公开(公告)号：US08528019B1

公开(公告)日：2013-09-03

申请号：US09442960

申请日：1999-11-18

申请人： Nevenka Dimitrova ,  Thomas McGee ,  Jan Hermanus Elenbaas ,  Lalitha Agnihotri ,  Radu Jasinschi ,  Serhan Dagtas ,  Aaron S Mendelsohn

发明人： Nevenka Dimitrova ,  Thomas McGee ,  Jan Hermanus Elenbaas ,  Lalitha Agnihotri ,  Radu Jasinschi ,  Serhan Dagtas ,  Aaron S Mendelsohn

IPC分类号： G06F3/00 ,  G06F13/00 ,  H04N5/445

CPC分类号： H04N21/44222 ,  G06F17/30787 ,  G06F17/30796 ,  G06F17/30811 ,  G06F17/30828 ,  H04H60/27 ,  H04H60/46 ,  H04H60/58 ,  H04H60/59 ,  H04H60/65 ,  H04H60/72 ,  H04N7/163 ,  H04N21/434 ,  H04N21/4351 ,  H04N21/44008 ,  H04N21/4532 ,  H04N21/4622 ,  H04N21/4755

摘要： A method of selecting, storing and delivering desired audio/data/visual information includes the steps of determining viewing preferences of a viewer and receiving a first group of audio/data/visual signals, for example, broadcast and cable television signals or internet-based signals. Based on the first group of audio/data/visual signals, a second group of audio/data/visual signals, which is a subset of the first group of audio/data/visual signals, is identified. The second group of audio/data/visual signals is selected based on the association of EPG data for each signal with the viewing preferences of the viewer. Content data is then extracted from the second group of audio/data/visual signals and compared with the viewing preferences. The content data may include, for example, closed-captioned text, EPG data, audio information, visual information and transcript information. Based on the comparison of the content data extracted from the second group of audio/data/visual signals with the viewing preferences, audio/data/visual information contained in the second group of audio/data/visual signals which is of interest to the viewer is identified and stored for review at the viewers convenience.

摘要翻译： 选择，存储和传送所需音频/数据/视觉信息的方法包括以下步骤：确定观看者的观看偏好并接收第一组音频/数据/视觉信号，例如广播和有线电视信号或基于因特网 信号。 基于第一组音频/数据/视觉信号，识别作为第一组音频/数据/视觉信号的子集的第二组音频/数据/视觉信号。 基于每个信号的EPG数据与观看者的观看偏好的关联来选择第二组音频/数据/视觉信号。 然后从第二组音频/数据/视觉信号中提取内容数据，并与观看偏好进行比较。 内容数据可以包括例如闭路字幕文本，EPG数据，音频信息，视觉信息和抄本信息。 基于从第二组音频/数据/视觉信号提取的内容数据与观看偏好的比较，包含在观众感兴趣的第二组音频/数据/视觉信号中的音频/数据/视觉信息 被识别并存储在观众的方便审查。

公开(公告)号：US07143353B2

公开(公告)日：2006-11-28

申请号：US09822447

申请日：2001-03-30

申请人： Thomas McGee ,  Lalitha Agnihotri ,  Nevenka Dimitrova ,  Radu Jasinschi

发明人： Thomas McGee ,  Lalitha Agnihotri ,  Nevenka Dimitrova ,  Radu Jasinschi

IPC分类号： G06F3/00 ,  H04N5/91

CPC分类号： G06F17/30814 ,  G06F17/30852 ,  G11B27/105 ,  G11B27/107 ,  G11B27/11 ,  G11B27/326 ,  G11B2220/2562 ,  G11B2220/90 ,  H04N5/4401 ,  H04N21/4334 ,  H04N21/4335 ,  H04N21/435 ,  H04N21/43637 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/4663 ,  H04N21/47214 ,  H04N21/47217 ,  H04N21/84 ,  H04N21/8455 ,  H04N21/8456

摘要： A method, apparatus and systems for bookmarking an area of interest of stored video content is provided. As a viewer is watching a video and finds an area of interest, they can bookmark the particular segment of the video and then return to that segment with relative simplicity. This can be accomplished by pressing a button, clicking with a mouse or otherwise sending a signal to a device for marking a particular location of the video that is of interest. Frame identifiers can also be used to select a desired video from an index and to then retrieve the video from a medium containing multiple videos.

公开(公告)号：US07337455B2

公开(公告)日：2008-02-26

申请号：US10029916

申请日：2001-12-31

申请人： Lalitha Agnihotri ,  J. David Schaffer ,  Nevenka Dimitrova ,  Thomas McGee ,  Sylvie Jeannin

发明人： Lalitha Agnihotri ,  J. David Schaffer ,  Nevenka Dimitrova ,  Thomas McGee ,  Sylvie Jeannin

IPC分类号： H04N7/10 ,  H04N7/025

CPC分类号： G06K9/00718 ,  G06F17/30787 ,  G06F17/30802 ,  G06K9/62 ,  G11B27/28 ,  G11B2220/20 ,  H04N5/76 ,  H04N21/4147 ,  H04N21/44008 ,  H04N21/812

摘要： A method for optimizing the performance of an algorithm for detecting predetermined content in a media information stream, and a program and apparatus that operate in accordance with the method. The algorithm is a function of a set of parameters. The method comprises the steps of performing the algorithm at least once to detect the predetermined content in the media information stream, while employing a respective set of parameters in the algorithm for each performance thereof, and automatically evolving at least one respective set of parameters employed in the algorithm to maximize the degree of accuracy at which the algorithm detects the predetermined content in the media information stream.

摘要翻译： 一种用于优化用于检测媒体信息流中的预定内容的算法的性能的方法，以及根据该方法操作的程序和装置。 该算法是一组参数的函数。 该方法包括以下步骤：至少一次执行该算法以检测媒体信息流中的预定内容，同时在算法中对其每次演奏采用相应的一组参数，并且自动演化至少一个相应的参数集 最大化算法在媒体信息流中检测预定内容的准确度的算法。

公开(公告)号：US06771885B1

公开(公告)日：2004-08-03

申请号：US09498884

申请日：2000-02-07

申请人： Lalitha Agnihotri ,  Nevenka Dimitrova ,  Thomas McGee ,  Nicholas J. Mankovich

发明人： Lalitha Agnihotri ,  Nevenka Dimitrova ,  Thomas McGee ,  Nicholas J. Mankovich

IPC分类号： H04N591

CPC分类号： H04N21/4334 ,  H04N5/782 ,  H04N21/44008 ,  H04N21/458 ,  H04N21/47214

摘要： A video signal is processed to generate one or more signatures associated with a broadcast program to be recorded by a recording device. The signatures are then processed to determine an actual start time and end time of the desired broadcast program, such that the program can be properly recorded despite delays or other changes in a pre-scheduled broadcast time of the program. One or more of the extracted signatures may be based at least in part on, e.g., a keyframe similarity measure, a histogram, one or more detected commercials, a transcript, a program logo or other detected object, detected text, and a sign-on or sign-off of the desired program. Other types of signatures can also be used.

摘要翻译： 视频信号被处理以产生与由记录装置记录的广播节目相关联的一个或多个签名。 然后处理签名以确定所需广播节目的实际开始时间和结束时间，使得尽管程序的预先计​​划的广播时间有延迟或其他改变，也可以适当地记录节目。 提取的签名中的一个或多个可以至少部分地基于例如关键帧相似性度量，直方图，一个或多个检测到的广告，抄本，节目标志或其他检测到的对象，检测到的文本和签名， 打开或关闭所需的程序。 也可以使用其他类型的签名。

公开(公告)号：US07170566B2

公开(公告)日：2007-01-30

申请号：US10028378

申请日：2001-12-21

申请人： Thomas McGee ,  Lalitha Agnihotri ,  Nevenka Dimitrova ,  Radu Serban Jasinschi

发明人： Thomas McGee ,  Lalitha Agnihotri ,  Nevenka Dimitrova ,  Radu Serban Jasinschi

IPC分类号： H04N5/222

CPC分类号： H04N5/44 ,  H04N21/44008 ,  H04N21/812 ,  H04N21/84 ,  H04N21/8456

摘要： Techniques are disclosed for detecting commercials or other particular types of video content in a video signal. In an illustrative embodiment, color histograms are extracted from frames of the video signal. For each of at least a subset of the extracted color histograms, the extracted color histogram is compared to a family histogram. If the extracted color histogram falls within a specified range of the family histogram, the family histogram is updated to include the extracted color histogram as a new member. If the extracted color histogram does not fall within the specified range of the family histogram, the family histogram is considered complete and the extracted color histogram is utilized to generate a new family histogram for use in processing subsequent extracted color histograms. The resulting family histograms are utilized to detect commercials or other particular type of video content in the video signal.

摘要翻译： 公开了用于检测视频信号中的商业广告或其他特定类型的视频内容的技术。 在说明性实施例中，从视频信号的帧中提取颜色直方图。 对于提取的颜色直方图的至少一个子集中的每一个，将所提取的颜色直方图与族直方图进行比较。 如果提取的颜色直方图落入家族直方图的指定范围内，则更新系列直方图以将所提取的颜色直方图包括为新成员。 如果提取的颜色直方图不在家庭直方图的指定范围内，则家族直方图被认为是完整的，并且所提取的颜色直方图被用于生成用于处理随后提取的颜色直方图的新家族直方图。 所得到的系列直方图用于检测视频信号中的广告或其他特定类型的视频内容。

公开(公告)号：US06469749B1

公开(公告)日：2002-10-22

申请号：US09417288

申请日：1999-10-13

申请人： Nevenka Dimitrova ,  Thomas McGee ,  Lalitha Agnihotri

发明人： Nevenka Dimitrova ,  Thomas McGee ,  Lalitha Agnihotri

IPC分类号： H04N5222

CPC分类号： H04N21/435 ,  G06F17/30814 ,  G06K9/00718 ,  H04H60/37 ,  H04H60/59 ,  H04N7/002 ,  H04N21/235 ,  H04N21/26603 ,  H04N21/454 ,  H04N21/458 ,  H04N21/812

摘要： A video signal is processed to identify segments that are likely to be associated with a commercial or other particular type of video content. A signature is extracted from each of the segments so identified, and the extracted signatures are used, possibly in conjunction with additional temporal and contextual information, to determine which of the identified segments are in fact associated with the particular video content. One or more of the extracted signatures may be, e.g., a visual frame signature based at least in part on a visual characteristic of a frame of the video segment, as determined using information based on DC and motion coefficients of the frame, or DC and AC coefficients of the frame. A given extracted signature may alternatively be an audio signature based at least in part on a characteristic of an audio signal associated with a portion of the video segment. Other types of signatures can also be used. Advantageously, the invention allows the identification and extraction of particular video content to be implemented with significantly reduced amounts of memory and computational resources.

摘要翻译： 处理视频信号以识别可能与商业或其他特定类型的视频内容相关联的片段。 从所识别的每个片段中提取签名，并且可以使用所提取的签名，可能与附加的时间和上下文信息相结合，以确定哪个已识别的片段实际上与特定的视频内容相关联。 所提取的签名中的一个或多个可以是例如至少部分地基于视频段的视频特征的视觉帧签名，使用基于DC和帧的运动系数或DC的信息来确定，以及 帧的AC系数。 至少部分地基于与视频段的一部分相关联的音频信号的特性，给定的提取的签名可以替代地是音频签名。 也可以使用其他类型的签名。 有利地，本发明允许以显着减少的存储器和计算资源的量来实现特定视频内容的识别和提取。

公开(公告)号：US08199991B2

公开(公告)日：2012-06-12

申请号：US12516931

申请日：2007-12-03

申请人： Lalitha Agnihotri ,  James David Schaffer ,  Nevenka Dimitrova

发明人： Lalitha Agnihotri ,  James David Schaffer ,  Nevenka Dimitrova

IPC分类号： G06K9/36

CPC分类号： G06K9/00134 ,  G06K9/3233 ,  G06K9/3275 ,  G06T7/70 ,  G06T2207/20056 ,  G06T2207/30072

摘要： A method of automatically identifying the microarray chip corners and probes, even if there are no probes at the corners, in a high density and high resolution microarray scanned image having an image space, wherein the method minimizes the error distortions in the image arising in the scanning process by applying to the image a multipass corner finding algorithm comprising: (a) applying a Radon transform to an input microarray image to project the image into an angle and distance space where it is possible to find the orientation of the straight lines; (b) applying a fast Fourier transform to the projected image of (a) to find the optimal tilting angle of the projected image; (c) determining the optimal first and last local maxima for the optimal tilting angle; (d) back projecting the determined first and last local maxima to the image space to find the first approximation of the first and last column lines of the image; (e) rotating the image and repeating steps (a) through (d) to find the first approximation of the top and bottom row lines of the image; (f) determining the first approximation of the four corners of the image from the intersection of the column and row lines; (g) applying a heuristic for determining if the first approximation of step (f) is sufficient; and (h) optionally trimming the scanned image around the first approximation of the four corners and repeating steps (a) through (f).

摘要翻译： 即使在具有图像空间的高密度和高分辨率的微阵列扫描图像中，即使在角落处没有探针也能够自动识别微阵列芯片角部和探针的方法，其中该方法使图像中产生的图像中的误差失真最小化 扫描过程，通过向图像应用多点角发现算法，包括：（a）将Radon变换应用于输入微阵列图像以将图像投影到可以找到直线的取向的角度和距离空间中; （b）对（a）的投影图像应用快速傅立叶变换以找到投影图像的最佳倾斜角; （c）确定最佳倾斜角的最佳第一和最后局部最大值; （d）将确定的第一和最后局部最大值向前投影到图像空间，以找到图像的第一列和最后一列的第一近似; （e）旋转图像并重复步骤（a）至（d）以找到图像的顶行和下行行的第一近似值; （f）从列和行之间的交点确定图像的四个角的第一近似值; （g）应用启发式来确定步骤（f）的第一近似是否足够; 和（h）可选地修整围绕四个角的第一近似的扫描图像并重复步骤（a）至（f）。

公开(公告)号：US07457811B2

公开(公告)日：2008-11-25

申请号：US10178015

申请日：2002-06-21

申请人： Angel Janevski ,  Nevenka Dimitrova ,  Lalitha Agnihotri

发明人： Angel Janevski ,  Nevenka Dimitrova ,  Lalitha Agnihotri

IPC分类号： G06F17/00

CPC分类号： G06F17/30828 ,  G06F17/30867 ,  H04N21/44218 ,  H04N21/44222 ,  Y10S707/99942 ,  Y10S707/99943 ,  Y10S707/99944 ,  Y10S707/99945

摘要： A content maintenance system uses a time-dependent precipitation function for iteratively augmenting or removing content over time, after an initial demonstration of user interest. A plurality of parallel precipitation processes can be launched simultaneously in response to different facets of a user expression of interest. Precipitation is dependent on highlighting or extracting segment descriptors from content of interest to the user. Then segments are filtered, rated, annotated and/or prioritized from that content. The remaining segments are matched against stored search structures. When the segments match, they are precipitated out for storage and can generate new search structures.

摘要翻译： 在用户感兴趣的初步演示之后，内容维护系统使用时间依赖的降水函数来迭代地增加或移除内容。 响应于感兴趣的用户表达的不同方面，可以同时启动多个并行降水过程。 降水取决于从用户感兴趣的内容中突出显示或提取片段描述符。 然后，细分受到过滤，评分，注释和/或从内容中排列。 剩余的段与存储的搜索结构匹配。 当段匹配时，它们被沉淀出来用于存储，并且可以生成新的搜索结构。

公开(公告)号：US06754389B1

公开(公告)日：2004-06-22

申请号：US09452581

申请日：1999-12-01

申请人： Nevenka Dimitrova ,  Lalitha Agnihotri ,  Gang Wei

发明人： Nevenka Dimitrova ,  Lalitha Agnihotri ,  Gang Wei

IPC分类号： G06K962

CPC分类号： G06K9/00228 ,  G06F17/30256 ,  G06K2009/3291

摘要： A content-based classification system is provided that detects the presence of object images within a frame and determines the path, or trajectory, of each object image through multiple frames of a video segment. In a preferred embodiment, face objects and text objects are used for identifying distinguishing object trajectories. A combination of face, text, and other trajectory information is used in a preferred embodiment of this invention to classify each segment of a video sequence. In one embodiment, a hierarchical information structure is utilized to enhance the classification process. At the upper, video, information layer, the parameters used for the classification process include, for example, the number of object trajectories of each type within the segment, an average duration for each object type trajectory, and so on. At the lowest, model, information layer, the parameters include, for example, the type, color, and size of the object image corresponding to each object trajectory. In an alternative embodiment, a Hidden Markov Model (HMM) technique is used to classify each segment into one of a predefined set of classifications, based on the observed characterization of the object trajectories contained within the segment.

摘要翻译： 提供了基于内容的分类系统，其检测帧内的对象图像的存在，并且通过视频段的多个帧来确定每个对象图像的路径或轨迹。 在优选实施例中，脸部对象和文本对象被用于识别区分对象轨迹。 在本发明的优选实施例中使用面部，文本和其他轨迹信息的组合来对视频序列的每个片段进行分类。 在一个实施例中，利用分层信息结构来增强分类过程。 在上部，视频信息层，用于分类处理的参数包括例如段内每种类型的对象轨迹数，每个对象类型轨迹的平均持续时间等。 在最低的模型信息层，参数包括例如对应于每个对象轨迹的对象图像的类型，颜色和尺寸。 在替代实施例中，基于观察到的包含在段内的对象轨迹的特征，使用隐马尔可夫模型（HMM）技术将每个段分类为预定义的一组分类。

公开(公告)号：US06731788B1

公开(公告)日：2004-05-04

申请号：US09441949

申请日：1999-11-17

申请人： Lalitha Agnihotri ,  Nevenka Dimitrova

发明人： Lalitha Agnihotri ,  Nevenka Dimitrova

IPC分类号： G06K962

CPC分类号： G11B27/28 ,  G06F17/30796 ,  G06K9/3266 ,  G06K2209/01 ,  G11B27/034 ,  G11B27/105

摘要： An image processing device and method for classifying symbols, such as text, in a video stream employs a back propagation neural network (BPNN) whose feature space is derived from size, translation, and rotation invariant shape-dependent features. Various example feature spaces are discussed such as regular and invariant moments and an angle histogram derived from a Delaunay triangulation of a thinned, thresholded, symbol. Such feature spaces provide a good match to BPNN as a classifier because of the poor resolution of characters in video streams.

摘要翻译： 用于在视频流中对诸如文本之类的符号进行分类的图像处理设备和方法使用其特征空间从尺寸，平移和旋转不变形状相关特征导出的反向传播神经网络（BPNN）。 讨论了各种示例特征空间，例如常规和不变矩，以及从稀疏，阈值符号的Delaunay三角测量得到的角度直方图。 由于视频流中的字符分辨率差，这样的特征空间提供了与BPNN作为分类器的良好匹配。