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

EP3238137A1 REPRESENTATION SEMANTIQUE DU CONTENU D'UNE IMAGE 有权
标题翻译：表示SEMANTIQUE DU CONTENU D'UNE图像
公开(公告)号：EP3238137A1
公开(公告)日：2017-11-01
申请号：EP15801869.7
申请日：2015-12-01
申请人： Commissariat à l'Énergie Atomique et aux Énergies Alternatives
发明人： POPESCU, Adrian , BALLAS, Nicolas , GINSCA, Alexandru Lucian , LE BORGNE, Hervé
IPC分类号： G06K9/62 , G06F17/30
CPC分类号： G06K9/00456 , G06F17/30256 , G06F17/30271 , G06K9/62 , G06K9/726 , G06N99/005
摘要： The invention discloses a method implemented by computer for semantically describing the content of an image comprising the steps consisting of receiving a signature associated with said image; receiving a plurality of groups of initial visual concepts; the method being characterised by the steps consisting of expressing the signature of the image in the form of a vector comprising components referring to the groups of initial visual concepts; and modifying said signature by applying a filtering rule that is applied to the components of said vector. Developments describe, in particular, filtering rules that involve filtering by thresholds and/or by intra-group or inter-group order statistics, partitioning techniques including the visual similarity of the images and/or the semantic similarity of the concepts, and the optional addition of manual annotations to the semantic description of the image. The advantages of the method in terms of sparse and diversified semantic representation are presented.
摘要翻译：本发明公开了一种由计算机实现的用于语义描述图像内容的方法，包括以下步骤：接收与所述图像相关联的签名; 接收多组初始视觉概念; 该方法的特征在于以下步骤：以向量形式表示图像的签名，该向量包括涉及初始视觉概念组的组件; 以及通过应用应用于所述向量的分量的过滤规则来修改所述签名。发展尤其描述了涉及通过阈值和/或通过组内或组间秩序统计过滤的过滤规则，包括图像的视觉相似性和/或概念的语义相似性的划分技术以及可选的添加手动注释到图像的语义描述。给出了该方法在稀疏和多样化语义表示方面的优势。

2. 发明授权

EP1804183B1 Process for selecting objects in a PLM database and apparatus implementing this process 有权转让
标题翻译： Verfahren zur Auswahl von Objekten in einer PLM-Datenbank und Vorrichtung zur Implementierung dieses Verfahrens。
公开(公告)号：EP1804183B1
公开(公告)日：2017-06-21
申请号：EP05028720
申请日：2005-12-30
申请人： DASSAULT SYSTÈMES
发明人： DELARUE GUILLAUME , NONCLERCQ ARNAUD
IPC分类号： G06F17/50 , G06F3/033 , G06F3/048 , G06F3/0482 , G06F3/14 , G06F9/44 , G06F17/30 , G06T11/00 , G06T15/00 , G06T15/04 , G06T17/00 , G06T19/00
CPC分类号： G06F17/50 , G06F3/0482 , G06F3/14 , G06F9/4443 , G06F17/30271 , G06T11/001 , G06T15/005 , G06T15/04 , G06T17/005 , G06T19/00 , G06T2200/24
摘要： The invention is directed to a process, an apparatus and a program for selecting objects in a PLM database containing modeled objects. The process comprises displaying (step 620) in a graphical user interface a view of a set of objects of the database. Said view is a non-associative view, that is, the graphical elements of said view are not partitioned according to the individual objects of the set, from the system standpoint. In this respect, the process may comprise, prior to the step of displaying, aggregating (step 610) representations of respective objects of the set of objects to form the displayed view. The view is thereby rendered more rapidly. Then, upon definition (step 630) of a volume by the user, it is determined (steps 640 - 650) the objects intersecting said volume in the non-associative view. The process comprises searching the database and identifying to the user objects according to the intersection. Use is for example made of bounding boxes, stored in the PLM database (step 600). Hence, the proposed solution allows a user to rapidly display a view of the set of objects while allowing for selecting objects in the view, without the need for loading the complete and exact representations of all the objects of the view when the user is looking for particular objects to work on.
摘要翻译：本发明涉及用于在包含建模对象的PLM数据库中选择对象的过程，装置和程序。该过程包括在图形用户界面中显示（步骤620）数据库的一组对象的视图。所述视图是非关联视图，即从系统的观点来看，所述视图的图形元素不根据集合的各个对象进行分区。就此而言，该过程可以包括在显示步骤之前聚集（步骤610）该对象集合中的各个对象的表示以形成显示的视图。从而视野更加迅速。然后，在用户定义（步骤630）音量时，确定（步骤640-650）与非关联视图中的音量相交的对象。该过程包括搜索数据库并根据交集识别用户对象。例如使用存储在PLM数据库中的边界框（步骤600）。因此，所提出的解决方案允许用户快速显示该组对象的视图，同时允许在视图中选择对象，而不需要在用户正在寻找时加载视图的所有对象的完整和精确表示要处理的特定对象。

3. 发明公开

EP3157628A1 SYSTEM AND COMPUTER PROGRAM PRODUCT FOR INVERSE TREATMENT PLANNING. 有权
标题翻译：系统计算机计算机系统。
公开(公告)号：EP3157628A1
公开(公告)日：2017-04-26
申请号：EP15731534.2
申请日：2015-06-11
申请人： Intuitive Therapeutics SA
发明人： MARTIN, André , SALZMANN, Daniel
IPC分类号： A61N5/10
CPC分类号： A61N5/1031 , A61B6/5294 , A61B6/54 , A61N5/103 , A61N5/1038 , A61N5/1042 , A61N5/1047 , A61N5/1071 , A61N5/1075 , G01T1/2914 , G05B2219/33079 , G06F17/16 , G06F17/30271
摘要： The present invention concerns an inverse treatment planning system. The system includes, at least a data bus system (102), a memory (106) coupled to the data bus system (102), and a processing unit (104) coupled to the data bus system (102). The processing unit (104) is configured to execute the instructions to pre-compute (10) a set of individual dose shots (aj), each individual dose shot having a predetermined location inside and/or outside a target area, a size and a shape. The processing unit also associates (40) a weight (sj) to each individual dose shot (aj), based on one or more constraints (20). The processing unit (104) further executes the instructions to find (30) the sparsest subset of individual dose shots, so as to satisfy said one or more constraints (20).
摘要翻译：本发明涉及一种用于线性加速器的辐射反向治疗计划系统，包括：辐射源，其被配置用于传送各个剂量射击（aj），每个单独的剂量射击在目标区域内部和/或外部具有预定位置和入射角至少数据总线系统（102）的大小和形状，耦合到数据总线系统（102）的存储器（106），其中存储器（106）包括计算机可用程序代码，以及处理单元（104））耦合到所述数据总线系统（102），其中所述处理单元（104）被配置为执行所述计算机可用程序代码以预先计算（10）一组单独剂量镜头（aj），所述联合（40）重量（20），其特征在于，所述处理单元（104）执行所述计算机可用程序代码以找到（30）所述单个剂量镜头的最小子集，以便满足所述一个或多个约束（20）。

4. 发明公开

EP2994853A4 EFFICIENT IMAGE MATCHING FOR LARGE SETS OF IMAGES 审中-公开
标题翻译： EFFIZIENTER BILDVERGLEICHFÜRGROSSE MENGEN VON BILDERN
公开(公告)号：EP2994853A4
公开(公告)日：2016-12-21
申请号：EP14794756
申请日：2014-05-07
申请人： PICSCOUT (ISRAEL) LTD
发明人： LAVI URI , GOZ ELI , BEGELMAN GREGORY
IPC分类号： G06K9/62 , G06F17/30
CPC分类号： G06F17/30271 , G06F17/30097 , G06F17/30109 , G06F17/30256 , G06F17/30259 , G06F17/3028 , G06K9/4671 , G06K9/6857 , G06K2209/29
摘要： A system and method to detect similarities between images. The system and method allow comparisons between a query image and one or more catalog images in a manner that is resilient to scanning, scaling, rotating, cropping and other distortions of the query image. The system includes an image processing module that determines and/or calculates principle features of a catalog image and constructs a feature vector using one or more of the principle features. The system also includes a matching module that matches a query image to one or more catalog images. The system finds matches based on a distance measure of features present in the query image and features present in the catalog images.
摘要翻译：一种检测图像相似性的系统和方法。该系统和方法允许以对于查询图像的扫描，缩放，旋转，裁剪和其它失真有弹性的方式在查询图像和一个或多个目录图像之间进行比较。该系统包括图像处理模块，其确定和/或计算目录图像的主要特征，并使用一个或多个主要特征构建特征向量。该系统还包括匹配模块，将查询图像与一个或多个目录图像相匹配。系统根据查询图像中存在的特征的距离度量和目录图像中存在的特征，找到匹配。

5. 发明公开

EP3086238A1 VISUAL SEARCH METHOD, SYSTEM AND MOBILE TERMINAL 审中-公开
标题翻译： VISUELLES SUCHVERFAHREN，SYSTEM UND MOBILESENDGERÄT
公开(公告)号：EP3086238A1
公开(公告)日：2016-10-26
申请号：EP14801411.1
申请日：2014-06-10
申请人： ZTE Corporation
发明人： LIU, Ming
IPC分类号： G06F17/30
CPC分类号： G06F17/30277 , G06F17/30244 , G06F17/30256 , G06F17/30271 , G06F17/30274 , G06F17/30339 , G06F17/30371
摘要： The present disclosure discloses a visual search method, system and a mobile terminal. The visual search method includes: collecting, by a mobile terminal, an image, acquiring an image complexity coefficient of the image, sending the image to a serving end for the serving end to perform image search and receiving a search result fed back by the serving end when a value of the image complexity parameter is not within a preset range; and performing image search locally in a mobile terminal according to the image when the value of the image complexity parameter is within the preset range.
摘要翻译：本公开公开了一种视觉搜索方法，系统和移动终端。视觉搜索方法包括：由移动终端收集图像，获取图像的图像复杂度系数，将图像发送到服务端的服务端，以进行图像搜索，并接收由服务端反馈的搜索结果当图像复杂度参数的值不在预设范围内时结束; 以及当所述图像复杂度参数的值在所述预设范围内时，根据所述图像在移动终端中本地执行图像搜索。

6. 发明公开

EP3084642A1 SYSTEMS, METHODS, AND APPARATUS FOR IMAGE RETRIEVAL 审中-公开
标题翻译： SYSTEME，VERFAHREN UND VORRICHTUNG ZUM ABRUF VON BILDERN
公开(公告)号：EP3084642A1
公开(公告)日：2016-10-26
申请号：EP14825555.7
申请日：2014-12-19
申请人： Qualcomm Incorporated
发明人： GAO, Dashan , ZHONG, Xin , KANDHADAI, Ananthapadmanabhan Arasanipalai , LAVER, Steven Douglas
IPC分类号： G06F17/30
CPC分类号： G06F17/30268 , G06F3/04842 , G06F3/0488 , G06F17/2765 , G06F17/30271 , G06F17/30705 , G06F17/3079 , G06F17/30817 , G06F17/30831 , G06F17/30867 , G06K9/00664 , G06K9/00671 , G06K9/00711 , G06K9/22 , G06K9/3241 , G06T7/20 , G06T7/70 , G06T11/00 , G06T11/60 , G06T2207/10004 , G06T2207/10016 , G06T2207/20076
摘要： A method of image retrieval includes obtaining information identifying a plurality of selected objects and selecting one among a plurality of candidate geometrical arrangements. This method also includes, by at least one processor, and in response to the selecting, identifying at least one digital image, among a plurality of digital images, that depicts the plurality of selected objects arranged according to the selected candidate geometrical arrangement.
摘要翻译：生成元数据的方法包括使用至少一个数字图像来选择多个对象，其中所述至少一个数字图像描绘与物理空间相关的多个对象。该方法还包括至少一个处理器并且基于指示位置空间中所选择的对象的位置的信息，产生识别所选对象的多个候选几何布置中的一个的元数据。

7. 发明公开

EP3031032A1 A METHOD AND SYSTEM FOR LINKING PRINTED OBJECTS WITH ELECTRONIC CONTENT 审中-公开
标题翻译： VERFAHREN UND系统ZUR VERBINDUNG GEDRUCKTER OBJEKTE MIT ELEKTRONISCHEN INHALTEN
公开(公告)号：EP3031032A1
公开(公告)日：2016-06-15
申请号：EP13827861.9
申请日：2013-08-08
申请人： WINK-APP Ltd.
发明人： ARAD, Itai , HERMAN, Tsur
IPC分类号： G06T1/00 , G06F17/30
CPC分类号： G06K9/00456 , G06F17/30271 , G06F17/30879 , G06F17/30914 , G06K9/00463 , G06T2207/30176
摘要： A method for linking objects to electronic content is disclosed. The method includes providing a digital copy of a layout of an object; processing the digital copy for distinguishing text objects each associated with a visual form of at least portion of a word or a combination of adjacent words in the layout, and determining bounding boxes of the text objects; coding each text object in a binary descriptor corresponding to its visual form, whereby the coding includes: scaling the bounding box of the text object to a fixed size binary image, and flattening the binary image to form the binary descriptor; representing the layout in a binary vector formed as an array of the binary descriptors of at least the text objects in the layout; and assigning hashwords to the binary descriptors, for converting the binary vector into a searchable text form.
摘要翻译：本发明涉及一种将打印对象与电子内容相链接的方法，包括：a）将至少一个打印对象的数字拷贝提供给服务器的数据库，其中所述数字副本至少表示所述打印对象的一部分，其中内容数字拷贝和打印对象的布局是相同的; b）通过提取和保存数字副本中的每个链接的坐标或通过外部链接列表来提供所述数字副本的布局中的至少一个部分与电子内容的关联; c）处理所述数字副本以区分两种类型的对象：文本对象和非文本对象，其中每个文本对象表示相对于任何方向的单词的至少部分或至少两个或更多个相邻单词的组合，所述印刷物体的平面; d）根据所述对象的视觉形状及其参考位置，根据所述打印对象的布局上的定义的坐标对来自两种类型对象的每个对象进行编码，从而将所述数字副本表示为二进制格式的向量阵列; e）创建类似二进制向量的集群，并将随机数组的字符分配给每个所述集群，并将所述字符数组保存为“哈希字”的编码字典，从而将所述二进制向量转换成可搜索的文本形式; f）通过移动设备捕获所述打印对象的至少一部分的图像; g）处理所述捕捉的图像以区分文本对象和面向图像的对象，并且根据其视觉形状及其相对于所述打印对象的布局的参考位置对每个所述对象进行编码，从而将所述捕获的数字图像表示为阵列的二进制格式的向量; h）经由通信网络将所述二进制向量数组发送到所述服务器; i）将每个聚类向量转换为一个杂散字; j）执行文本搜索以识别基本上最匹配从数字副本编码的哈希字的相应的哈希字，其中将所述阵列转换成哈希字在本地在移动设备之前在发送之前完成，或者在所述服务器之后远程地在所述服务器之后完成发送; k）在表示所捕获图像的向量阵列之间执行最佳匹配之间的几何匹配; l）在最佳匹配数字拷贝上计算拍摄部分的位置，并提取捕获图像所针对的特定链接; 以及m）将所述相关联的电子内容或其相应链接从所述服务器发送到所述移动设备。

8. 发明公开

EP2352105A4 METHOD AND SYSTEM OF GRAPHICS DESCRIPTION AND TRANSFORMATION 审中-公开
标题翻译：方法和系统描述和变换图形学报
公开(公告)号：EP2352105A4
公开(公告)日：2014-05-07
申请号：EP09838103
申请日：2009-07-29
申请人： STATE GRID CORP CHINA
发明人： XIN YAOZHONG , LI WEI , SHEN GUOHUI , TAO HONGZHU , HUANG KUN , BIAN XIAOYU , LI YAPING , YAO JIANGUO , ZHAO LIN , LI YISONG , SHANG XUEWEI
IPC分类号： G06F17/30
CPC分类号： G06F17/30265 , G06F17/30271

9. 发明公开

EP2608062A1 Method of automatic management of images in a collection of images and corresponding device 审中-公开
标题翻译：自动管理图像集合和相应设备中图像的方法
公开(公告)号：EP2608062A1
公开(公告)日：2013-06-26
申请号：EP11306771.4
申请日：2011-12-23
申请人： Thomson Licensing
发明人： Montalvo, Luis , Defrance, Serge , Gendrot, Rémy , Lefebre, Frédéric
IPC分类号： G06F17/30
CPC分类号： G06K9/627 , G06F17/30038 , G06F17/30268 , G06F17/30271 , G06F17/3028
摘要： The present invention relates to the field of management of image data in data storage. In particular, the present invention relates to a method and device for automatic detection of duplicate images in data storage and corresponding device while taking into account user perception of what he considers to be duplicate images, which method and device are particularly efficient with regard to the personalized, automatic management of large amounts of image data.
摘要翻译：数据存储中图像数据的管理领域特别地，本发明涉及一种用于在考虑用户对他认为是复制图像的感知的情况下自动检测数据存储器和相应设备中的复制图像的方法和设备，该方法和设备对于个性化的，自动管理大量的图像数据。

10. 发明公开

EP1447767A3 Image document administration method 审中-公开
标题翻译： Bilddokumentenverwaltungsverfahren
公开(公告)号：EP1447767A3
公开(公告)日：2005-06-15
申请号：EP04250777.2
申请日：2004-02-13
申请人： CANON KABUSHIKI KAISHA
发明人： Ohta, Ken-ichi Canon Kabushiki Kaisha , Tanioka, Hiroshi Canon Kabushiki Kaisha , Usami, Akihiro Canon Kabushiki Kaisha , Kaneda, Kitahiro Canon Kabushiki Kaisha , Ito, Hirohiko Canon Kabushiki Kaisha , Kato, Shinichi Canon Kabushiki Kaisha , Akiba, Tomohiro Canon Kabushiki Kaisha , Kanatsu, Tomotoshi Canon Kabushiki Kaisha , Misawa, Reiji Canon Kabushiki Kaisha , Terao, Yoshihide Canon Kabushiki Kaisha , Uzawa, Mitsuru Canon Kabushiki Kaisha
IPC分类号： G06K9/20 , G06K9/48 , G06T9/20 , G06F17/30
CPC分类号： G06K9/00456 , G06F17/30271 , G06K9/48 , H04N1/4177
摘要： Original digital data stored in a memory is searched for on the basis of an input image, difference information is extracted by comprising the retrieved original digital data and the input image, and the difference information is composited to the original digital data. Furthermore, digital data generated by composition is stored in the memory. Also, original digital data stored in a memory is searched for on the basis of an input image, and when no original digital data is retrieved, the input image is converted into vector data, and the image that has been converted into the vector data is stored as digital data in the memory. Moreover, region segmentation information obtained in a block selection step and an input image are composited, the composite image is displayed on an operation screen of an MFP, and a rectangular block to be vectorized is designated as a specific region from the displayed region segmentation information. As a method of designating the specific region, for example, the user designates one or a plurality of rectangular blocks in an image using a pointing device.

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