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. 发明授权

EP2859506B1 SYSTEM AND METHOD FOR DETECTION CARGO CONTAINER SEALS 有权
公开(公告)号：EP2859506B1
公开(公告)日：2018-08-22
申请号：EP13804298.1
申请日：2013-06-11
申请人： Hi-Tech Solutions Ltd.
发明人： HOFMAN, Yoram
IPC分类号： G06K9/62 , G06Q10/08 , G06K9/00 , G06K9/72
CPC分类号： G06T7/001 , G06K9/00 , G06K9/00456 , G06K9/00684 , G06K9/00697 , G06K9/3241 , G06K9/52 , G06K9/62 , G06K9/6201 , G06K9/6202 , G06K9/72 , G06K2009/4666 , G06Q10/0833
摘要： Systems and methods are disclosed for detecting container seals. In one implementation, a processing device receives one or more images and processes the one or more images to identify one or more areas of interest within at least one of the one or more images, the one or more areas of interest including one or more areas of the one or more images within which a container seal is relatively likely to be present. The processing device compares the one or more identified areas of interest with one or more templates, each of the one or more templates being associated with one or more respective seal types. The processing device identifies, based on the comparison, one or more matches between the one or more identified areas and the one or more templates, and provides, based on the identification of the one or more matches, an identification of the container seal.

2. 发明公开

EP3346419A1 FEATURE EXTRACTION AND CLASSIFICATION METHOD BASED ON SUPPORT VECTOR DATA DESCRIPTION AND SYSTEM THEREOF 审中-公开
公开(公告)号：EP3346419A1
公开(公告)日：2018-07-11
申请号：EP16907682.5
申请日：2016-12-19
申请人： Soochow University
发明人： ZHANG, Li , LU, Xingning , WANG, Bangjun , LI, Fanzhang , ZHANG, Zhao
IPC分类号： G06K9/62
CPC分类号： G06N99/005 , G06F17/5009 , G06F2217/16 , G06K9/62 , G06N3/08
摘要： A feature extraction and classification method based on support vector data description is provided, which includes: calculating, for each sample, Euclidean distances from the sample to spherical centers of multiple hypersphere models corresponding to different data categories, where the multiple hypersphere models are acquired in advance by training using a support vector data description algorithm(s101); substituting, for each sample, the Euclidean distances and radiuses of the hypersphere models respectively corresponding to the Euclidean distances into a new feature relation equation, to acquire a new feature sample corresponding to the sample, where the new feature samples constitute a new feature sample set(s102); and performing classification on the new feature sample set using a preset classification algorithm, to acquire a classification result(s103). With the method, a calculation amount in feature extraction can be reduced, and the speed of data classification can be increased. A feature extraction and classification system based on support vector data description having the above advantages is further provided.

3. 发明公开

EP3321859A1 OPTICAL FIBER PERIMETER INTRUSION SIGNAL IDENTIFICATION METHOD AND DEVICE, AND PERIMETER INTRUSION ALARM SYSTEM 失效
标题翻译：光纤周界信号识别方法和装置以及周界入侵报警系统
公开(公告)号：EP3321859A1
公开(公告)日：2018-05-16
申请号：EP16840792.2
申请日：2016-08-26
申请人： Nuctech Company Limited
发明人： CONG, Yushu , JIANG, Ting , XU, Jun , YANG, Jie , GAO, Baisong , XU, Huikang , TONG, Yian , DONG, Kun , MAO, Xianhui
IPC分类号： G06K9/62 , G08B13/186
CPC分类号： G06K9/62 , G08B13/186
摘要： An optical fiber perimeter intrusion signal identification method (10), identification device (30) and optical fiber perimeter intrusion alarm system (40). The identification method (10) comprises: acquiring a real-time signal from a monitoring signal of an optical fiber perimeter monitoring system; pre-processing the real-time signal to remove noises; determining whether the denoised real-time signal is an intrusion signal; if so, truncating the intrusion signal to acquire signal segments of the intrusion signal, and extracting relevant characteristic variables of respective signal segments; and classifying the intrusion signal according to a
classification rule determined by a pre-established decision tree model and the relevant characteristic variables of the signal segments. The method is simple, easy to implement, and has a high capability and good effect of intrusion signal classification.
摘要翻译：一种光纤周界入侵信号识别方法（10），识别装置（30）和光纤周界入侵报警系统（40）。该识别方法（10）包括：从光纤周边监测系统的监测信号中获取实时信号; 预处理实时信号以消除噪音; 确定去噪后的实时信号是否是入侵信号; 如果是，则截取入侵信号以获取入侵信号的信号段，并提取各个信号段的相关特征变量; 根据预先建立的决策树模型确定的分类规则和所述信号分段的相关特征变量对入侵信号进行分类。该方法简单，易于实现，具有较高的能力和良好的入侵信号分类效果。

4. 发明公开

EP3287953A4 INPUT PROCESSING PROGRAM, INPUT PROCESSING DEVICE, INPUT PROCESSING METHOD, CHARACTER IDENTIFICATION PROGRAM, CHARACTER IDENTIFICATION DEVICE, AND CHARACTER IDENTIFICATION METHOD 审中-公开
公开(公告)号：EP3287953A4
公开(公告)日：2018-04-11
申请号：EP15889930
申请日：2015-04-24
申请人： FUJITSU LTD
发明人： MATSUDA YUGO , TSUYUKI YASUHIRO
IPC分类号： G06K9/62 , G06F3/023 , G06F3/0488 , G06F17/24 , G06K9/03 , G06K9/22
CPC分类号： G06F17/242 , G06F3/0233 , G06F3/0488 , G06F3/04883 , G06K9/00416 , G06K9/033 , G06K9/222 , G06K9/62 , G06K2209/01
摘要： A computer is caused to execute a process. The process includes receiving a handwriting input on a display screen on which a character is displayed; and in response to detecting that the handwriting input has been performed at a position corresponding to a display position of a specific character displayed on the display screen, executing a process of changing the specific character into a character recognized with respect to the handwriting input.

5. 发明授权

EP2946316B1 INDEXING APPLICATION PAGES OF NATIVE APPLICATIONS 有权转让
标题翻译：索引本土应用程序的应用程序页面
公开(公告)号：EP2946316B1
公开(公告)日：2018-04-11
申请号：EP14740959.3
申请日：2014-01-13
申请人： Google LLC
发明人： CHANG, Lawrence , JUNG, Chaesang , YEOM, Jaehyun , LEE, Sang-il
IPC分类号： G06F17/30 , G06F3/048 , G06F3/14 , G06K9/32 , G06K9/62 , G06F9/455
CPC分类号： G06F17/30876 , G06F9/45533 , G06F17/30321 , G06F17/30336 , G06F17/30864 , G06K9/3283 , G06K9/62 , G06K2209/01
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for indexing application pages of native applications that operate independent of a browser application on a user device. In one aspect, a method includes instantiating a virtual machine emulating an operating system of a user device; instantiating, within the virtual machine, a native application that generates application pages for display on a user device within the native application; accessing, within the virtual machine, application pages of the native application, and for each of the application pages: generating application page data describing content of the application page, the content described by the application page data including text that a user device displays on the application page when the user device displays the application page; and indexing the application page data for the native application in an index that is searchable by a search engine.

6. 发明公开

EP3227861A4 IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND COMPUTER-READABLE STORAGE MEDIUM 审中-公开
公开(公告)号：EP3227861A4
公开(公告)日：2018-01-17
申请号：EP15864831
申请日：2015-11-27
申请人： RICOH CO LTD
发明人： EMORI MOTOTSUGU
IPC分类号： G06T11/60 , G06K9/62
CPC分类号： G06F17/242 , G06F3/04883 , G06F3/1454 , G06F17/214 , G06K9/00416 , G06K9/00422 , G06K9/62 , G06T11/203 , G06T11/60 , G09G2340/12 , H04N1/387
摘要： An image processing device includes a handwriting renderer, an image renderer, an external image renderer, a serializer, a creator, a recognizer, and a concatenation unit. The handwriting renderer is configured to render a stroke on a first layer. The image renderer is configured to render an image on a second layer lower than the first layer. The external image renderer is configured to render an external image on a third layer lower than the second layer. The serializer is configured to convert the stroke rendered on the first layer and the images rendered on the second and third layers into text data. The creator is configured to create document data corresponding to one page based on the text data. The recognizer is configured to acquire a character string from the stroke. The concatenation unit is configured to concatenate adjacent characters on the string with an unnecessary space therebetween being deleted.

7. 发明公开

EP2525306A4 PATTERN RECOGNITION DEVICE, PATTERN RECOGNITION METHOD AND PATTERN RECOGNITION-USE PROGRAM 审中-公开
公开(公告)号：EP2525306A4
公开(公告)日：2018-01-10
申请号：EP10843002
申请日：2010-12-20
申请人： NEC CORP
发明人： SATO ATSUSHI
IPC分类号： G06N99/00 , G06K9/62 , G06N3/08
CPC分类号： G06K9/62 , G06K9/6269 , G06N3/08 , G06N99/005
摘要： Loss calculation means calculates a loss of a feature vector for each class, the feature vector indicating a feature of data belonging to the class. Loss difference calculation means calculates a total sum of differences of losses between the classes on a basis of the loss calculated for each class. Recognition dictionary creation means creates a recognition dictionary on a basis of a total sum of losses calculated for the classes and the total sum of loss differences between the classes. The recognition dictionary creation means corrects, on a basis of an input feature vector, a recognition dictionary so as to minimize a sum of the total sum of losses for the classes calculated by the loss calculation means and the total sum of loss differences between the classes calculated by the loss difference calculation means, and the pattern classification means classifies a pattern of data using the corrected recognition dictionary.

8. 发明公开

EP2993618A1 DOMAIN ADAPTATION FOR IMAGE CLASSIFICATION WITH CLASS PRIORS 审中-公开
标题翻译： DOMÄNENANPASSUNGZUR BILDKLASSIFIZIERUNG MIT KLOCENPRIOREN
公开(公告)号：EP2993618A1
公开(公告)日：2016-03-09
申请号：EP15181884.6
申请日：2015-08-20
申请人： Xerox Corporation
发明人： CHIDLOVSKII, Boris , CSURKA, Gabriela
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/6259 , G06K9/00624 , G06K9/00771 , G06K9/00785 , G06K9/46 , G06K9/62 , G06K9/6217 , G06K9/6256 , G06K9/6257 , G06K9/6267 , G06K9/627 , G06K9/6288
摘要： In camera-based object labeling, boost classifier f T x = ∑ r = 1 M β r h r x is trained to classify an image represented by feature vector x using a target domain training set D T of labeled feature vectors representing images acquired by the same camera and a plurality of source domain training sets D S 1 ,...,D S N acquired by other cameras. The training applies an adaptive boosting (AdaBoost) algorithm to generate base classifiers h r (x) and weights β r . The r th iteration of the AdaBoost algorithm trains candidate base classifiers h r k x each trained on a training set D T UD S k , and selects h r (x) from previously trained candidate base classifiers. The target domain training set D T may be expanded based on a prior estimate of the labels distribution for the target domain. The object labeling system may be a vehicle identification system, a machine vision article inspection system, or so forth.
摘要翻译：在基于相机的对象标签中，训练分类器f T x ='r = 1 M 2 rhrx被训练为使用由表示相同相机获取的图像的标记特征向量的目标域训练集DT来对由特征向量x表示的图像进行分类以及由其他相机获取的多个源域训练集DS 1，...，DS N。训练采用自适应增强（AdaBoost）算法生成基本分类器h r（x）和权重r。 AdaBoost算法的第r次迭代训练在训练集D T UD S k上训练的候选基本分类器h r k x，并且从先前训练的候选基本分类器中选择h r（x）。可以基于目标域的标签分布的先前估计来扩展目标域训练集D T。对象标注系统可以是车辆识别系统，机器视觉物品检查系统等。

9. 发明公开

EP2946316A1 INDEXING APPLICATION PAGES OF NATIVE APPLICATIONS 有权转让
标题翻译： INDEXIERUNG VON ANWENDUNGSSEITEN NATIVER ANWENDUNGEN
公开(公告)号：EP2946316A1
公开(公告)日：2015-11-25
申请号：EP14740959.3
申请日：2014-01-13
申请人： Google Inc.
发明人： CHANG, Lawrence , JUNG, Chaesang , YEOM, Jaehyun , LEE, Sang-il
IPC分类号： G06F17/30 , G06F3/048 , G06F3/14
CPC分类号： G06F17/30876 , G06F9/45533 , G06F17/30321 , G06F17/30336 , G06F17/30864 , G06K9/3283 , G06K9/62 , G06K2209/01
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for indexing application pages of native applications that operate independent of a browser application on a user device. In one aspect, a method includes instantiating a virtual machine emulating an operating system of a user device; instantiating, within the virtual machine, a native application that generates application pages for display on a user device within the native application; accessing, within the virtual machine, application pages of the native application, and for each of the application pages: generating application page data describing content of the application page, the content described by the application page data including text that a user device displays on the application page when the user device displays the application page; and indexing the application page data for the native application in an index that is searchable by a search engine.
摘要翻译：方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于索引独立于用户设备上的浏览器应用的本机应用程序的应用页面。一方面，一种方法包括实例化仿真用户设备的操作系统的虚拟机; 在虚拟机内实例化生成应用页面以在本机应用内的用户设备上显示的本地应用程序; 在虚拟机内访问本机应用的应用页面以及每个应用页面：生成描述应用页面的内容的应用页面数据，由应用页面数据描述的内容，包括用户设备在其上显示的文本用户设备显示应用页面时的应用页面; 以及在搜索引擎可搜索的索引中索引本机应用的应用页面数据。

10. 发明公开

EP2722819A4 CHARACTER REGION PIXEL IDENTIFICATION DEVICE AND METHOD THEREOF 审中-实审
标题翻译：装置用于识别PIXEL SIGN区及其方法
公开(公告)号：EP2722819A4
公开(公告)日：2015-06-24
申请号：EP11867581
申请日：2011-09-09
申请人： EIZO CORP
发明人： CHEN HAIFENG , NAKAO MASASHI
IPC分类号： G06T7/40 , G06K9/32 , G06K9/38 , G06K9/46 , G09G3/20
CPC分类号： G09G3/20 , G06K9/325 , G06K9/38 , G06K9/4642 , G06K9/62 , G06K2209/01

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