公开(公告)号：US20050156926A1

公开(公告)日：2005-07-21

申请号：US11081320

申请日：2005-03-16

申请人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner ,  David Cook

发明人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner ,  David Cook

IPC分类号： G06T7/60 ,  G06T7/00 ,  G06T7/20 ,  G06T15/40

CPC分类号： G06T7/579

摘要： In one embodiment according to the present invention, relative z-ordering of segments in a digital image is determined. A method comprises forward and backward motion matching of image regions to determine overlap, followed by the creation of relationships (e.g., pairwise relationships) between regions and comparing the result with the original image to determine the relative z-ordering.

摘要翻译： 在根据本发明的一个实施例中，确定数字图像中段的相对z-排列。 一种方法包括图像区域的向前和向后运动匹配以确定重叠，随后在区域之间建立关系（例如，成对关系），并将结果与​​原始图像进行比较以确定相对z排序。

公开(公告)号：US07429986B2

公开(公告)日：2008-09-30

申请号：US11081320

申请日：2005-03-16

申请人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner ,  David Cook

发明人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner ,  David Cook

IPC分类号： G06T15/00

CPC分类号： G06T7/579

摘要： In one embodiment according to the present invention, relative z-ordering of segments in a digital image is determined. A method comprises forward and backward motion matching of image regions to determine overlap, followed by the creation of relationships (e.g., pairwise relationships) between regions and comparing the result with the original image to determine the relative z-ordering.

摘要翻译： 在根据本发明的一个实施例中，确定数字图像中段的相对z-排列。 一种方法包括图像区域的向前和向后运动匹配以确定重叠，随后在区域之间建立关系（例如，成对关系），并将结果与​​原始图像进行比较以确定相对z排序。

公开(公告)号：US06900802B2

公开(公告)日：2005-05-31

申请号：US09922299

申请日：2001-08-03

申请人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner ,  David Cook

发明人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner ,  David Cook

IPC分类号： G06T7/60 ,  G06T7/00 ,  G06T7/20 ,  G06T15/40 ,  G06T15/00

CPC分类号： G06T7/579

摘要： In one embodiment according to the present invention, relative z-ordering of segments in a digital image is determined. A method comprises forward and backward motion matching of image regions to determine overlap, followed by the creation of relationships (e.g., pairwise relationships) between regions and comparing the result with the original image to determine the relative z-ordering.

公开(公告)号：US06584213B2

公开(公告)日：2003-06-24

申请号：US09912743

申请日：2001-07-23

申请人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner

发明人： Adityo Prakash ,  Eniko Fodor ,  Edward Ratner

IPC分类号： G06K900

CPC分类号： H04N19/543 ,  G06T7/248 ,  G06T2207/10016 ,  G06T2207/30221

摘要： An efficient method of matching a segment in one image with a segment in another image. Fourier transforms are implemented to aid in the process. In one embodiment, a method involves identifying a displacement of a segment present in a first image and a second image, the displacement representing a relative change in position of the segment between the first and second images.

公开(公告)号：US06876771B2

公开(公告)日：2005-04-05

申请号：US10028998

申请日：2001-12-20

申请人： Adityo Prakash ,  Edward Ratner

发明人： Adityo Prakash ,  Edward Ratner

IPC分类号： G06T9/00 ,  H04N7/26 ,  H04N7/30 ,  H04N7/34 ,  G06K9/36

CPC分类号： G06T9/007 ,  H04N19/105 ,  H04N19/146 ,  H04N19/176 ,  H04N19/593 ,  H04N19/60

摘要： In accordance with an embodiment, a method of encoding includes generating for each transform point a double difference coefficient (comprising the difference between a modeled difference coefficient and a raw difference coefficient) and encoding as an adaptive difference coefficient for each transform point either the double difference coefficient or the raw difference coefficient. Whether the double difference coefficient or the raw difference coefficient is selected to be the adaptive difference coefficient depends on which one provides more efficient coding. A method of decoding includes receiving the adaptive difference coefficients from the encoder, applying the same modeling and transform as the encoder to generate the modeled difference coefficients, generating corrective difference coefficients (from the adaptive difference coefficients and the modeled coefficients), and inverse transformation using the corrective difference coefficients. A system may include an encoder implementing the method of encoding and a decoder implementing the method of decoding.

摘要翻译： 根据实施例，一种编码方法包括：为每个变换点生成双差分系数（包括建模差分系数和原始差分系数之间的差异），并且将每个变换点的自适应差分系数进行编码， 系数或原始差分系数。 双差分系数或原始差分系数是否选择为自适应差分系数取决于哪一个提供更有效的编码。 解码方法包括从编码器接收自适应差分系数，应用与编码器相同的建模和变换以产生建模的差分系数，产生校正差分系数（来自自适应差分系数和建模系数），以及使用 校正差分系数。 系统可以包括实现编码方法的编码器和实现解码方法的解码器。

公开(公告)号：US06959117B2

公开(公告)日：2005-10-25

申请号：US10027924

申请日：2001-12-19

申请人： Edward Ratner ,  Adityo Prakash ,  Oliver W. Shih ,  Carroll Philip Gossett

发明人： Edward Ratner ,  Adityo Prakash ,  Oliver W. Shih ,  Carroll Philip Gossett

IPC分类号： G06T5/00 ,  H04N7/26 ,  G06K9/40

CPC分类号： G06T9/00 ,  G06T5/002 ,  G06T5/003 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20012 ,  G06T2207/20192 ,  H04N19/20

摘要： Using image segmentation in video compression brings about a limitation in video quality when a segment moves in position from frame to frame. The limitation arises because color contributions (bleeding or blurring) naturally occur between neighboring segments. The above-identified problem is overcome by providing solutions to compensate for color contributions between neighboring segments. In accordance with one embodiment, a method and apparatus de-blurs an image segment. De-blurring involves removing from the segment approximate color contributions from neighboring segments. This results in a segment that is approximately independent of color contributions from neighboring segments. In accordance with another embodiment, a method and apparatus re-blurs an image segment. Re-blurring involves adding to the segment approximate color contributions from a new arrangement of neighboring segments. This results in more realistic rendering of the segment, as it is located in the new arrangement.

摘要翻译： 在视频压缩中使用图像分割在片段从帧到帧的位置移动时，对视频质量产生限制。 限制出现是因为颜色贡献（渗色或模糊）自然地发生在相邻片段之间。 通过提供补偿相邻片段之间的颜色贡献的解决方案来克服上述问题。 根据一个实施例，一种方法和装置使图像段变得模糊。 去模糊涉及从段中去除相邻段的近似颜色贡献。 这导致大致独立于来自相邻片段的颜色贡献的片段。 根据另一个实施例，一种方法和装置重新模糊图像段。 重新模糊涉及从相邻片段的新布局添加到片段近似颜色贡献。 这将导致细分的更逼真的渲染，因为它位于新安排中。

公开(公告)号：US07133564B2

公开(公告)日：2006-11-07

申请号：US10087001

申请日：2002-02-28

申请人： Edward Ratner ,  Adityo Prakash ,  Hitoshi Watanabe ,  Sachin Ahuja

发明人： Edward Ratner ,  Adityo Prakash ,  Hitoshi Watanabe ,  Sachin Ahuja

IPC分类号： G06K9/36 ,  G06K9/48

CPC分类号： G06T7/12 ,  G06T2207/10016 ,  G06T2207/20008

摘要： One embodiment relates to an apparatus for image processing. The apparatus includes a candidate edge chain identifier for identifying candidate edge chains in an image being processed, means for calculating a dynamic chain-based threshold function that is dependent on at least one characteristic of the image being processed, and a threshold applicator for applying the dynamic chain-based threshold function to the candidate edge chains. The characteristic of the image being processed may be global in that it is determined from the overall image being processed. A system may include an encoder or a decoder, both of which include the above apparatus. Another embodiment relates to a method for image processing. The method determines a dynamic chain-based threshold function that is dependent on at least one characteristic of the image being processed and applies the dynamic threshold to a candidate edge chain.

公开(公告)号：US06947605B2

公开(公告)日：2005-09-20

申请号：US10087463

申请日：2002-02-28

申请人： Adityo Prakash ,  Edward Ratner ,  Hitoshi Watanabe ,  Sachin Ahuja

发明人： Adityo Prakash ,  Edward Ratner ,  Hitoshi Watanabe ,  Sachin Ahuja

IPC分类号： G06T7/60 ,  G06T5/00 ,  G06T7/00 ,  G06K9/36

CPC分类号： G06T7/12 ,  G06T2207/10016 ,  G06T2207/20008

摘要： One embodiment relates to an apparatus for image processing. The apparatus includes a candidate edge chain identifier for identifying candidate edge chains in an image being processed, means for calculating a dynamic chain-based threshold function that is dependent on at least one characteristic of the image being processed, and a threshold applicator for applying the dynamic chain-based threshold function to the candidate edge chains. The characteristic of the image being processed may be local in that it is calculated from the vicinity of each candidate chain. A system may include an encoder or a decoder, both of which include the above apparatus. Another embodiment relates to a method for image processing. The method determines a dynamic chain-based threshold function that is dependent on at least one characteristic of the image being processed and applies the dynamic threshold to a candidate edge chain.

摘要翻译： 一个实施例涉及用于图像处理的装置。 所述装置包括候选边缘链标识符，用于识别正在处理的图像中的候选边缘链，用于计算取决于正被处理的图像的至少一个特征的基于动态链的阈值函数的装置，以及用于应用 基于动态链路阈值函数的候选边缘链。 正在处理的图像的特征可以是局部的，因为它是从每个候选链的附近计算的。 系统可以包括编码器或解码器，它们都包括上述装置。 另一实施例涉及一种用于图像处理的方法。 该方法确定依赖于正在处理的图像的至少一个特性的基于动态链的阈值函数，并将动态阈值应用于候选边缘链。

公开(公告)号：US06898240B2

公开(公告)日：2005-05-24

申请号：US10094427

申请日：2002-03-07

申请人： Adityo Prakash ,  Eniko F. Prakash ,  Edward Ratner ,  John S. Chen

发明人： Adityo Prakash ,  Eniko F. Prakash ,  Edward Ratner ,  John S. Chen

IPC分类号： G06T7/20 ,  G06T9/00 ,  H04N7/26 ,  H04N7/12

CPC分类号： G06T7/20 ,  G06T9/00 ,  G06T9/004

摘要： One embodiment comprises a method for image processing. The method includes identifying an uncovered region in an image, determining at least one trivalent point, and extrapolating from the trivalent point to extend an edge of at least one of the image segments into the uncovered region. Another embodiment comprises an apparatus for image processing. The apparatus includes a predictor for predicting higher-frequency boundary information in newly uncovered regions. Another embodiment comprises a system for efficiently communicating video information. The system includes an encoder that encodes a video frame into an encoded frame, and a decoder that receives and decodes the encoded frame, wherein the encoder and decoder are both configured to identify uncovered regions and to extend edges from neighboring image segments into the uncovered region.

摘要翻译： 一个实施例包括用于图像处理的方法。 该方法包括识别图像中的未覆盖区域，确定至少一个三价点，并从三价点外推，将至少一个图像片段的边缘延伸到未覆盖区域。 另一实施例包括用于图像处理的装置。 该装置包括用于预测新近未覆盖区域中的较高频率边界信息的预测器。 另一实施例包括用于有效地传送视频信息的系统。 该系统包括将视频帧编码为编码帧的编码器和接收并解码编码帧的解码器，其中编码器和解码器都被配置为识别未覆盖区域并将边缘从相邻图像段延伸到未覆盖区域 。

公开(公告)号：US07792390B2

公开(公告)日：2010-09-07

申请号：US10032394

申请日：2001-12-19

申请人： Adityo Prakash ,  Edward Ratner ,  Dimitri Antsos

发明人： Adityo Prakash ,  Edward Ratner ,  Dimitri Antsos

IPC分类号： G06K9/54

CPC分类号： H04N19/649 ,  H04N19/119 ,  H04N19/30 ,  H04N19/50 ,  H04N19/593

摘要： In one embodiment, an image is broken up into multiple regions or segments, where each segment may be of arbitrary shape, and a transform (multi-scale or otherwise) is applied on the set of segments. In another embodiment, pattern adaptive prediction is used when predicting the next finer level of the transform pyramid. The pattern adaptive prediction uses the parent grid to determine what geometry of a filter is to be used when predicting the child grid. At the boundaries of the domain, the pattern adaptive prediction can be coupled with the domain adaptive prediction technique.

摘要翻译： 在一个实施例中，图像被分解成多个区域或区段，其中每个区段可以是任意形状，并且在该组段上应用变换（多尺度或其他）。 在另一个实施例中，当预测变换金字塔的下一个较细的级别时，使用模式自适应预测。 模式自适应预测使用父网格来确定在预测子网格时要使用的滤波器的几何形状。 在域的边界，模式自适应预测可以与域自适应预测技术相结合。