Transferring colors from a source object to a target object
    3.
    发明授权
    Transferring colors from a source object to a target object 有权
    将颜色从源对象传输到目标对象

    公开(公告)号:US08494262B2

    公开(公告)日:2013-07-23

    申请号:US13114736

    申请日:2011-05-24

    IPC分类号: G06K9/00

    CPC分类号: H04N1/603 G06T7/74

    摘要: A technique includes using a processor-based machine to determine a discrete color flow transformation to map target colors of a target object to source colors of a source object based at least in part on a first histogram indicating a color distribution of the target object and a second histogram of a color distribution indicating the source object. The technique includes determining a continuous color flow transformation to map the target colors to the source colors based at least in part on the discrete color flow transformation; and transforming the target colors of the target object to generate a third object based at least in part on the continuous color flow transformation.

    摘要翻译: 一种技术包括使用基于处理器的机器来至少部分地基于指示目标对象的颜色分布的第一直方图来确定离散颜色流变换以将目标对象的目标颜色映射到源对象的源颜色, 指示源对象的颜色分布的第二直方图。 该技术包括:至少部分地基于离散的颜色流变换来确定连续的颜色流变换以将目标颜色映射到源颜色; 以及至少部分地基于所述连续色彩流转换来转换所述目标对象的目标颜色以生成第三对象。

    SEGMENTING AN IMAGE
    4.
    发明申请
    SEGMENTING AN IMAGE 有权
    分割图像

    公开(公告)号:US20120301017A1

    公开(公告)日:2012-11-29

    申请号:US13114690

    申请日:2011-05-24

    申请人: Daniel Freedman

    发明人: Daniel Freedman

    IPC分类号: G06K9/00

    摘要: A technique includes representing an image to be segmented using a graph including vertices and edges, where a subset of the vertices is marked as belonging to a plurality of objects. The technique includes assigning weights to the edges based at least in part on color probability densities associated with the objects derived from the subset of vertices marked as belonging to the plurality of objects; and segmenting the image, including identifying boundaries of the objects based at least in part on the weights and the graph.

    摘要翻译: 一种技术包括使用包括顶点和边缘的图表示要分割的图像,其中顶点的子集被标记为属于多个对象。 该技术包括至少部分地基于与从标记为属于多个对象的顶点的子集导出的对象相关联的颜色概率密度来向边缘分配权重; 以及分割图像,包括至少部分地基于权重和图形来识别对象的边界。

    Image registration
    5.
    发明授权
    Image registration 有权
    图像注册

    公开(公告)号:US09088673B2

    公开(公告)日:2015-07-21

    申请号:US13825793

    申请日:2010-09-24

    摘要: An image registration method to register a target image with a reference image is provided, including to determine a target set of features present in the target image, to determine a reference set of features present in the reference image, to generate respective signatures for each feature in the target and reference sets, to match features from the target set to corresponding features in the reference set using the signatures, to generate respective transformations to map pairs of features in the target set to corresponding pairs of features in the reference set, and determine a similarity transformation for the target image using a measure of the accuracy of the transformations.

    摘要翻译: 提供了一种用参考图像注册目标图像的图像注册方法,包括确定目标图像中存在的特征的目标集合,以确定参考图像中存在的特征的参考集合,以生成每个特征的各个签名 在目标和参考集中,使用特征将来自目标集的特征与参考集中的对应特征相匹配,以产生相应的变换以将目标集中的特征对映射到参考集中的相应特征对,并且确定 使用测量转换精度的目标图像的相似度变换。

    DETERMINING PARAMETER VALUES BASED ON INDICATIONS OF PREFERENCE
    6.
    发明申请
    DETERMINING PARAMETER VALUES BASED ON INDICATIONS OF PREFERENCE 有权
    基于偏好指标确定参数值

    公开(公告)号:US20120308157A1

    公开(公告)日:2012-12-06

    申请号:US13118699

    申请日:2011-05-31

    IPC分类号: G06K9/36

    摘要: Indications are received regarding which of plural outputs are preferred over others of the plural outputs. A continuous function is computed that satisfies constraints corresponding to the received indications and that satisfies a predefined criterion. Values of parameters are computed based on the continuous function, wherein the values of the parameters are useable in a process to generate an output.

    摘要翻译: 接收关于多个输出中的哪一个比多个输出中的其他输出优先的指示。 计算满足与接收到的指示对应的约束并且满足预定准则的连续函数。 基于连续函数计算参数值,其中参数的值可用于生成输出的过程。

    Segmenting an image
    8.
    发明授权
    Segmenting an image 有权
    分割图像

    公开(公告)号:US08478032B2

    公开(公告)日:2013-07-02

    申请号:US13114690

    申请日:2011-05-24

    申请人: Daniel Freedman

    发明人: Daniel Freedman

    IPC分类号: G06K9/00

    摘要: A technique includes representing an image to be segmented using a graph including vertices and edges, where a subset of the vertices is marked as belonging to a plurality of objects. The technique includes assigning weights to the edges based at least in part on color probability densities associated with the objects derived from the subset of vertices marked as belonging to the plurality of objects; and segmenting the image, including identifying boundaries of the objects based at least in part on the weights and the graph.

    摘要翻译: 一种技术包括使用包括顶点和边缘的图表示要分割的图像,其中顶点的子集被标记为属于多个对象。 该技术包括至少部分地基于与从标记为属于多个对象的顶点的子集导出的对象相关联的颜色概率密度来向边缘分配权重; 以及分割图像,包括至少部分地基于权重和图形来识别对象的边界。

    Editing system for audiovisual works and corresponding text for television news
    9.
    发明授权
    Editing system for audiovisual works and corresponding text for television news 有权
    视听作品编辑系统和电视新闻相应文本

    公开(公告)号:US07836389B2

    公开(公告)日:2010-11-16

    申请号:US11106278

    申请日:2005-04-13

    IPC分类号: G06F17/00

    CPC分类号: G11B27/034 G11B27/329

    摘要: An audiovisual editing system that permits a journalist and other editors to edit both audiovisual and corresponding text segments included in a story. The data structure representing a story includes a list of media segments and a list of corresponding text segments. Each media segment has a type, such as script, SOT and voice, and includes a list of video clips. Each SOT segment or voice segment includes a list of timing control elements that determine the length of a media segment. The difference in the duration of the audiovisual material and the duration of the related text may be displayed to the editor, making it easier for the editor to match video to a script. Similarly, the duration of voice and SOT clips can be displayed to the editor, making it easier for the editor to match the video to the audio.

    摘要翻译: 一种视听编辑系统,允许记者和其他编辑者编辑故事中包含的视听和相应的文本段。 表示故事的数据结构包括媒体片段列表和相应文本片段的列表。 每个媒体片段都有一个类型,例如脚本,SOT和语音,并且包括视频剪辑列表。 每个SOT段或语音段包括确定媒体段的长度的定时控制元素的列表。 视听材料的持续时间和相关文本的持续时间的差异可能会显示给编辑器,使编辑器更容易将视频与脚本进行匹配。 类似地,语音和SOT剪辑的持续时间可以显示给编辑器,使得编辑器更容易将视频与音频相匹配。

    Determining parameter values based on indications of preference
    10.
    发明授权
    Determining parameter values based on indications of preference 有权
    根据偏好指标确定参数值

    公开(公告)号:US08903126B2

    公开(公告)日:2014-12-02

    申请号:US13118699

    申请日:2011-05-31

    摘要: Indications are received regarding which of plural outputs are preferred over others of the plural outputs. A continuous function is computed that satisfies constraints corresponding to the received indications and that satisfies a predefined criterion. Values of parameters are computed based on the continuous function, wherein the values of the parameters are useable in a process to generate an output.

    摘要翻译: 接收关于多个输出中的哪一个比多个输出中的其他输出优先的指示。 计算满足与接收到的指示对应的约束并且满足预定准则的连续函数。 基于连续函数计算参数值,其中参数的值可用于生成输出的过程。