公开(公告)号：WO0007367A3

公开(公告)日：2000-03-23

申请号：PCT/IB9901206

申请日：1999-06-28

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS SVENSKA AB

Inventor： DIMITROVA NEVENKA ,  MCGEE THOMAS ,  ELENBAAS JAN H ,  LEYVI EUGENE ,  RAMSEY CAROLYN ,  BERKOWITZ DAVID

IPC: H04N5/91 ,  G11B27/10 ,  G11B27/28 ,  H04H1/00 ,  H04H60/59 ,  H04N5/14 ,  H04N5/782 ,  H04N17/00 ,  H04N5/76

CPC classification number: H04N5/782 ,  G06F17/30814 ,  G06F17/30825 ,  G11B27/107 ,  G11B27/28 ,  G11B2220/90 ,  H04H20/10 ,  H04H60/375 ,  H04H60/59 ,  H04N5/147 ,  H04N21/4325 ,  H04N21/4334 ,  H04N21/44008 ,  H04N21/812 ,  Y10S358/908

Abstract: A commercial detection apparatus includes a frame grab thread which acquires frames from an input data stream to be analyzed by a cut detector thread and a filter thread. A commercial detection thread determines whether a commercial has occurred from data created by the cut detector thread and the filter thread stored in a memory. A factor used by the commercial detection thread is whether a black frame has occurred. The input data stream is divided into a plurality of regions and then a maximum and minimum value for a section of these regions is determined and compared to one another. If the maximum and minimum values are close enough, and the maximum value is below a threshold, then the frame is deemed to be black. The commercial detection thread also looks at the average cut frame distance, cut rate, changes in the average cut frame distance, the absence of a logo, a commercial signature detection, brand name detection, a series of black frames preceding a high cut rate, similar frames located within a specified period of time before a frame being analyzed and character detection. During playback, the detected commercials are either skipped or substituted with alternate content.

Abstract translation: 一种商业检测设备包括帧抓取线程，该帧抓取线程从将要由切断检测器线程和过滤器线程分析的输入数据流获取帧。 商业检测线程确定是否由切割检测器线程创建的数据和存储器中存储的过滤器线程产生商业广告。 商业检测线程使用的一个因素是黑帧是否已经发生。 输入数据流被分成多个区域，然后确定这些区域的一部分的最大值和最小值并相互比较。 如果最大值和最小值足够接近，并且最大值低于阈值，则该帧被认为是黑色的。 商业检测线程还查看平均切割帧距离，切割速率，平均切割帧距离的变化，没有标志，商业签名检测，品牌名称检测，高切割率之前的一系列黑色帧， 位于帧被分析和字符检测之前的特定时间段内的相似帧。 在播放过程中，检测到的广告片段会被跳过或替换为替代内容。

公开(公告)号：WO9855942A2

公开(公告)日：1998-12-10

申请号：PCT/IB9800793

申请日：1998-05-25

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS SVENSKA AB

Inventor： DIMITROVA NEVENKA ,  MCGEE THOMAS ,  ELENBAAS JAN

IPC: H04N5/76 ,  G06F17/30 ,  G11B27/10 ,  G11B27/11 ,  G11B27/28 ,  G11B27/30 ,  G11B27/32 ,  H04N5/14 ,  H04N7/26

CPC classification number: G06F17/30843 ,  G06F17/30814 ,  G06F17/30852 ,  G11B27/102 ,  G11B27/11 ,  G11B27/28 ,  G11B27/3027 ,  G11B27/326 ,  G11B2220/2562 ,  G11B2220/65 ,  G11B2220/90 ,  H04N5/147 ,  H04N19/48 ,  H04N19/90

Abstract: A video indexing system analyzes contents of source video and develops a visual table of contents using selected images. The source video is analyzed to detect video cuts from one scene to another, and static scenes. Keyframes are selected for each significant scene. A keyframe filtering process filters out less desired frames including, for example, unicolor frames, or those frames having a same object as a primary focus or one of the primary focuses. A visual index is created from those frames remaining after the keyframe filtering and stored for retrieval. The visual index may be retrieved by a user who may then display the visual index on a display. The user may select one of the frames displayed in the visual index and the source video may be manually (by the user) or automatically advanced to that frame of the source video. Additionally, a user may print the visual index.

Abstract translation: 视频索引系统分析源视频的内容，并使用选定的图像开发视觉目录。 源视频被分析以检测从一个场景到另一个场景的视频剪辑以及静态场景。 为每个重要场景选择关键帧。 关键帧滤波处理过滤掉不太期望的帧，包括例如单色帧，或具有与主要焦点相同的对象或主要焦点的那些帧。 从关键帧过滤之后剩余的帧创建视觉索引，并存储以供检索。 视觉索引可以由用户检索，然后用户可以在显示器上显示视觉索引。 用户可以选择在视觉索引中显示的帧中的一个，并且源视频可以是手动的（由用户）或自动前进到源视频的帧。 另外，用户可以打印视觉索引。

公开(公告)号：WO9936863A3

公开(公告)日：1999-10-14

申请号：PCT/IB9900033

申请日：1999-01-13

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS SVENSKA AB

Inventor： DIMITROVA NEVENKA

IPC: G06F17/30 ,  G10L15/00 ,  G11B27/22 ,  G11B27/28 ,  H04N5/76

CPC classification number: G06K9/00711 ,  G06F17/30787 ,  G06F17/30796 ,  G11B27/22 ,  G11B27/28 ,  G11B2220/216 ,  G11B2220/2516 ,  G11B2220/2545 ,  G11B2220/2562 ,  G11B2220/455 ,  G11B2220/90 ,  Y10S707/914 ,  Y10S707/99934 ,  Y10S707/99935 ,  Y10S707/99936

Abstract: Information is generated to support selective retrieval of a video sequence. This involves providing a set of models, each for recognizing a sequence of symbols. The symbols include symbols that represent key frames, audio and text properties associated with segments of the video sequence. A matching model is selected, which allows recognition of a sequence of symbols that are coupled to successive segments of the video sequence so that the key frame and audio and/or text properties satisfy the selected matching model. A reference to the matching model is used as a selection criterion for retrieving the video sequence. Optionally, a new model is constructed when no matching model for the video sequence is present in the set of models. The new model is constructed so that it allows recognition of the symbols of the video sequence. The new model is then used as selection criterion for retrieving the video sequence.

Abstract translation: 产生信息以支持视频序列的选择性检索。 这涉及提供一组模型，每个模型用于识别符号序列。 符号包括表示与视频序列的段相关联的关键帧，音频和文本属性的符号。 选择匹配模型，其允许识别耦合到视频序列的连续片段的符号序列，使得关键帧和音频和/或文本属性满足所选择的匹配模型。 对匹配模型的引用被用作检索视频序列的选择标准。 可选地，当在该组模型中不存在用于视频序列的匹配模型时，构建新模型。 新的模型被构造成允许识别视频序列的符号。 然后将新模型用作检索视频序列的选择标准。

公开(公告)号：WO9855943A3

公开(公告)日：1999-04-15

申请号：PCT/IB9800795

申请日：1998-05-25

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS SVENSKA AB

Inventor： DIMITROVA NEVENKA ,  MCGEE THOMAS ,  ELENBAAS JAN

IPC: H04N5/76 ,  G06F17/30 ,  H04N7/26 ,  H04N21/458 ,  H04N21/81 ,  H04N5/14

CPC classification number: G06K9/00711 ,  G06F17/30802 ,  G06F17/30814 ,  G06F17/30858 ,  H04N19/179 ,  H04N19/87 ,  H04N21/458 ,  H04N21/812

Abstract: A video indexing system analyzes contents of source video and develops a visual table of contents using selected images. A system for detecting significant scenes detects video cuts from one scene to another, and static scenes based on DCT coefficients and macroblocks. A keyframe filtering process filters out less desired frames including, for example, unicolor frames, or those frames having a same object as a primary focus or one primary focuses. Commercials may also be detected and frames of commercials eliminated.

Abstract translation: 视频索引系统分析源视频的内容，并使用选定的图像开发视觉目录。 用于检测重要场景的系统检测从一个场景到另一个场景的视频剪辑，以及基于DCT系数和宏块的静态场景。 关键帧过滤过滤过滤出不太期望的帧，包括例如单色帧，或者具有与主要焦点相同的对象的帧或一个主要焦点。 也可以检测商业广告，消除商业广告。

公开(公告)号：WO9928835A3

公开(公告)日：1999-08-26

申请号：PCT/IB9801909

申请日：1998-11-30

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS SVENSKA AB

Inventor： ELENBAAS HERMAN ,  DIMITROVA NEVENKA

IPC: G06F17/30 ,  H04N5/76 ,  H04N5/91

CPC classification number: G06F17/30852 ,  G06F17/30858 ,  Y10S707/99943 ,  Y10S707/99945

Abstract: Keyframes extracted from a video or blobs (binary large objects) extracted from a multimedia or hypermedia document, are stored so as to optimize retrieval from a relatively slow memory device. Retrieval and storage may be based on significant or representative images in the video or on user preferences on information, including text, audio, video and hyperlinks to other documents, from a multimedia document. Elimination of redundant information is also possible.

Abstract translation: 存储从多媒体或超媒体文档中提取的视频或Blob（二进制大对象）提取的关键帧，以优化从相对较慢的存储器设备的检索。 检索和存储可以基于视频中的重要的或代表性的图像，或者来自多媒体文档的关于信息的用户偏好，包括文本，音频，视频和到其他文档的超链接。 消除冗余信息也是可能的。

公开(公告)号：WO2010055487A3

公开(公告)日：2010-09-30

申请号：PCT/IB2009055057

申请日：2009-11-13

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  WU YING ,  ZHU HONGGUANG ,  LI JIAN ,  XU LIANG ,  VERHAEGH WILHELMUS F J ,  REN YIPING ,  JANEVSKI ANGEL ,  VARADAN VINAY ,  LI ZHAOYONG ,  DIMITROVA NEVENKA

Inventor： WU YING ,  ZHU HONGGUANG ,  LI JIAN ,  XU LIANG ,  VERHAEGH WILHELMUS F J ,  REN YIPING ,  JANEVSKI ANGEL ,  VARADAN VINAY ,  LI ZHAOYONG ,  DIMITROVA NEVENKA

IPC: C12Q1/68

CPC classification number: C12N15/111 ,  C12N2310/141 ,  C12N2320/10 ,  C12N2330/10 ,  C12N2330/31 ,  C12Q1/6816 ,  C12Q1/6886 ,  C12Q2600/158 ,  C12Q2600/178

Abstract: The present invention relates compositions and methods for microRNA (miRNA) expression profiling of colorectal cancer. In particular, the invention relates to a diagnostic kit of molecular markers for identifying one or more mammalian target cells exhibiting or having a predisposition to develop colorectal cancer, the kit comprising a plurality of nucleic acid molecules, each nucleic acid molecule encoding a miRNA sequence, wherein one or more of the plurality of nucleic acid molecules are differentially expressed in the target cells and in one or more control cells, and wherein the one or more differentially expressed nucleic acid molecules together represent a nucleic acid expression signature that is indicative for the presence of or the predisposition to develop colorectal cancer. The invention further relates to corresponding methods using such nucleic acid expression signatures for identifying one or more mammalian target cells exhibiting or having a predisposition to develop colorectal cancer as well as for preventing or treating such a condition. Finally, the invention is directed to a pharmaceutical composition for the prevention and/or treatment of colorectal cancer.

Abstract translation: 本发明涉及用于结直肠癌的微RNA（miRNA）表达谱分析的组合物和方法。 具体而言，本发明涉及分子标记的诊断试剂盒，用于鉴定展现或具有发展结肠直肠癌倾向的一种或多种哺乳动物靶细胞，所述试剂盒包含多个核酸分子，每个核酸分子编码miRNA序列， 其中所述多种核酸分子中的一种或多种在所述靶细胞和一种或多种对照细胞中差异表达，并且其中所述一种或多种差异表达的核酸分子一起表示核酸表达签名， 或发展大肠癌的倾向。 本发明进一步涉及使用此类核酸表达签名鉴定一种或多种哺乳动物靶细胞的相应方法，所述一种或多种哺乳动物靶细胞展现或具有发展结肠直肠癌的倾向以及用于预防或治疗这样的状况。 最后，本发明涉及用于预防和/或治疗结肠直肠癌的药物组合物。

公开(公告)号：WO2007029204A3

公开(公告)日：2007-09-13

申请号：PCT/IB2006053174

申请日：2006-09-08

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  AGNIHOTRI LALITHA ,  DIMITROVA NEVENKA ,  BARBIERI MAURO

Inventor： AGNIHOTRI LALITHA ,  DIMITROVA NEVENKA ,  BARBIERI MAURO

IPC: G06F17/30

CPC classification number: G06F17/30905 ,  G06F17/30867

Abstract: A method, a device and a system for providing a search result in response to a user request. The method includes the steps of entering one or more keywords to a search engine. The search engine may be an Internet search engine or a local search facility to search on a local hard disc. At least one information link is received in response to the search, e.g. a website homepage or a directory on a hard disc. The method includes scanning through documents arranged in connection with the information link in order to find documents that are relevant with respect to the user request. The documents arranged in connection with the information link may be scanned through using a width-before-depth or depth-before-width strategy or a combination thereof. A path is generated through the documents that are found relevant, and a video presentation based on this path through the documents is finally generated. Preferably, the video presentation includes a video part as well as an audio part. In preferred embodiments, selected parts of text documents are translated into a synthesized voice signal before included into the video presentation. As a result, a user can enjoy a video show of the search result in a lean-back mode, e.g. on a TV set, instead of clicking through all parts of an Internet website in order to find relevant documents. A device with user input means, network connecting means and processing means adapted to perform the mentioned method may be formed by a computer, a video recorder, a hard disc recorder, a video camera or a digital TV set.

Abstract translation: 一种用于响应于用户请求提供搜索结果的方法，设备和系统。 该方法包括将一个或多个关键字输入到搜索引擎的步骤。 搜索引擎可以是互联网搜索引擎或本地搜索工具以在本地硬盘上进行搜索。 响应于搜索接收至少一个信息链接，例如， 网站主页或硬盘上的目录。 该方法包括扫描与信息链接有关的文档，以便找到与用户请求相关的文档。 可以使用宽度之前的宽度或宽度之前的深度策略或其组合来扫描与信息链接相关地布置的文档。 通过找到相关的文档生成路径，并最终生成基于该路径通过文档的视频演示文稿。 优选地，视频呈现包括视频部分以及音频部分。 在优选实施例中，文本文档的选定部分在被包括到视频呈现之前被翻译成合成语音信号。 结果，用户可以在后退模式下欣赏搜索结果的视频节目，例如， 在电视机上，而不是点击互联网网站的所有部分以找到相关文件。 具有用户输入装置，网络连接装置和适于执行所述方法的处理装置的设备可以由计算机，录像机，硬盘记录器，摄像机或数字电视机构成。

公开(公告)号：WO03054754A2

公开(公告)日：2003-07-03

申请号：PCT/IB0205246

申请日：2002-12-06

Applicant: KONINKL PHILIPS ELECTRONICS NV

Inventor： LI DONGGE ,  ZIMMERMAN JOHN ,  DIMITROVA NEVENKA

IPC: G06F17/30 ,  G06F17/60

CPC classification number: G06F17/30787 ,  G06F17/30796 ,  G06F17/30802 ,  G06F17/30811 ,  G06F17/30843 ,  G06F17/30852

Abstract: A visualization system captures and analyzes a video signal to extract features in the video signal to render a graphical multi-dimensional visual representation of the program. The visualization system includes a memory and a processor and is programmed to extract features, augment the feature extraction with supplemental information, and render a visual summary to be displayed on a display device. Using the visual summary, a user can more easily determine the nature of a particular video program.

Abstract translation: 可视化系统捕获并分析视频信号以提取视频信号中的特征以呈现节目的图形多维视觉表示。 可视化系统包括存储器和处理器，并且被编程为提取特征，利用补充信息来增强特征提取，并呈现要在显示装置上显示的视觉摘要。 使用视觉摘要，用户可以更容易地确定特定视频节目的性质。

公开(公告)号：WO03021954A2

公开(公告)日：2003-03-13

申请号：PCT/IB0203631

申请日：2002-09-03

Applicant: KONINKL PHILIPS ELECTRONICS NV

Inventor： AGNIHOTRI LALITHA A ,  DIMITROVA NEVENKA ,  MCGEE THOMAS F M

IPC: H04N5/44 ,  H04H60/48 ,  H04H60/56 ,  H04H60/65 ,  H04H60/72 ,  H04N5/76

CPC classification number: H04H60/72 ,  H04H60/48 ,  H04H60/56 ,  H04H60/65

Abstract: Advertisers want to deliver their message in a relatively short period of time. This leads to the product name, company name and other identifying features being repeated frequently during a commercial broadcast. Transcript information can be used to detect commercials by detecting frequently occurring words in the commercials. This can also be used to identify an individual commercial from other commercials. Once the individual commercials have been identified, the transcript information corresponding to each commercial can be stored in a database to identify the commercial in subsequent broadcasts, or to provide a search mechanism for searching a particular commercial in the database.

Abstract translation: 广告商希望在相对较短的时间内传递他们的信息。 这导致在商业广播期间频繁地重复的产品名称，公司名称和其他识别特征。 记录信息可以通过检测广告中的频繁出现的单词来用于检测广告。 这也可以用于从其他广告中识别单个商业广告。 一旦确定了各个商业广告，则可以将与每个商业广告相对应的抄本信息存储在数据库中以识别后续广播中的商业广告，或提供搜索数据库中的特定广告的搜索机制。

公开(公告)号：WO0172040A2

公开(公告)日：2001-09-27

申请号：PCT/EP0102759

申请日：2001-03-12

Applicant: KONINKL PHILIPS ELECTRONICS NV

Inventor： DIMITROVA NEVENKA ,  AGNIHOTRI LALITHA ,  MCGEE THOMAS F ,  MANKOVICH NICHOLAS J

IPC: H04B1/16 ,  H04N5/765 ,  H04N7/16 ,  H04N7/173 ,  H04N7/24

CPC classification number: H04N21/26603 ,  H04N7/165 ,  H04N7/17354 ,  H04N21/23424 ,  H04N21/234318 ,  H04N21/235 ,  H04N21/25883 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/4331 ,  H04N21/435 ,  H04N21/4381 ,  H04N21/4532 ,  H04N21/454 ,  H04N21/4622 ,  H04N21/4667 ,  H04N21/4722 ,  H04N21/4725 ,  H04N21/4782 ,  H04N21/64322 ,  H04N21/6582 ,  H04N21/812 ,  H04N21/858 ,  H04N21/8586

Abstract: A media display system enhances content by recognizing patterns in the media signal and modifying the media signal responsively to the recognized patterns. For example, in a television broadcast environment, the media signal could be a television program. At one instant, the television could include a logo of a car company. The system would recognize the logo and correlate it with enhanced content stored locally or by using additional input. Based on user preferences (e.g., whether the user is interested in that particular car company) and the correlated enhanced content, the system would modify the broadcast signal in appropriate way. For example, the enhanced content could be a commercial video clip or the phone number of a local car dealer. The modification to the broadcast signal could, in such a case, include overlaying the local car dealer's number on the video signal or buffering the broadcast signal and playing the commercial video clip to perform content enhancement.

Abstract translation: 媒体显示系统通过识别媒体信号中的模式和响应于识别的模式来修改媒体信号来增强内容。 例如，在电视广播环境中，媒体信号可以是电视节目。 一时，电视机可以包括汽车公司的标志。 系统将识别标识并将其与本地存储的增强内容或通过使用附加输入进行关联。 基于用户偏好（例如，用户是否对该特定汽车公司感兴趣）和相关的增强内容，系统将以适当的方式修改广播信号。 例如，增强内容可以是商业视频剪辑或本地汽车经销商的电话号码。 在这种情况下，对广播信号的修改可以包括在视频信号上覆盖本地汽车经销商的号码或缓冲广播信号并播放商业视频剪辑以执行内容增强。