公开(公告)号：US20060077489A1

公开(公告)日：2006-04-13

申请号：US10923116

申请日：2004-08-20

申请人： Yeqing Zhang ,  Robert Loce ,  Beilei Xu

发明人： Yeqing Zhang ,  Robert Loce ,  Beilei Xu

IPC分类号： H04N1/46

CPC分类号： H04N1/603

摘要： Compensation for rendering device non-uniformities is provided for halftoned images. A spatially dependent tone reproduction curve (TRC) provides compensation values. Pixel location information is used to access TRC values. For example, the values are modification values. The modification values are added to the pixel values to generate combined values. Quantization is applied to the combined values to prepare compensated image data for rendering. For example, Rank Ordered Error Diffusion is applied to the combined values. The combined values may include diffused error from previously processed pixels. Gray values may be estimated for the respective pixels. The estimated gray values may be used to access compensation information from a TRC that is both spatially and gray value dependent. Mathematical basis decomposition is used to reduce TRC memory requirements. For example, Discrete Cosine Transformation, Singular Value Decomposition or Principal Component Analysis is used to determine a compact form for the TRC.

公开(公告)号：US09165201B2

公开(公告)日：2015-10-20

申请号：US13233780

申请日：2011-09-15

申请人： Yeqing Zhang ,  Beilei Xu ,  Lalit K. Mestha ,  Graham Pennington

发明人： Yeqing Zhang ,  Beilei Xu ,  Lalit K. Mestha ,  Graham Pennington

IPC分类号： G06K9/32 ,  G06K9/00

CPC分类号： G06K9/3241 ,  G06K9/00362 ,  G06K9/3233

摘要： An embodiment generally relates to systems and methods for determining cell phone usage automatically by individuals operating vehicles. A processing module can process multi-spectral images or videos of individuals and detect different regions in the image such as face regions, hand regions, and cell phone regions. Further, the processing module can analyze the regions based on locations and numbers of skin pixels and cell phone pixels to determine if the individual is holding his or her cell phone near his or her face. Based on the analysis, it can be determined whether the individual is operating the cell phone. Further, the analysis can yield a confidence level associated with the cell phone usage.

摘要翻译： 实施例一般涉及用于由个人操作车辆自动确定手机使用的系统和方法。 处理模块可以处理个人的多光谱图像或视频，并检测图像中的不同区域，例如面部区域，手区域和蜂窝电话区域。 此外，处理模块可以基于皮肤像素和手机像素的位置和数量来分析区域，以确定个体是否将他或她的手机保持在他或她的脸部附近。 基于分析，可以确定个人是否在操作手机。 此外，分析可以产生与手机使用相关联的置信水平。

公开(公告)号：US08432582B2

公开(公告)日：2013-04-30

申请号：US10923116

申请日：2004-08-20

申请人： Yeqing Zhang ,  Robert Paul Loce ,  Beilei Xu

发明人： Yeqing Zhang ,  Robert Paul Loce ,  Beilei Xu

IPC分类号： G06K15/00 ,  H04N1/40

CPC分类号： H04N1/603

摘要： Compensation for rendering device non-uniformities is provided for halftoned images. A spatially dependent tone reproduction curve (TRC) provides compensation values. Pixel location information is used to access TRC values. For example, the values are modification values. The modification values are added to the pixel values to generate combined values. Quantization is applied to the combined values to prepare compensated image data for rendering. For example, Rank Ordered Error Diffusion is applied to the combined values. The combined values may include diffused error from previously processed pixels. Gray values may be estimated for the respective pixels. The estimated gray values may be used to access compensation information from a TRC that is both spatially and gray value dependent. Mathematical basis decomposition is used to reduce TRC memory requirements. For example, Discrete Cosine Transformation, Singular Value Decomposition or Principal Component Analysis is used to determine a compact form for the TRC.

摘要翻译： 为半色调图像提供渲染设备不均匀性的补偿。 空间依赖色调再现曲线（TRC）提供补偿值。 像素位置信息用于访问TRC值。 例如，值是修改值。 将修改值添加到像素值以生成组合值。 将量化应用于组合值以准备用于渲染的补偿图像数据。 例如，将秩排序误差扩散应用于组合值。 组合的值可以包括来自先前处理的像素的扩散误差。 可以针对各个像素估计灰度值。 估计的灰度值可用于从空间和灰度依赖的TRC访问补偿信息。 数学基础分解用于减少TRC记忆体要求。 例如，使用离散余弦变换，奇异值分解或主成分分析来确定TRC的紧凑形式。

公开(公告)号：US07627191B2

公开(公告)日：2009-12-01

申请号：US11505220

申请日：2006-08-14

申请人： Beilei Xu ,  Robert P. Loce ,  Yeqing Zhang

发明人： Beilei Xu ,  Robert P. Loce ,  Yeqing Zhang

IPC分类号： G06K9/40

CPC分类号： H04N1/3872 ,  H04N1/3877

摘要： Image data is scaled, rotated and/or otherwise manipulated. Diffusive effects of associated interpolation and/or re-sampling are compensated for, or corrected, by applying an adaptive packing form of error diffusion to output data of one or more manipulating transforms. For example, rank order error diffusion is applied to output data of a manipulating transform, thereby restoring compaction to otherwise diffuse halftone structures (e.g., halftone dots, lines, etc), saturated text and/or other small, high contrast image elements.

摘要翻译： 图像数据被缩放，旋转和/或以其它方式操纵。 通过将误差扩散的自适应填充形式应用于一个或多个操纵变换的输出数据来补偿或校正相关内插和/或重新采样的扩散效应。 例如，排序误差扩散被应用于操纵变换的输出数据，由此恢复压缩以另外漫射半色调结构（例如，半色调点，线等），饱和文本和/或其它小的高对比度图像元素。

公开(公告)号：US20080037899A1

公开(公告)日：2008-02-14

申请号：US11505220

申请日：2006-08-14

申请人： Beilei Xu ,  Robert P. Loce ,  Yeqing Zhang

发明人： Beilei Xu ,  Robert P. Loce ,  Yeqing Zhang

IPC分类号： G06K9/36 ,  G06K9/32

CPC分类号： H04N1/3872 ,  H04N1/3877

摘要： Image data is scaled, rotated and/or otherwise manipulated. Diffusive effects of associated interpolation and/or re-sampling are compensated for, or corrected, by applying an adaptive packing form of error diffusion to output data of one or more manipulating transforms. For example, rank order error diffusion is applied to output data of a manipulating transform, thereby restoring compaction to otherwise diffuse halftone structures (e.g., halftone dots, lines, etc), saturated text and/or other small, high contrast image elements.

摘要翻译： 图像数据被缩放，旋转和/或以其它方式操纵。 通过将误差扩散的自适应填充形式应用于一个或多个操纵变换的输出数据来补偿或校正相关内插和/或重新采样的扩散效应。 例如，排序误差扩散被应用于操纵变换的输出数据，由此恢复压缩以另外漫射半色调结构（例如，半色调点，线等），饱和文本和/或其它小的高对比度图像元素。

公开(公告)号：US20130070957A1

公开(公告)日：2013-03-21

申请号：US13233780

申请日：2011-09-15

申请人： Yeqing Zhang ,  Beilei Xu ,  Lalit K. Mestha ,  Graham Pennington

发明人： Yeqing Zhang ,  Beilei Xu ,  Lalit K. Mestha ,  Graham Pennington

IPC分类号： G06K9/00

CPC分类号： G06K9/3241 ,  G06K9/00362 ,  G06K9/3233

摘要： An embodiment generally relates to systems and methods for determining cell phone usage automatically by individuals operating vehicles. A processing module can process multi-spectral images or videos of individuals and detect different regions in the image such as face regions, hand regions, and cell phone regions. Further, the processing module can analyze the regions based on locations and numbers of skin pixels and cell phone pixels to determine if the individual is holding his or her cell phone near his or her face. Based on the analysis, it can be determined whether the individual is operating the cell phone. Further, the analysis can yield a confidence level associated with the cell phone usage.

摘要翻译： 实施例一般涉及用于由个人操作车辆自动确定手机使用的系统和方法。 处理模块可以处理个人的多光谱图像或视频，并检测图像中的不同区域，例如面部区域，手区域和蜂窝电话区域。 此外，处理模块可以基于皮肤像素和手机像素的位置和数量来分析区域，以确定个体是否将他或她的手机保持在他或她的脸部附近。 基于分析，可以确定个人是否在操作手机。 此外，分析可以产生与手机使用相关联的置信水平。

公开(公告)号：US20080068660A1

公开(公告)日：2008-03-20

申请号：US11522610

申请日：2006-09-18

申请人： Robert P. Loce ,  Yeqing Zhang ,  Beilei Xu

发明人： Robert P. Loce ,  Yeqing Zhang ,  Beilei Xu

IPC分类号： G06F15/00

CPC分类号： H04N1/40075 ,  H04N1/4092

摘要： Images that include halftone structures are sharpened. A copy of received halftone image data is blurred, thereby reducing a detectability of edges of the halftone structures. Edges remaining in the blurred image data are detected. An edge enhancement image is generated based on the detected edges. The original received halftone image data is combined with the edge enhancement image, thereby generating sharpness enhanced image data having halftone structures. The sharpness enhanced image data having halftone structures can be rendered through a halftone screen that is compatible with a halftone screen that was used to generate the originally received image data. Alternatively, the sharpness enhanced image data having halftone structures is rendered according to error diffusion techniques, such as, rank order error diffusion in order to achieve or maintain dot or halftone structure compaction.

摘要翻译： 包括半色调结构的图像被削尖。 所接收的半色调图像数据的副本被模糊，从而降低了半色调结构的边缘的可检测性。 检测残留在模糊图像数据中的边缘。 基于检测到的边缘生成边缘增强图像。 原始接收的半色调图像数据与边缘增强图像组合，从而产生具有半色调结构的锐度增强的图像数据。 具有半色调结构的清晰度增强的图像数据可以通过与用于生成原始接收的图像数据的半色调屏幕兼容的半色调屏幕来呈现。 或者，具有半色调结构的清晰度增强的图像数据根据误差扩散技术（例如等级误差扩散）来进行，以实现或维持点或半色调结构压缩。

公开(公告)号：US07719719B2

公开(公告)日：2010-05-18

申请号：US11522610

申请日：2006-09-18

申请人： Robert P. Loce ,  Yeqing Zhang ,  Beilei Xu

发明人： Robert P. Loce ,  Yeqing Zhang ,  Beilei Xu

IPC分类号： H04N1/405 ,  H04N1/409

CPC分类号： H04N1/40075 ,  H04N1/4092

摘要： Images that include halftone structures are sharpened. A copy of received halftone image data is blurred, thereby reducing a detectability of edges of the halftone structures. Edges remaining in the blurred image data are detected. An edge enhancement image is generated based on the detected edges. The original received halftone image data is combined with the edge enhancement image, thereby generating sharpness enhanced image data having halftone structures. The sharpness enhanced image data having halftone structures can be rendered through a halftone screen that is compatible with a halftone screen that was used to generate the originally received image data. Alternatively, the sharpness enhanced image data having halftone structures is rendered according to error diffusion techniques, such as, rank order error diffusion in order to achieve or maintain dot or halftone structure compaction.

摘要翻译： 包括半色调结构的图像被削尖。 所接收的半色调图像数据的副本被模糊，从而降低了半色调结构的边缘的可检测性。 检测残留在模糊图像数据中的边缘。 基于检测到的边缘生成边缘增强图像。 原始接收的半色调图像数据与边缘增强图像组合，从而产生具有半色调结构的锐度增强的图像数据。 具有半色调结构的清晰度增强的图像数据可以通过与用于生成原始接收的图像数据的半色调屏幕兼容的半色调屏幕来呈现。 或者，具有半色调结构的清晰度增强的图像数据根据误差扩散技术（诸如等级误差扩散）来形成，以实现或维持点或半色调结构压缩。

公开(公告)号：US20070139520A1

公开(公告)日：2007-06-21

申请号：US11311950

申请日：2005-12-20

申请人： Robert Loce ,  Yeqing Zhang ,  Gaurav Sharma ,  Steven Harrington ,  Peter Crean

发明人： Robert Loce ,  Yeqing Zhang ,  Gaurav Sharma ,  Steven Harrington ,  Peter Crean

IPC分类号： H04N13/04

CPC分类号： H04N13/302

摘要： A system for enabling depth perception of image content in a rendered composite image, wherein illuminant/colorant depth discrimination encoding provides encoding of first and second source images in a composite image, for the purposes of subsequent illuminant/colorant depth discrimination decoding. Composite image rendering allows for rendering the composite image in a physical form. Illuminant/colorant depth discrimination decoding allows recovery of the first and second source images, thus offering to an observer the perception of spatial disparity between at least one of the recovered source images and some or all of the remaining image content perceived in the rendered composite image.

摘要翻译： 一种用于在渲染的合成图像中实现图像内容的深度感知的系统，其中光源/着色剂深度识别编码提供合成图像中的第一和第二源图像的编码，以用于随后的发光/着色剂深度鉴别解码。 复合图像渲染允许以物理形式呈现合成图像。 照明/着色深度鉴别解码允许恢复第一和第二源图像，从而向观察者提供至少一个恢复的源图像与所渲染的合成图像中感知的剩余图像内容中的一些或全部之间的空间差异的感知 。

公开(公告)号：US20070035749A1

公开(公告)日：2007-02-15

申请号：US11200227

申请日：2005-08-09

申请人： Yeqing Zhang ,  Robert Loce ,  Raja Bala

发明人： Yeqing Zhang ,  Robert Loce ,  Raja Bala

IPC分类号： G03F3/08 ,  G06F15/00

CPC分类号： H04N1/6016

摘要： A color correction method includes for each of a plurality of color separations of a digital image, establishing a tone reproduction curve in the form of a vector. The vector is a function of a plurality of basis vectors. The basis vectors account for colorant interactions between a primary colorant with which the color separation is to be rendered and at least one secondary colorant with which at least a second of the plurality of color separations is to be rendered. The vector includes modified input values corresponding to input values for the color separation which vary, depending on the input values of at least the second color separation. For a pixel of interest in the digital image, a modified input value for the color separation which corresponds to the input value of the given color separation is identified from the vector.

摘要翻译： 颜色校正方法包括数字图像的多个分色中的每一个，建立矢量形式的色调再现曲线。 向量是多个基本向量的函数。 基本向量涉及要与其进行分色的主要着色剂和至少一种次要着色剂之间的着色剂相互作用，至少一个次要着色剂将使多个分色中的至少一个分色进行再现。 矢量包括对应于颜色分离的输入值的修改的输入值，其根据至少第二颜色分离的输入值而变化。 对于数字图像中感兴趣的像素，从向量中识别对应于给定颜色分离的输入值的颜色分离的修改输入值。