo Thiesson ,  Ying-Qing Xu ,  Jue Wang

发明人： Michael Cohen ,  Bo Thiesson ,  Ying-Qing Xu ,  Jue Wang

IPC分类号： G06K9/00

CPC分类号： G06K9/4652 ,  G06T7/11

摘要： Mean shift is a nonparametric estimator of density which has been applied to image and video segmentation. Traditional mean shift based segmentation uses a radially symmetric kernel to estimate local density, which is not optimal in view of the often structured nature of image and more particularly video data. The system and method of the invention employs an anisotropic kernel mean shift in which the shape, scale, and orientation of the kernels adapt to the local structure of the image or video. The anisotropic kernel is decomposed to provide handles for modifying the segmentation based on simple heuristics. Experimental results show that the anisotropic kernel mean shift outperforms the original mean shift on image and video segmentation in the following aspects: 1) it gets better results on general images and video in a smoothness sense; 2) the segmented results are more consistent with human visual saliency; and 3) the system and method is robust to initial parameters.

摘要翻译： 平均偏移是已经应用于图像和视频分割的密度的非参数估计器。 传统的基于平均移位的分割使用径向对称的核来估计局部密度，鉴于图像的经常结构化的特性，更特别是视频数据，这是非最优的。 本发明的系统和方法采用各向异性核平均移位，其中内核的形状，尺度和取向适应于图像或视频的局部结构。 各向异性核被分解以提供用于基于简单启发式修改分割的句柄。 实验结果表明，各向异性核平均偏移在以下几个方面优于原始平均偏移图像和视频分割：1）在平滑度方面对一般图像和视频获得更好的结果; 2）分段结果与人类视觉显着性更为一致; 和3）系统和方法对初始参数是鲁棒的。

公开(公告)号：US08194102B2

公开(公告)日：2012-06-05

申请号：US12245771

申请日：2008-10-06

申请人： Michael Cohen ,  Qing Luan ,  Steven Drucker ,  Johannes Kopf ,  Ying-Qing Xu ,  Matthew T. Uyttendaele

发明人： Michael Cohen ,  Qing Luan ,  Steven Drucker ,  Johannes Kopf ,  Ying-Qing Xu ,  Matthew T. Uyttendaele

IPC分类号： G09G5/02 ,  G06T15/10 ,  G09G5/00 ,  G10L21/00

CPC分类号： G06T3/40

摘要： Techniques are described for rendering annotations associated with an image. A view of an image maybe shown on a display, and different portions of the image are displayed and undisplayed in the view according to panning and/or zooming of the image within the view. The image may have annotations. An annotation may have a location in the image and may have associated renderable media. The location of the annotation relative to the view may change according to the panning and/or zooming. A strength of the annotation may be computed, the strength changing based the panning and/or zooming of the image. The media may be rendered according to the strength. Whether to render the media may be determined by comparing the strength to a threshold.

摘要翻译： 描述了用于渲染与图像相关联的注释的技术。 可以在显示器上显示图像的视图，并且根据视图内的图像的平移和/或缩放来在视图中显示和不显示图像的不同部分。 图像可能有注释。 注释可以在图像中具有位置并且可以具有相关联的可渲染媒体。 注释相对于视图的位置可能会根据平移和/或缩放而改变。 可以计算注释的强度，根据图像的平移和/或缩放来改变强度。 媒体可以根据实力渲染。 可以通过将强度与阈值进行比较来确定是否呈现媒体。

公开(公告)号：US20100085383A1

公开(公告)日：2010-04-08

申请号：US12245771

申请日：2008-10-06

申请人： Michael Cohen ,  Qing Luan ,  Steven Drucker ,  Johannes Kopf ,  Ying-Qing Xu ,  Matthew T. Uyttendaele

发明人： Michael Cohen ,  Qing Luan ,  Steven Drucker ,  Johannes Kopf ,  Ying-Qing Xu ,  Matthew T. Uyttendaele

IPC分类号： G09G5/00

CPC分类号： G06T3/40

摘要： Techniques are described for rendering annotations associated with an image. A view of an image maybe shown on a display, and different portions of the image are displayed and undisplayed in the view according to panning and/or zooming of the image within the view. The image may have annotations. An annotation may have a location in the image and may have associated renderable media. The location of the annotation relative to the view may change according to the panning and/or zooming. A strength of the annotation may be computed, the strength changing based the panning and/or zooming of the image. The media may be rendered according to the strength. Whether to render the media may be determined by comparing the strength to a threshold.

摘要翻译： 描述了用于渲染与图像相关联的注释的技术。 可以在显示器上显示图像的视图，并且根据视图内的图像的平移和/或缩放来在视图中显示和不显示图像的不同部分。 图像可能有注释。 注释可以在图像中具有位置并且可以具有相关联的可渲染媒体。 注释相对于视图的位置可能会根据平移和/或缩放而改变。 可以计算注释的强度，根据图像的平移和/或缩放来改变强度。 媒体可以根据实力渲染。 可以通过将强度与阈值进行比较来确定是否呈现媒体。

公开(公告)号：US20070189627A1

公开(公告)日：2007-08-16

申请号：US11353799

申请日：2006-02-14

申请人： Michael Cohen ,  Jue Wang

发明人： Michael Cohen ,  Jue Wang

IPC分类号： G06K9/40 ,  G06K9/00

CPC分类号： G06K9/00228

摘要： An automated face enhancement system and process which can automatically improve faces in videos or other images by applying cosmetic effects, given only a small amount of user interaction for initialization. For an input video, the system will first track the face and eye locations, and classify pixels in the face into different facial components based on local color models. The classification results of different frames are temporally smoothed to ensure temporal coherence. A set of cosmetic filters are then applied to different facial components.

摘要翻译： 一种自动化的面部增强系统和过程，可以通过应用美容效果来自动改善视频或其他图像中的脸部，只给予少量用户交互进行初始化。 对于输入视频，系统将首先跟踪脸部和眼睛的位置，并根据本地颜色模型将脸部像素分类为不同的面部组件。 不同帧的分类结果在时间上平滑，以确保时间一致性。 然后将一套美容过滤器应用于不同的面部组件。

公开(公告)号：US20060215016A1

公开(公告)日：2006-09-28

申请号：US11087221

申请日：2005-03-22

申请人： Michael Cohen ,  Jue Wang

发明人： Michael Cohen ,  Jue Wang

IPC分类号： H04N7/14

CPC分类号： H04N7/148

摘要： A real-time low frame-rate video compression system and method that allows the user to perform face-to-face communication through an extremely low bandwidth network. At the encoder side, the system is able to automatically select only a few good faces from the original sequence with high visual quality and compress and transmit them. At the decoder side, the system use image-morphing based rendering method to generate a normal frame-rate video. Experimental results show that the system is superior to more traditional video codecs for low bit-rate face-to-face communication.

公开(公告)号：US07583287B2

公开(公告)日：2009-09-01

申请号：US11087221

申请日：2005-03-22

申请人： Michael Cohen ,  Jue Wang

发明人： Michael Cohen ,  Jue Wang

IPC分类号： H04N7/14

CPC分类号： H04N7/148

摘要： A real-time low frame-rate video compression system and method that allows the user to perform face-to-face communication through an extremely low bandwidth network. At the encoder side, the system is able to automatically select only a few good faces from the original sequence with high visual quality and compress and transmit them. At the decoder side, the system use image-morphing based rendering method to generate a normal frame-rate video. Experimental results show that the system is superior to more traditional video codecs for low bit-rate face-to-face communication.

摘要翻译： 一种实时低帧率视频压缩系统和方法，允许用户通过极低带宽网络进行面对面通信。 在编码器侧，系统能够以较高的视觉质量自动从原始序列中仅选择几个良好的面，并进行压缩和传输。 在解码器侧，系统使用基于图像变形的渲染方法来生成正常的帧率视频。 实验结果表明，该系统优于传统的低比特率面对面通信视频编解码器。