公开(公告)号：DE602004015491D1

公开(公告)日：2008-09-11

申请号：DE602004015491

申请日：2004-10-13

Applicant: PHILIPS INTELLECTUAL PROPERTY

Inventor： PETERS JOCHEN

IPC: G10L15/26 ,  G10L15/22

Abstract: The invention relates to a method, an apparatus, a Graphical User Interface and a computer program product for transforming speech to text. In a speech recognition step (100) a text is provided to which an automatic text modification based on text modification rules is applied (102). Text portions to which the modification applies, are highlighted in the text (106) and at least one suggestion for the modification is displayed to a user (110), being enabled to select one of the suggestions and therefore having control over the automatic text modification process (112). For example the rules identify text portions relating to ambiguous speech or missing text formatting characters that might have been misinterpreted in the speech recognition step.

公开(公告)号：DE50204352D1

公开(公告)日：2005-11-03

申请号：DE50204352

申请日：2002-02-08

Applicant: PHILIPS INTELLECTUAL PROPERTY

Inventor： PETERS JOCHEN

IPC: G10L15/183 ,  G10L15/197 ,  G10L15/18

Abstract: The desired orthogonalized boundary value malphaortho is calculated by linear combination of the desired boundary value malpha with the desired boundary value mbeta from the attributes beta which has a higher range than attribute alpha. Independent claims are also included for: (a) a speech recognition system (b) a training device.

公开(公告)号：DE59911187D1

公开(公告)日：2005-01-05

申请号：DE59911187

申请日：1999-11-02

Applicant: PHILIPS INTELLECTUAL PROPERTY ,  KONINKL PHILIPS ELECTRONICS NV

Inventor： PETERS JOCHEN ,  MEINHARD ULRICH

IPC: G10L15/28 ,  G10L15/22

公开(公告)号：WO2011070464A2

公开(公告)日：2011-06-16

申请号：PCT/IB2010055246

申请日：2010-11-17

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS INTELLECTUAL PROPERTY ,  ZAGORCHEV LYUBOMIR GEORGIEV ,  MOORE ELIZABETH ANNE ,  GARLINGHOUSE MATTHEW A ,  ROTH ROBERT M ,  MCALLISTER THOMAS W ,  KNESER REINHARD ,  GELLER DIETER ,  PETERS JOCHEN ,  WEESE JUERGEN ,  QIAN YUECHEN ,  DARTMOUTH COLLEGE

Inventor： ZAGORCHEV LYUBOMIR GEORGIEV ,  MOORE ELIZABETH ANNE ,  GARLINGHOUSE MATTHEW A ,  ROTH ROBERT M ,  MCALLISTER THOMAS W ,  KNESER REINHARD ,  GELLER DIETER ,  PETERS JOCHEN ,  WEESE JUERGEN ,  QIAN YUECHEN

IPC: G06T7/00

CPC classification number: G06T7/0089 ,  G06T7/0012 ,  G06T7/149 ,  G06T2200/24 ,  G06T2207/10081 ,  G06T2207/30016

Abstract: A system and method for automatic segmentation, performed by selecting a deformable model of an anatomical structure of interest imaged in a volumetric image, the deformable model formed of a plurality of polygons including vertices and edges, displaying the deformable model on a display, detecting a feature point of the anatomical structure of interest corresponding to each of the plurality of polygons and adapting the deformable model by moving each of the vertices toward the corresponding feature points until the deformable model morphs to a boundary of the anatomical structure of interest, forming a segmentation of the anatomical structure of interest.

Abstract translation: 一种用于自动分割的系统和方法，通过选择在体积图像中成像的感兴趣的解剖结构的可变形模型来执行，所述可变形模型由包括顶点和边缘的多个多边形形成，在显示器上显示可变形模型， 对应于多个多边形中的每一个的感兴趣的解剖结构的特征点，并且通过将每个顶点移向对应的特征点来适应可变形模型，直到可变形模型变形为感兴趣的解剖结构的边界，形成分割 的感兴趣的解剖结构。

公开(公告)号：WO2005050621A3

公开(公告)日：2005-10-27

申请号：PCT/IB2004052403

申请日：2004-11-12

Applicant: PHILIPS INTELLECTUAL PROPERTY ,  KONINKL PHILIPS ELECTRONICS NV ,  PETERS JOCHEN ,  MATUSOV EVGENY ,  MEYER CARSTEN ,  KLAKOW DIETRICH

Inventor： PETERS JOCHEN ,  MATUSOV EVGENY ,  MEYER CARSTEN ,  KLAKOW DIETRICH

IPC: G06F17/21 ,  G06F17/27 ,  G10L15/183 ,  G10L15/22 ,  G10L15/32 ,  G10L15/18

CPC classification number: G10L15/183 ,  G06F17/211 ,  G06F17/2715 ,  G10L15/32

Abstract: The present invention relates to a method, a computer system and a computer program product for speech recognition and/or text formatting by making use of topic specific statistical models. A text document which may be obtained from a first speech recognition pass is subject to segmentation and to an assignment of topic specific models for each obtained section. Each model of the set of models provides statistic information about language model probabilities, about text processing or formatting rules, as e.g. the interpretation of commands for punctuation, formatting, text highlighting or of ambiguous text portions requiring specific formatting, as well as a specific vocabulary being characteristic for each section of the recognized text. Furthermore, other properties of a speech recognition and/or formatting system (such as e.g. settings for the speaking rate) may be encoded in the statistical models. The models themselves are generated on the basis of annotated training data and/or by manual coding. Based on the assignment of models to sections of text an improved speech recognition and/or text formatting procedure is performed.

Abstract translation: 本发明涉及通过利用话题特定的统计模型来进行语音识别和/或文本格式化的方法，计算机系统和计算机程序产品。 可以从第一语音识别过程中获得的文本文档受到分割以及为每个获得的章节分配主题特定模型。 该组模型的每个模型提供关于语言模型概率的统计信息，例如关于文本处理或格式化规则，例如， 用于标点符号，格式化，文本突出显示或需要特定格式的模糊文本部分的命令的解释，以及针对识别文本的每个部分的特定词汇表。 此外，可以在统计模型中编码语音识别和/或格式化系统的其他属性（例如，对于讲话速率的设置）。 模型本身是基于注释的训练数据和/或手动编码生成的。 基于将模型分配给文本段，执行改进的语音识别和/或文本格式化过程。

公开(公告)号：WO2005050472A3

公开(公告)日：2006-07-20

申请号：PCT/IB2004052404

申请日：2004-11-12

Applicant: PHILIPS INTELLECTUAL PROPERTY ,  KONINKL PHILIPS ELECTRONICS NV ,  PETERS JOCHEN ,  MEYER CARSTEN ,  KLAKOW DIETRICH ,  MATUSOV EVGENY

Inventor： PETERS JOCHEN ,  MEYER CARSTEN ,  KLAKOW DIETRICH ,  MATUSOV EVGENY

IPC: G06F17/27 ,  G06F17/30

CPC classification number: G06F17/27 ,  G06F17/2765

Abstract: The invention relates to a method, a computer program product and a computer system for structuring an unstructured text by making use of statistical models trained on annotated training data. Each section of text in which the text is segmented is further assigned to a topic which is associated to a set of labels. The statistical models for the segmentation of the text and for the assignment of a topic and its associated labels to a section of text explicitly accounts for: correlations between a section of text and a topic, a topic transition between sections, a topic position within the document and a (topic-dependent) section length. Hence structural information of the training data is exploited in order to perform segmentation and annotation of unknown text.

Abstract translation: 本发明涉及一种通过利用在注释训练数据上训练的统计模型来构造非结构化文本的方法，计算机程序产品和计算机系统。 将文本分割的文本的每个部分进一步分配给与一组标签相关联的主题。 用于文本分段和用于将主题及其关联标签分配给文本部分的统计模型明确地表示：文本部分与主题之间的相关性，部分之间的主题转换，内容中的主题位置 文件和（主题相关）部分长度。 因此，利用训练数据的结构信息来执行未知文本的分割和注释。

公开(公告)号：WO2005050474A3

公开(公告)日：2006-07-13

申请号：PCT/IB2004052405

申请日：2004-11-12

Applicant: PHILIPS INTELLECTUAL PROPERTY ,  KONINKL PHILIPS ELECTRONICS NV ,  PETERS JOCHEN ,  MATUSOV EVGENY ,  MEYER CARSTEN ,  KLAKOW DIETRICH

Inventor： PETERS JOCHEN ,  MATUSOV EVGENY ,  MEYER CARSTEN ,  KLAKOW DIETRICH

IPC: G06F17/27 ,  G06F17/30

CPC classification number: G06F17/21 ,  G06F17/27 ,  G06F17/2765

Abstract: The invention relates to a method, a computer program product, a segmentation system and a user interface for structuring an unstructured text by making use of statistical models trained on annotated training data. The method performs text segmentation into text sections and assigns labels to text sections as section headings. The performed segmentation and assignment is provided to a user for general review. Additionally, alternative segmentations and label assignments are provided to the user being capable to select alternative segmentations and alternative labels as well as to enter a user defined segmentation and user defined label. In response to the modifications introduced by the user, a plurality of different actions are initiated incorporating the re-segmentation and re-labelling of successive parts of the document or the entire document. Furthermore the method comprises a learning functionality, logging and analyzing user introduced modifications for adaptation of the method to the user's preferences and for further training of the statistical models.

Abstract translation: 本发明涉及一种方法，计算机程序产品，分割系统和用户界面，用于通过利用在注释训练数据上训练的统计模型来构造非结构化文本。 该方法执行文本分段到文本部分，并将标签分配给文本部分作为标题。 执行的分割和分配被提供给用户进行一般审查。 此外，替代分割和标签分配被提供给能够选择替代分割和替代标签以及输入用户定义的分割和用户定义标签的用户。 响应于用户引入的修改，启动了多个不同的动作，其中包括文档或整个文档的连续部分的重新分割和重新标记。 此外，该方法包括学习功能，记录和分析用户引入的修改以将该方法适应于用户的偏好和进一步训练统计模型。

公开(公告)号：WO2008120177A3

公开(公告)日：2009-01-08

申请号：PCT/IB2008051631

申请日：2008-04-28

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS INTELLECTUAL PROPERTY ,  PETERS JOCHEN ,  ECABERT OLIVIER ,  SCHRAMM HAUKE ,  WEESE JUERGEN ,  BERG JENS VON ,  LORENZ CRISTIAN

Inventor： PETERS JOCHEN ,  ECABERT OLIVIER ,  SCHRAMM HAUKE ,  WEESE JUERGEN ,  BERG JENS VON ,  LORENZ CRISTIAN

IPC: G06T7/00

CPC classification number: G06T7/149 ,  G06T7/12 ,  G06T2207/10072 ,  G06T2207/30048 ,  G06T2207/30101

Abstract: The invention relates to an adaptation system for adapting a deformable model to an object of interest in an image data set, the system comprising a propagator for propagating a set of predetermined transformation parameters to the model segments that have not yet been activated for adaptation to the image; an activator for activating at least one model segment from the model segments that have not yet been activated for adaptation to the image; and an adapter for adapting the deformable model by optimizing model energy of the deformable model, said model energy comprising internal energy of the plurality of model segments and external energy of at least the latest activated model segment(s). By enabling propagation of the transformation parameters from the model segments that have been adapted to the image to the model segments that have not been adapted to the image, this invention can improve the robustness and flexibility of the adaptation.

Abstract translation: 本发明涉及一种用于将可变形模型适应于图像数据集中的感兴趣对象的自适应系统，该系统包括传播器，用于将一组预定变换参数传播到尚未被激活以适应于 图片; 用于激活来自尚未被激活用于适应图像的模型段的至少一个模型段的激活器; 以及用于通过优化所述可变形模型的模型能量来适配所述可变形模型的适配器，所述模型能量包括所述多个模型段的内部能量和至少最近激活的模型段的外部能量。 通过使来自已经适应于图像的模型段的变换参数能够传播到尚未适应于图像的模型段，本发明可以提高适应性的鲁棒性和灵活性。

公开(公告)号：WO2008041165A3

公开(公告)日：2008-11-20

申请号：PCT/IB2007053949

申请日：2007-09-28

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS INTELLECTUAL PROPERTY ,  VON BERG JENS ,  HOFMANN BERND ,  LORENZ CRISTIAN ,  ECABERT OLIVIER ,  PETERS JOCHEN ,  WEESE JUERGEN

Inventor： VON BERG JENS ,  HOFMANN BERND ,  LORENZ CRISTIAN ,  ECABERT OLIVIER ,  PETERS JOCHEN ,  WEESE JUERGEN

IPC: G06T7/00

CPC classification number: G06T7/30 ,  A61B5/055 ,  A61B6/504 ,  A61B6/5229 ,  A61B8/0891 ,  A61B8/5238 ,  G06T2207/20044 ,  G06T2207/30101 ,  Y10S128/922

Abstract: The invention relates to a system (100) for registering a vessel model with an image data set based on a joined model comprising a reference object model and the vessel model, the system comprising: a placement unit (110) for placing the joined model in a space of the image data set, thereby creating a placed joined model comprising a placed reference object model and a placed vessel model; a computation unit (120) for computing a deformation field based on a landmark displacement field comprising displacements of landmarks of the placed reference object model relative to corresponding landmarks in the image data set; a transformation unit (130) for transforming the placed joined model using the deformation field, thereby creating a transformed joined model comprising a transformed reference object model and a transformed vessel model; and a registration unit (140) for registering the transformed vessel model with the image data set based on modifying the transformed vessel model and optimizing an objective function of the modified transformed vessel model, wherein the objective function comprises a location-prior term based on a localization of the modified transformed vessel model relative to the transformed joined model. Hence, the system is arranged to model a vessel taking into account the localization of a vessel model relative to a reference anatomical structure described by a reference model.

Abstract translation: 本发明涉及一种用于基于包括参考对象模型和血管模型的结合模型将血管模型与图像数据集配准的系统（100），所述系统包括：放置单元（110），用于将所述结合模型放入 图像数据集的空间，由此创建包括放置的参考对象模型和放置的船模型的放置的连接模型; 计算单元（120），用于基于地标位移场来计算变形场，所述地标位移场包括所放置的参考对象模型的地标相对于所述图像数据集中的对应地标的位移; 变换单元（130），用于使用所述变形场来变换所放置的结合模型，从而创建包括变换的参考对象模型和变换的血管模型的变换的结合模型; 以及注册单元（140），用于基于修改所述变换的血管模型并优化所述修改的变换的血管模型的目标函数来将所述变换的血管模型与所述图像数据集配准，其中所述目标函数包括基于 修改后的转化血管模型相对于转化的连接模型的定位。 因此，该系统被设置成考虑到血管模型相对于由参考模型描述的参考解剖结构的定位来对血管进行建模。

公开(公告)号：WO2008018014A3

公开(公告)日：2008-04-10

申请号：PCT/IB2007053101

申请日：2007-08-07

Applicant: KONINKL PHILIPS ELECTRONICS NV ,  PHILIPS INTELLECTUAL PROPERTY ,  KIEFER GUNDOLF ,  LEHMANN HELKO ,  GELLER DIETER ,  SCHRAMM HAUKE ,  PETERS JOCHEN ,  ECABERT OLIVIER ,  WEESE JUERGEN

Inventor： KIEFER GUNDOLF ,  LEHMANN HELKO ,  GELLER DIETER ,  SCHRAMM HAUKE ,  PETERS JOCHEN ,  ECABERT OLIVIER ,  WEESE JUERGEN

IPC: G06F19/00

CPC classification number: G16H40/63

Abstract: The invention relates to a system (100) for obtaining information relating to segmented volumetric medical image data, the system comprising: a display unit (110) for displaying a view of the segmented volumetric medical image data on a display; an indication unit (115) for indicating a location on the displayed view; a trigger unit (120) for triggering an event; an identification unit (125) for identifying a segmented anatomical structure comprised in the segmented volumetric medical image data based on the indicated location on the displayed view in response to the triggered event; and an execution unit (130) for executing an action associated with the identified segmented anatomical structure, thereby obtaining information relating to the segmented volumetric medical image data. The action executed by the execution unit (130) may be displaying a name of the segmented anatomical structure, a short description of the segmented anatomical structure, or a hint on a potential malformation or malfunction of the segmented anatomical structure. Thus, the system (100) allows obtaining valuable information relating to the volumetric medical image data viewed by a physician on the display, thereby assisting the physician in medical diagnosing.

Abstract translation: 本发明涉及一种用于获取与分段体积医学图像数据相关的信息的系统（100），该系统包括：显示单元（110），用于在显示器上显示分割的体积医学图像数据的视图; 指示单元（115），用于指示所显示的视图上的位置; 触发单元（120），用于触发事件; 识别单元（125），用于响应于触发的事件，基于所显示的视图上的指示位置来识别包含在所述分段体积医学图像数据中的分段解剖结构; 以及执行单元（130），用于执行与所识别的分段解剖结构相关联的动作，从而获得与分割的体积医学图像数据相关的信息。 由执行单元（130）执行的动作可以显示分割的解剖结构的名称，分割的解剖结构的简短描述，或对分割的解剖结构的潜在畸形或故障的提示。 因此，系统（100）允许获得与医生在显示器上观看的体积医学图像数据相关的有价值的信息，从而辅助医师进行医学诊断。