专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2012121956A1 SYSTEMS AND METHODS FOR TOPOLOGICAL REPRESENTATION OF GEOMETRIC CONTEXT IN AN IMAGE BY DISCRETE TEXTURE TRACES 审中-公开
标题翻译：通过离散纹理轨迹对图像中的几何背景进行拓扑表征的系统和方法
公开(公告)号：WO2012121956A1
公开(公告)日：2012-09-13
申请号：PCT/US2012/027172
申请日：2012-03-01
申请人： SIEMENS CORPORATION , ERNST, Jan , SINGH, Maneesh Kumar
发明人： ERNST, Jan , SINGH, Maneesh Kumar
IPC分类号： G06K9/46
CPC分类号： G06K9/4671 , G06K9/469
摘要： Novel patch representations which are used in machine vision and are quasi-invariant to a large class of smooth deformations are provided. These patches are derived from a continuous domain model, called Profile Traces, which is a function only of the topological properties of the image patch and is, by construction, invariant to any homeomorphic transformations of the domain. The model is defined in terms of intersections of equivalence sets. A discrete-domain approximation called Discrete Texture Traces (DTT) is provided. DTT is designed to be computationally practical and is shown to be quasi-invariant to smooth spatial deformations. Methods and system that implement the steps of the methods are also provided.
摘要翻译：提供了在机器视觉中使用并且对于大类光滑变形是准不变的新颖补丁表示。这些补丁从连续域模型派生，称为简档跟踪，它仅是图像补丁的拓扑属性的一个功能，并且通过构造对域的任何同态变换都是不变的。该模型是根据等价集合的交集来定义的。提供了称为离散纹理跟踪（DTT）的离散域近似。 DTT被设计为在计算上实用，并且被证明是对于平滑的空间变形是准不变的。还提供了实现方法步骤的方法和系统。

2. 发明申请

WO2014078615A1 METHOD TO IDENTIFY OPTIMUM CORONARY ARTERY DISEASE TREATMENT 审中-公开
标题翻译：识别最佳冠状动脉疾病治疗的方法
公开(公告)号：WO2014078615A1
公开(公告)日：2014-05-22
申请号：PCT/US2013/070225
申请日：2013-11-15
申请人： SIEMENS HEALTHCARE DIAGNOSTICS INC. , KAMEN, Ali , SINGH, Maneesh Kumar , POELSTERL, Sebastian , LADIC, Lance Anthony , COMANICIU, Dorin
发明人： KAMEN, Ali , SINGH, Maneesh Kumar , POELSTERL, Sebastian , LADIC, Lance Anthony , COMANICIU, Dorin
IPC分类号： G06F19/00
CPC分类号： G06F19/345 , G06F19/00 , G06N3/0472 , G06N3/08 , G16H50/20
摘要： A method of identifying an optimum treatment for a patient suffering from coronary artery disease, comprising: (i) providing patient information selected from: (a) status in the patient of one or more coronary disease associated biomarkers; (b) one or more items of medical history information selected from prior condition history, intervention history and medication history; (c) one or more items of diagnostic history, if the patient has a diagnostic history; and (d) one or more items of demographic data; (ii) aggregating the patient information in: (a) a Bayesian network; (b) a machine learning and neural network; (c) a rule-based system; and (d) a regression-based system; (iii) deriving a predicted probabilistic adverse event outcome for each intervention comprising percutaneous coronary intervention by placement of a bare metal stent, or a drug-coated stent; or by coronary artery bypass grafting; and (iv) determining the intervention having the lowest predicted probabilistic adverse outcome.
摘要翻译：一种鉴定患有冠状动脉疾病的患者的最佳治疗的方法，包括：（i）提供患者信息，所述患者信息选自：（a）患者中一种或多种冠状动脉疾病相关生物标志物的状态; （b）从先前情况史，干预史和用药史选择的一项或多项病史信息; （c）患者具有诊断史的一项或多项诊断史; 和（d）一个或多个人口统计数据项目; （ii）在以下方面聚合患者信息：（a）贝叶斯网络; （b）机器学习和神经网络; （c）基于规则的制度; 和（d）基于回归的系统; （iii）通过放置裸金属支架或药物涂层支架，导出包括经皮冠状动脉介入的每个干预的预测概率不良事件结果; 或通过冠状动脉旁路移植术; 和（iv）确定具有最低预测概率不良结果的干预。

3. 发明申请

WO2012112756A1 OBJECT RECOGNITION FOR SECURITY SCREENING AND LONG RANGE VIDEO SURVEILLANCE 审中-公开
标题翻译：用于安全筛选和长距离视频监控的目标识别
公开(公告)号：WO2012112756A1
公开(公告)日：2012-08-23
申请号：PCT/US2012/025409
申请日：2012-02-16
申请人： SIEMENS CORPORATION , SHET, Vinay Damodar , BAHLMANN, Claus , SINGH, Maneesh Kumar
发明人： SHET, Vinay Damodar , BAHLMANN, Claus , SINGH, Maneesh Kumar
IPC分类号： G06K9/00 , G01V5/00
CPC分类号： G06K9/00771 , G06K2209/09
摘要： A method of detecting an object in image data that is deemed to be a threat includes annotating sections of at least one training image to indicate whether each section is a component of the object (S101), encoding a pattern grammar describing the object using a plurality of first order logic based predicate rules (S102), training distinct component detectors to each identify a corresponding one of the components based on the annotated training images (S103), processing image data with the component detectors to identify at least one of the components (S104), and executing the rules to detect the object based on the identified components (S105).
摘要翻译：检测被认为是威胁的图像数据中的对象的方法包括：注释至少一个训练图像的部分，以指示每个部分是否是对象的组成部分（S101），使用多个对对象进行描述对象的模式语法的编码基于一阶逻辑的谓词规则（S102），训练不同的分量检测器，以基于所注释的训练图像识别相应的一个分量（S103），利用分量检测器处理图像数据以识别组件中的至少一个（ S104），并且基于所识别的组件执行规则以检测对象（S105）。

4. 发明申请

WO2013086123A1 CONFIGURATION TOOL FOR VIDEO ANALYTICS 审中-公开
标题翻译：视频分析的配置工具
公开(公告)号：WO2013086123A1
公开(公告)日：2013-06-13
申请号：PCT/US2012/068153
申请日：2012-12-06
申请人： SIEMENS AKTIENGESELLSCHAFT , GAO, Xiang , SHET, Vinay, Damodar , ZHENG, Xianjun, S. , MITTAL, Sushil , RANA, Mayank , SINGH, Maneesh, Kumar , AGTHE, Bernhard , HUTTER, Andreas
发明人： GAO, Xiang , SHET, Vinay, Damodar , ZHENG, Xianjun, S. , MITTAL, Sushil , RANA, Mayank , SINGH, Maneesh, Kumar , AGTHE, Bernhard , HUTTER, Andreas
IPC分类号： H04N7/18 , G08B13/196
CPC分类号： H04N7/181 , G08B13/19645 , G08B13/1968
摘要： Multiple cameras are configured for use in video analytics. A single configuration tool is provided. The interrelationships between cameras are included within the configuration. Using a combination of text entry fields, registration of the cameras on a floor or other map, and marking on images from the cameras, an efficient workflow for configuration may be provided
摘要翻译：配置多个摄像机用于视频分析。提供了一个单一的配置工具。相机之间的相互关系包含在配置内。使用文本输入字段的组合，将相机注册在地板或其他地图上，并且对来自相机的图像进行标记，可以提供有效的配置工作流程

5. 发明申请

WO2019204547A1 SYSTEMS AND METHODS FOR AUTOMATIC SPEECH RECOGNITION USING DOMAIN ADAPTATION TECHNIQUES 审中-公开
公开(公告)号：WO2019204547A1
公开(公告)日：2019-10-24
申请号：PCT/US2019/028023
申请日：2019-04-18
申请人： SINGH, Maneesh Kumar
发明人： SINGH, Maneesh Kumar , TRIPATHI, Aditay , ANAND, Saket
IPC分类号： G10L15/00 , G10L15/01 , G10L15/02 , G10L15/08 , G10L15/16
摘要： Systems and methods for automatic speech recognition by training a neural network to learn features from raw speech. The system comprises a neural network executing on a computer system and comprising a feature extractor, a label classifier, and a domain classifier. The feature extractor processes raw speech data and generates a first output data. The label classifier processes the first output data and generates a second output data. The domain classifier processes the first output data and generating a third output data. The neural network calculates first loss data based on the second output, and second loss data based on the third output. Further, the neural network is trained to minimize a cross-entropy cost of the label classifier and to maximize a cross-entropy cost of the domain classifier using the first loss data and the second loss data.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式