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. 发明公开

EP3272611A4 INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING METHOD, AND PROGRAM 有权转让
公开(公告)号：EP3272611A4
公开(公告)日：2018-06-20
申请号：EP16782808
申请日：2016-04-21
申请人： PANASONIC IP MAN CO LTD
发明人： MOTOMURA HIDETO , KOURKOUSS MOHAMED SAHIM , SAWADA YOSHIHIDE , MORI TOSHIYA , TSUJI MASANAGA
IPC分类号： B60W50/14 , B60K31/00 , B60K35/00 , B60R16/02 , B60W30/00 , B60W40/09 , B60W50/00 , B60W50/10 , G05D1/00 , G06K9/00 , G08G1/16
CPC分类号： B60W50/14 , B60K35/00 , B60R16/02 , B60W40/09 , B60W50/00 , B60W50/0097 , B60W2050/0002 , B60W2050/0075 , B60W2050/146 , B60W2420/42 , B60W2420/52 , B60W2520/10 , B60W2530/14 , B60W2540/10 , B60W2540/12 , B60W2540/20 , B60W2550/20 , B60W2550/30 , B60W2550/402 , G05D1/0088 , G05D2201/0213 , G06K9/00791 , G06K9/6274 , G08G1/0112 , G08G1/0129 , G08G1/0141 , G08G1/0962 , G08G1/09626 , G08G1/096716 , G08G1/096725 , G08G1/096741 , G08G1/096775 , G08G1/167
摘要： An information processing system (1000) that appropriately estimates a driving conduct includes: a detector (1001) that detects a vehicle environment state, which is at least one of surroundings of a vehicle and a driving state of the vehicle; a behavior learning unit (1002) configured to cause a neural network to learn a relationship between the vehicle environment state detected by the detector (1001) and a behavior of the vehicle implemented after the vehicle environment state; and a behavior estimation unit (1003) configured to estimate a behavior of the vehicle by inputting, into the neural network that learned, the vehicle environment state detected at a current point in time by the detector.

2. 发明公开

EP2903513A2 AUTOMATIC STENT DETECTION 审中-公开
标题翻译： AUTOMATISCHE STENTERKENNUNG
公开(公告)号：EP2903513A2
公开(公告)日：2015-08-12
申请号：EP13843546.6
申请日：2013-10-04
申请人： Begin, Elizabeth , Kemp, Nathaniel J. , Sproul, Jason , Elmaanaoui, Badr
发明人： Begin, Elizabeth , Kemp, Nathaniel J. , Sproul, Jason , Elmaanaoui, Badr
IPC分类号： A61B5/06 , A61B5/00
CPC分类号： G06T7/0012 , A61B5/0066 , A61B5/0073 , A61B5/061 , A61B5/6852 , A61B8/0841 , A61B8/12 , A61B8/14 , A61B8/4416 , A61B8/5223 , A61B8/5261 , A61B34/20 , G06K9/6247 , G06K9/6274 , G06T7/0014 , G06T7/70 , G06T7/74 , G06T2207/10072 , G06T2207/10081 , G06T2207/10088 , G06T2207/10101 , G06T2207/10132 , G06T2207/10136 , G06T2207/20048 , G06T2207/20076 , G06T2207/20081 , G06T2207/30021 , G06T2207/30101
摘要： This invention relates generally to the detection of objects, such as stents, within intraluminal images using principal component analysis and/or regional covariance descriptors. In certain aspects, a training set of pre-defined intraluminal images known to contain an object is generated. The principal components of the training set can be calculated in order to form an object space. An unknown input intraluminal image can be obtained and projected onto the object space. From the projection, the object can be detected within the input intraluminal image. In another embodiment, a covariance matrix is formed for each pre-defined intraluminal image known to contain an object. An unknown input intraluminal image is obtained and a covariance matrix is computed for the input intraluminal image. The covariances of the input image and each image of the training set are compared in order to detect the presence of the object within the input intraluminal image.
摘要翻译：本发明一般涉及使用主成分分析和/或区域协方差描述符检测在腔内图像内的物体，例如支架。在某些方面，生成已知包含对象的预定义的管腔内图像的训练集。可以计算训练集的主要组成部分以形成对象空间。可以获得未知的输入管腔内图像并将其投影到对象空间上。从投影中可以在输入的管腔内图像中检测物体。在另一个实施例中，为已知包含对象的每个预定义的管腔内图像形成协方差矩阵。获得未知的输入管腔内图像，并为输入的管腔内图像计算协方差矩阵。比较输入图像和训练集合的每个图像的协方差，以便检测输入的管腔内图像中物体的存在。

3. 发明公开

EP2786311A1 METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR CLASSIFICATION OF OBJECTS 审中-公开
标题翻译： VERFAHREN，VORRICHTUNG UND COMPUTERPROGRAMMPRODUKT ZUR KLASSIFIZIERUNG VON OBJEKTEN
公开(公告)号：EP2786311A1
公开(公告)日：2014-10-08
申请号：EP12854032.5
申请日：2012-10-25
申请人： Nokia Corporation
发明人： GOVINDARAO, Krishna Annasagar , PUTRAYA, Gururaj Gopal
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06F17/30707 , G06F17/3002 , G06K9/00295 , G06K9/6215 , G06K9/6232 , G06K9/627 , G06K9/6274
摘要： In accordance with various example embodiments, methods, apparatuses, and computer program products are provided. A method comprises accessing a gallery comprising a plurality of classes, determining distances between classes of the plurality of classes, and determining thresholds for one or more classes of the gallery for classifying test objects in the classes, wherein threshold for a class is determined based on at least one distance of the class from at least one remaining class of the plurality of classes. The apparatus comprises at least one processor and at least one memory, configured to, cause the apparatus to perform accessing a gallery comprising a plurality of classes, determining distances between classes of the plurality of classes, and determining thresholds for classes of the gallery for classifying test objects in the classes, wherein threshold for a class is determined based on distances of the class from remaining classes of the gallery.
摘要翻译：根据各种示例性实施例，提供了方法，装置和计算机程序产品。一种方法包括访问包括多个类别的画廊，确定所述多个类别的类别之间的距离，以及确定所述画廊的一个或多个类别的门槛，以对所述类别中的测试对象进行分类，其中类别的阈值基于所述类别与所述多个类别中的至少一个剩余类别的至少一个距离。该装置包括至少一个处理器和至少一个存储器，其被配置为使得该装置执行访问包括多个类别的库，确定多个类别的类别之间的距离，以及确定用于分类的库的类别的阈值在类中测试对象，其中类的阈值基于类与图库的剩余类的距离来确定。

4. 发明授权

EP0574937B1 Method and apparatus for input classification using a neural network 失效
标题翻译：为输入进行分类以神经网络的方法和装置
公开(公告)号：EP0574937B1
公开(公告)日：2000-08-16
申请号：EP93109763.8
申请日：1993-06-18
申请人： UNITED PARCEL SERVICE OF AMERICA, INC.
发明人： Moed,Michael C. , Lee,Chih-Ping
IPC分类号： G06K9/66
CPC分类号： G06K9/6274 , G06K9/6223 , G06K9/6272 , G06K9/6273

5. 发明公开

EP0574937A3 Method and apparatus for input classification using a neural network 失效
标题翻译：为输入进行分类以神经网络的方法和装置。
公开(公告)号：EP0574937A3
公开(公告)日：1995-01-11
申请号：EP93109763.8
申请日：1993-06-18
申请人： UNITED PARCEL SERVICE OF AMERICA, INC.
发明人： Moed,Michael C. , Lee,Chih-Ping
IPC分类号： G06K9/66
CPC分类号： G06K9/6274 , G06K9/6223 , G06K9/6272 , G06K9/6273
摘要： The invention calculates a distance measure from the feature vector to the center of each neuron of a plurality of neurons, where each neuron is associated with one of the possible outputs. The invention then selects each neuron that encompasses the feature vector in accordance with the distance measure. The invention then determines a vote for each possible output, where the vote is the number of selected neurons that are associated with each possible output. If the vote for one of the possible outputs is greater than all other votes for all other possible outputs, then the invention selects that possible output as corresponding to the input. Otherwise, if the vote for one of the possible outputs is not greater than all other votes for all other possible outputs, then the invention identifies the neuron that has the smallest distance measure of all other neurons. If that smallest distance measure is less than a specified value, then the invention selects the possible output associated with that identified neuron as corresponding to the input.

6. 发明公开

EP0574937A2 Method and apparatus for input classification using a neural network 失效
标题翻译：为输入进行分类以神经网络的方法和装置。
公开(公告)号：EP0574937A2
公开(公告)日：1993-12-22
申请号：EP93109763.8
申请日：1993-06-18
申请人： UNITED PARCEL SERVICE OF AMERICA, INC.
发明人： Moed,Michael C. , Lee,Chih-Ping
IPC分类号： G06K9/66
CPC分类号： G06K9/6274 , G06K9/6223 , G06K9/6272 , G06K9/6273
摘要： The invention calculates a distance measure from the feature vector to the center of each neuron of a plurality of neurons, where each neuron is associated with one of the possible outputs. The invention then selects each neuron that encompasses the feature vector in accordance with the distance measure. The invention then determines a vote for each possible output, where the vote is the number of selected neurons that are associated with each possible output. If the vote for one of the possible outputs is greater than all other votes for all other possible outputs, then the invention selects that possible output as corresponding to the input. Otherwise, if the vote for one of the possible outputs is not greater than all other votes for all other possible outputs, then the invention identifies the neuron that has the smallest distance measure of all other neurons. If that smallest distance measure is less than a specified value, then the invention selects the possible output associated with that identified neuron as corresponding to the input.
摘要翻译：本发明是一种用于输入分类成可能的输出的多个一个的分类方法和装置。本发明基因费率特征矢量代表输入的。本发明然后计算从特征向量到神经元的复数，其中，每个神经元与可能输出的一个相关联的每个神经元的中心的距离度量。然后，本发明选择每个神经元没有涵盖具有距离度量在雅舞蹈的特征向量。本发明然后bestimmt表决对每个可能的输出，其中所述票是所选神经元的数量并与每个可能的输出相关联。如果可能的输出中的一个的投票是比所有其他票对于所有其它可能的输出值，则选择所述没有本发明可能的输出作为对应于输入。否则，如果可能的输出中的一个投票并不比其他所有选票其他所有可能的输出值，则该发明鉴别神经元做了所有其他神经元的最小距离度量。如果做了最小距离度量小于指定值时，则本发明选择与神经元相关联的可能的输出并识别为对应于该输入。因此，本发明是用于产生一个神经元锻炼方法和装置。本发明选择的锻炼的输入，其中，每个锻炼输入对应于第一种可能的输出多个。然后，本发明表征每个输入锻炼的质量。然后，本发明从锻炼特征的输入的锻炼输入所做选择比其它输入锻炼中的至少一个具有更高的质量。然后，本发明在创建雅舞蹈与所选择的输入特征的锻炼神经元。因此，本发明是一种用于输入分类成可能的输出的多个一个的分类方法。本发明的输入分类到簇代表两种或更多种可能的输出的一个。的本发明然后分类输入到由集群代表的两个或更多个可能输出之一。至少本发明的分类步骤中的一个是由表示输入的信息进行比较来神经元特征的。因此，本发明是一种用于调节神经元包含特征矢量的多个方法和装置。本发明表征了特征矢量的空间分布。与雅舞发明进行空间bestimmt神经元做了表征。

7. 发明公开

EP3179407A1 RECOGNITION OF A 3D MODELED OBJECT FROM A 2D IMAGE 有权
标题翻译：从2D图像识别3D模型对象
公开(公告)号：EP3179407A1
公开(公告)日：2017-06-14
申请号：EP15306952.1
申请日：2015-12-07
申请人： Dassault Systèmes
发明人： BOULKENAFED, Malika , MICHEL, Fabrice , REJEB SFAR, Asma
IPC分类号： G06K9/00
CPC分类号： G06K9/6269 , G06F17/50 , G06K9/00208 , G06K9/4628 , G06K9/6215 , G06K9/6274 , G06N3/04 , G06N3/0454 , G06N3/08
摘要： The invention notably relates to a computer-implemented method for recognizing a three-dimensional modeled object from a two-dimensional image. The method comprises providing a first set of two-dimensional images rendered from three-dimensional modeled objects, each two-dimensional image of the first set being associated to a label; providing a second set of two-dimensional images not rendered from three-dimensional objects, each two-dimensional image of the second set being associated to a label; training a model on both first and second sets; providing a similarity metric; submitting a two-dimensional image depicting at least one object; and retrieving a three-dimensional object similar to the said at least one object of the two-dimensional image submitted by using the trained model and the similarity metric.
摘要翻译：本发明特别涉及用于从二维图像识别三维建模对象的计算机实现的方法。该方法包括提供从三维建模对象渲染的第一组二维图像，第一组的每个二维图像与标签关联; 提供未从三维对象渲染的第二组二维图像，第二组的每个二维图像与标签相关联; 在第一组和第二组上训练模型; 提供相似性度量; 提交描绘至少一个对象的二维图像; 以及检索与使用训练模型和相似性度量提交的二维图像的所述至少一个对象相似的三维对象。

8. 发明公开

EP2786311A4 METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR CLASSIFICATION OF OBJECTS 审中-公开
标题翻译：方法，设备和计算机程序产品分类物体的
公开(公告)号：EP2786311A4
公开(公告)日：2016-08-17
申请号：EP12854032
申请日：2012-10-25
申请人： NOKIA TECHNOLOGIES OY
发明人： GOVINDARAO KRISHNA ANNASAGAR , PUTRAYA GURURAJ GOPAL
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06F17/30707 , G06F17/3002 , G06K9/00295 , G06K9/6215 , G06K9/6232 , G06K9/627 , G06K9/6274
摘要： In accordance with various example embodiments, methods, apparatuses, and computer program products are provided. A method comprises accessing a gallery comprising a plurality of classes, determining distances between classes of the plurality of classes, and determining thresholds for one or more classes of the gallery for classifying test objects in the classes, wherein threshold for a class is determined based on at least one distance of the class from at least one remaining class of the plurality of classes. The apparatus comprises at least one processor and at least one memory, configured to, cause the apparatus to perform accessing a gallery comprising a plurality of classes, determining distances between classes of the plurality of classes, and determining thresholds for classes of the gallery for classifying test objects in the classes, wherein threshold for a class is determined based on distances of the class from remaining classes of the gallery.

9. 发明公开

EP1646926A2 CHARACTERIZING BIOLOGICAL STIMULI BY RESPONSE CURVES 审中-公开
标题翻译：生物刺激BY响应曲线表征
公开(公告)号：EP1646926A2
公开(公告)日：2006-04-19
申请号：EP04778162.0
申请日：2004-07-16
申请人： Cytokinetics, Inc.
发明人： KUTSYY, Vadim , COLEMAN, Daniel, A. , VAISBERG, Eugeni, A.
IPC分类号： G06F1/00
CPC分类号： G06K9/6274 , G06K9/00147 , G06K9/00536
摘要： A method for calculating distances between stimulus response curves (e.g., dose response curves) allows classification of stimuli, The response curves show how the phenotype of one or more cells changes in response to varying levels of the stimulus. Each “point” on the curve represents quantitative phenotype or signature for cell(s) at a particular level of stimulus (e.g., dose of a therapeutic). The signatures are multivariate phenotypic representations of the cell (s). They include various features of the cell(s) obtained by image analysis. To facilitate the comparison of stimuli, distances between points on the response curves are calculated. First, the response curves may be aligned on a coordinate representing a separate distance, r, from a common point of negative control (e.g., the point where no stimulus is applied). Integration on r may be used to compute the distance between two response curves. The distance between response curves is used to classify stimuli.

10. 发明公开

EP1197913A1 Training method and apparatus for adjusting a neuron 失效
标题翻译：培训课程和教学课程Einstellung eines神经元
公开(公告)号：EP1197913A1
公开(公告)日：2002-04-17
申请号：EP01125304.4
申请日：1993-06-18
申请人： UNITED PARCEL SERVICE OF AMERICA, INC.
发明人： Moed, Michael C. , Lee, Chih-Ping
IPC分类号： G06K9/66
CPC分类号： G06K9/6274 , G06K9/6223 , G06K9/6273 , G06N3/082
摘要： A training method for adjusting a neuron comprises the steps of (a) generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; and (b) if said neuron encompasses said feature vector and said neuron does not correspond to said training input then spatially adjusting said neuron, wherein said adjusted neuron comprises a boundary defined by two or more adjusted neuron axes of different length, wherein said neuron is in a feature space comprising an existing feature vector, wherein said neuron comprises a boundary defined by two or more neuron axes, and wherein step (b) further comprises the steps of (i) selecting at least one of said neuron axes; (ii) calculating the distances along each of said selected neuron axes from the center of said neuron to said existing feature vector; and (iii) reducing said selected neuron axes by amounts proportional to said distances and the lengths of said selected neuron axes to create said adjusted neuron.
摘要翻译：用于调整神经元的训练方法包括以下步骤：（a）生成表示训练输入的特征向量，其中所述训练输入对应于多个可能输出中的一个; 和（b）如果所述神经元包含所述特征向量，并且所述神经元不对应于所述训练输入，则在空间上调整所述神经元，其中所述经调整的神经元包括由两个或更多个不同长度的经调整的神经元轴定义的边界，其中所述神经元是在包括现有特征向量的特征空间中，其中所述神经元包括由两个或更多个神经元轴定义的边界，并且其中步骤（b）还包括以下步骤：（i）选择所述神经元轴中的至少一个; （ii）计算从所述神经元的中心到所述现有特征向量的每个所述选择的神经元轴的距离; 以及（iii）将所选择的神经元轴减少与所述距离和所选择的神经元轴的长度成比例的量，以产生所述经调整的神经元。

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