利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

20 条记录 (耗时 0.021 秒)

    RETRIEVING RADIOLOGICAL STUDIES USING AN IMAGE-BASED QUERY
    1.
    发明申请
    RETRIEVING RADIOLOGICAL STUDIES USING AN IMAGE-BASED QUERY 审中-公开
    使用基于图像的查询检索放射学研究

    公开(公告)号：US20120191720A1

    公开(公告)日：2012-07-26

    申请号：US13499424

    申请日：2010-09-17

    申请人： Merlijn Sevenster ,  Yuechen Qian ,  Robbert Christiaan Van Ommering ,  Reinhard Kneser ,  Dieter Geller

    发明人： Merlijn Sevenster ,  Yuechen Qian ,  Robbert Christiaan Van Ommering ,  Reinhard Kneser ,  Dieter Geller

    IPC分类号： G06F17/30

    CPC分类号： G06F19/321

    摘要： The invention relates to a system (100) for identifying a document of a plurality of documents, based on a multidimensional image, the system (100) comprising an object unit (110) for identifying an object represented in the multidimensional image, based on a user input indicating a region of the multidimensional image, and further based on a model for modeling the object, determined by segmentation of the indicated region of the multidimensional image; a keyword unit (120) for identifying a keyword of a plurality of keywords, related to the identified object, based on an annotation of the model for modeling the object; and a document unit (130) for identifying the document of the plurality of documents, based on the identified keyword. Thus, the system advantageously facilitates a user's access to documents comprising information of interest based on a viewed multidimensional image. The document may be identified by its name or, preferably, by a link to the document. By following the link, the system may be further adapted to allow the user to retrieve the document stored in a storage comprising the plurality of documents, e.g. download a file comprising the document, and view the document on a display.

    摘要翻译： 本发明涉及一种用于基于多维图像来识别多个文档的文档的系统（100），所述系统（100）包括用于基于多维图像识别所述多​​维图像中表示的对象的对象单元（110） 用户输入指示多维图像的区域，并且还基于通过多维图像的指示区域的分割确定的用于建模对象的模型; 用于基于用于建模对象的模型的注释来识别与所识别的对象相关的多个关键字的关键字的关键词单元（120）; 以及用于基于所识别的关键字来识别所述多​​个文档的文档的文档单元（130）。 因此，该系统有利地促进用户基于所观看的多维图像来访问包括感兴趣的信息的文档。 该文件可以由其名称或优选地通过文档的链接来标识。 通过跟随链接，系统可以进一步适于允许用户检索存储在包括多个文档的存储器中的文档，例如， 下载包含文档的文件，并在显示器上查看文档。

    Image classification based on image segmentation
    2.
    发明授权
    Image classification based on image segmentation 有权
    基于图像分割的图像分类

    公开(公告)号：US09042629B2

    公开(公告)日：2015-05-26

    申请号：US12992190

    申请日：2009-05-08

    申请人： Yuechen Qian ,  Dieter Geller ,  Reinhard Kneser ,  Merlijn Sevenster ,  Robbert C. Van Ommering ,  Paola K. Tulipano

    发明人： Yuechen Qian ,  Dieter Geller ,  Reinhard Kneser ,  Merlijn Sevenster ,  Robbert C. Van Ommering ,  Paola K. Tulipano

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06T7/00

    CPC分类号： G06K9/6267 ,  G06K2209/05 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/149 ,  G06T2207/10072 ,  G06T2207/30041

    摘要： The invention relates to a system (100) for classifying image data on the basis of a model for adapting to an object in the image data, the system comprising a segmentation unit (110) for segmenting the image data by adapting the model to the object in the image data and a classification unit (120) for assigning a class to the image data on the basis of the model adapted to the object in the image data, thereby classifying the image data, wherein the classification unit (120) comprises an attribute unit (122) for computing a value of an attribute of the model on the basis of the model adapted to the object in the image data, and wherein the assigned class is based on the computed value of the attribute. Thus, the system (100) of the invention is capable of classifying the image data without any user input. All inputs required for classifying the image data 10 constitute a model for adapting to an object in the image data. A person skilled in the art will understand however that in some embodiments of the system (100), a limited number of user inputs may be enabled to let the user influence and control the system and the classification process.

    摘要翻译： 本发明涉及一种用于基于用于适应图像数据中的对象的模型对图像数据进行分类的系统（100），该系统包括分割单元（110），用于通过将模型适配到对象来分割图像数据 在所述图像数据中，以及分类单元（120），用于基于所述图像数据中适合于所述对象的模型，将类别分配给所述图像数据，从而对所述图像数据进行分类，其中所述分类单元（120）包括属性 单元（122），用于基于适于图像数据中的对象的模型来计算模型的属性的值，并且其中所分配的类基于所计算的属性值。 因此，本发明的系统（100）能够对没有任何用户输入的图像数据进行分类。 分类图像数据10所需的所有输入构成用于适应图像数据中的对象的模型。 然而，本领域技术人员将理解，在系统（100）的一些实施例中，可以使有限数量的用户输入能够使用户影响和控制系统和分类过程。

    IMAGE CLASSIFICATION BASED ON IMAGE SEGMENTATION
    3.
    发明申请
    IMAGE CLASSIFICATION BASED ON IMAGE SEGMENTATION 有权
    基于图像分割的图像分类

    公开(公告)号：US20110222747A1

    公开(公告)日：2011-09-15

    申请号：US12992190

    申请日：2009-05-08

    申请人： Yuechen Qian ,  Dieter Geller ,  Reinhard Kneser ,  Merlijn Sevenster ,  Robbert C. Van Ommering ,  Paola K. Tulipano

    发明人： Yuechen Qian ,  Dieter Geller ,  Reinhard Kneser ,  Merlijn Sevenster ,  Robbert C. Van Ommering ,  Paola K. Tulipano

    IPC分类号： G06K9/00

    CPC分类号： G06K9/6267 ,  G06K2209/05 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/149 ,  G06T2207/10072 ,  G06T2207/30041

    摘要： The invention relates to a system (100) for classifying image data on the basis of a model for adapting to an object in the image data, the system comprising a segmentation unit (110) for segmenting the image data by adapting the model to the object in the image data and a classification unit (120) for assigning a class to the image data on the basis of the model adapted to the object in the image data, thereby classifying the image data, wherein the classification unit (120) comprises an attribute unit (122) for computing a value of an attribute of the model on the basis of the model adapted to the object in the image data, and wherein the assigned class is based on the computed value of the attribute. Thus, the system (100) of the invention is capable of classifying the image data without any user input. All inputs required for classifying the image data 10 constitute a model for adapting to an object in the image data. A person skilled in the art will understand however that in some embodiments of the system (100), a limited number of user inputs may be enabled to let the user influence and control the system and the classification process.

    摘要翻译： 本发明涉及一种用于基于用于适应图像数据中的对象的模型对图像数据进行分类的系统（100），所述系统包括分割单元（110），用于通过将模型适配到对象来分割图像数据 在所述图像数据中，以及分类单元（120），用于基于所述图像数据中适合于所述对象的模型，将类别分配给所述图像数据，从而对所述图像数据进行分类，其中所述分类单元（120）包括属性 单元（122），用于基于适于图像数据中的对象的模型来计算模型的属性的值，并且其中所分配的类基于所计算的属性值。 因此，本发明的系统（100）能够对没有任何用户输入的图像数据进行分类。 分类图像数据10所需的所有输入构成用于适应图像数据中的对象的模型。 然而，本领域技术人员将理解，在系统（100）的一些实施例中，可以使有限数量的用户输入能够使用户影响和控制系统和分类过程。

    Retrieving and viewing medical images
    4.
    发明授权
    Retrieving and viewing medical images 有权
    检索和查看医学图像

    公开(公告)号：US09390236B2

    公开(公告)日：2016-07-12

    申请号：US13320956

    申请日：2010-05-17

    申请人： Dieter Geller ,  Reinhard Kneser ,  Yuechen Qian

    发明人： Dieter Geller ,  Reinhard Kneser ,  Yuechen Qian

    IPC分类号： G06F17/30 ,  G06F19/00

    CPC分类号： G06F19/3487 ,  G06F19/00 ,  G06F19/321 ,  G06F19/324 ,  G16H15/00

    摘要： As medical imaging becomes more affordable, and the diversity of diagnostic modalities and therapeutic treatments increase, the amount of data being stored increases, and the problem becomes even more critical. One approach to improve retrieval efficiency of images is to employ semantics to establish a defined set of search and classification terms. However, such semantic systems still require the user to make a selection of the most appropriate term or terms to classify a report or image, and the accuracy of the results are thus dependent on the skill and knowledge of the classifier. According to a first aspect of the invention, a retriever is provided for retrieving a medical image having a searchable attribute, the retriever being configured to interface with a semantic database and an image database, and wherein the searchable attribute is determined by segmenting the medical image, using the anatomical model.

    摘要翻译： 随着医学成像变得更加实惠，并且诊断模式和治疗方法的多样性增加，存储的数据量增加，并且问题变得更加重要。 提高图像检索效率的一种方法是采用语义来建立一组定义的搜索和分类术语。 然而，这样的语义系统仍然需要用户选择最合适的术语或术语来分类报告或图像，并且结果的准确性因此取决于分类器的技能和知识。 根据本发明的第一方面，提供了一种用于检索具有可搜索属性的医学图像的检索器，所述检索器被配置为与语义数据库和图像数据库进行接口，并且其中通过分割医学图像来确定可搜索属性 ，使用解剖模型。

    RETRIEVING AND VIEWING MEDICAL IMAGES
    7.
    发明申请
    RETRIEVING AND VIEWING MEDICAL IMAGES 有权
    检索和查看医学图像

    公开(公告)号：US20120066241A1

    公开(公告)日：2012-03-15

    申请号：US13320956

    申请日：2010-05-17

    申请人： Dieter Geller ,  Reinhard Kneser ,  Yuechen Qian

    发明人： Dieter Geller ,  Reinhard Kneser ,  Yuechen Qian

    IPC分类号： G06F17/30

    CPC分类号： G06F19/3487 ,  G06F19/00 ,  G06F19/321 ,  G06F19/324 ,  G16H15/00

    摘要： As medical imaging becomes more affordable, and the diversity of diagnostic modalities and therapeutic treatments increase, the amount of data being stored increases, and the problem becomes even more critical. One approach to improve retrieval efficiency of images is to employ semantics to establish a defined set of search and classification terms. However, such semantic systems still require the user to make a selection of the most appropriate term or terms to classify a report or image, and the accuracy of the results are thus dependent on the skill and knowledge of the classifier. According to a first aspect of the invention, a retriever is provided for retrieving a medical image having a searchable attribute, the retriever being configured to interface with a semantic database and an image database, and wherein the searchable attribute is determined by segmenting the medical image, using the anatomical model.

    摘要翻译： 随着医学成像变得更加实惠，并且诊断模式和治疗方法的多样性增加，存储的数据量增加，并且问题变得更加重要。 提高图像检索效率的一种方法是采用语义来建立一组定义的搜索和分类术语。 然而，这样的语义系统仍然需要用户选择最合适的术语或术语来分类报告或图像，并且结果的准确性因此取决于分类器的技能和知识。 根据本发明的第一方面，提供了一种用于检索具有可搜索属性的医学图像的检索器，所述检索器被配置为与语义数据库和图像数据库进行接口，并且其中通过分割医学图像来确定可搜索属性 ，使用解剖模型。

    Face Annotation In Streaming Video
    9.
    发明申请
    Face Annotation In Streaming Video 审中-公开
    流媒体视频中的脸部注释

    公开(公告)号：US20080235724A1

    公开(公告)日：2008-09-25

    申请号：US12088001

    申请日：2006-09-19

    申请人： Frank Sassenscheidt ,  Christian Benien ,  Reinhard Kneser

    发明人： Frank Sassenscheidt ,  Christian Benien ,  Reinhard Kneser

    IPC分类号： H04N9/81

    CPC分类号： G06F16/784

    摘要： The invention relates to a system (5, 15) and a method for detecting and annotating faces on-the-fly in video data. The annotation (29) is performed by modifying the pixel content of the video and is thereby independent of file types, protocols and standards. The invention can also perform real-time face-recognition by comparing detected faces with known faces from storage, so that the annotation can contain personal information (38) relating to the face. The invention can be applied at either end of a transmission channel and is particularly applicable in videoconferences, Internet classrooms, etc.

    摘要翻译： 本发明涉及一种用于在视频数据中动态检测和注释面部的系统（5,15）和方法。 通过修改视频的像素内容来执行注释（29），由此独立于文件类型，协议和标准。 本发明还可以通过将检测到的面部与存储器中的已知面部进行比较来执行实时面部识别，使得注释可以包含与脸部有关的个人信息（38）。 本发明可应用于传输通道的任一端，特别适用于视频会议，互联网教室等。

    Single-count backing-off method of determining N-gram language model values
    10.
    发明授权
    Single-count backing-off method of determining N-gram language model values 失效
    确定N-gram语言模型值的单次备份方法

    公开(公告)号：US5745876A

    公开(公告)日：1998-04-28

    申请号：US642012

    申请日：1996-05-02

    申请人： Reinhard Kneser ,  Hermann Ney

    发明人： Reinhard Kneser ,  Hermann Ney

    IPC分类号： G10L15/197 ,  G10L5/06

    CPC分类号： G10L15/197

    摘要： For the recognition of coherently spoken speech with a large vocabulary, language model values which take into account the probability of word sequences are considered at word transitions. Prior to the recognition, these language model values are derived on the basis of training speech signals. If the amount of training data is kept within sensible limits, not all word sequences will actually occur, so that the language model values for, for example an N-gram language model must be determined from word sequences of N-1 words actually occurring. In accordance with the invention, these reduced word sequences from each different, complete word sequence are counted only once, irrespective of the actual frequency of occurrence of the complete word sequence or only reduced training sequences which occur exactly once in the training data are taken into account.

    摘要翻译： 为了识别具有较大词汇量的相干语音，考虑到字序列的概率的语言模型值在词转换中被考虑。 在识别之前，这些语言模型值是基于训练语音信号导出的。 如果训练数据的数量保持在明显的限度内，并不是所有的字序列实际上都会发生，因此，例如N-gram语言模型的语言模型值必须从实际出现的N-1个字的单词序列中确定。 根据本发明，来自每个不同的完整字序列的这些缩减的字序列仅被计数一次，而不考虑完整字序列的实际发生频率，或者仅将训练数据中正好出现一次的训练序列减少 帐户。