公开(公告)号：EP1429257B1

公开(公告)日：2015-08-12

申请号：EP03028508.4

申请日：2003-12-10

申请人： Xerox Corporation

发明人： Privault, Caroline ,  Poirier, Herve

IPC分类号： G06F17/27

CPC分类号： G06F17/2755 ,  G06F17/277 ,  G06F17/2775

公开(公告)号：EP2846290A2

公开(公告)日：2015-03-11

申请号：EP14179609.4

申请日：2014-08-01

申请人： Xerox Corporation

发明人： Sandhawalia, Harsimrat Singh ,  Rodriguez Serrano, Jose Antonio ,  Poirier, Herve ,  Csurka, Gabriela

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62

CPC分类号： G01B11/24 ,  G01B11/2518 ,  G06K9/0014 ,  G06K9/00147 ,  G06K9/00187 ,  G06K9/00214 ,  G06K9/4676 ,  G06K9/54 ,  G06K9/6247

摘要： Methods, systems and processor-readable media for vehicle classification. In general, one or more vehicles can be scanned utilizing a laser scanner to compile data indicative of an optical profile of the vehicle(s). The optical profile associated with the vehicle(s) is then pre-processed. Particular features are extracted from the optical profile following pre-processing of the optical profile. The vehicle(s) can be then classified based on the particular features extracted from the optical feature. A segmented laser profile is treated as an image and profile features that integrate the signal in one of the two directions of the image and Fisher vectors which aggregate statistics of local "patches" of the image are computed and utilized as part of the extraction and classification process.

摘要翻译： 用于车辆分类的方法，系统和处理器可读介质。 通常，可以使用激光扫描器扫描一个或多个车辆，以编译指示车辆的光学轮廓的数据。 然后，与车辆相关联的光学轮廓被预处理。 在光学轮廓的预处理之后，从光学轮廓提取特定特征。 然后可以基于从光学特征提取的特定特征对车辆进行分类。 将分割的激光轮廓视为图像，并且将图像的两个方向中的一个方向上的信号进行整合的图像特征和计算图像的局部“斑块”的统计信息的Fisher向量，并将其用作提取和分类的一部分 处理。

公开(公告)号：EP2887333B1

公开(公告)日：2018-08-01

申请号：EP14195978.3

申请日：2014-12-02

申请人： Xerox Corporation

发明人： Meunier, Jean-Luc ,  Estehghari, Saghar ,  Poirier, Herve

IPC分类号： G08G1/017 ,  G08G1/04 ,  H04L9/08 ,  H04L9/32 ,  G08G1/054 ,  G06K9/00

CPC分类号： G06K9/00161 ,  G06K9/00577 ,  G06K2009/0059 ,  G08G1/0175 ,  G08G1/04 ,  G08G1/054 ,  H04L9/0866 ,  H04L9/0872 ,  H04L9/3247

摘要： A system and method for preserving privacy of evidence are provided. In the method, an encrypted first image is generated by encrypting a first image acquired at a first location with a symmetric cryptographic key that is based on first information such as a license plate number extracted from the first image and first metadata associated with the first image, such as a time at which the first image was acquired. When a link is established between a second image and the first image, for example, through visual signature matching, the symmetric cryptographic key can be reconstructed, without having access to the first image, but based instead on the first metadata and information extracted from the second image. The reconstructed symmetric cryptographic key can then be used for decryption of the encrypted image to establish evidence that the license plate number was indeed extracted from the first image.

公开(公告)号：EP1429257A3

公开(公告)日：2006-06-07

申请号：EP03028508.4

申请日：2003-12-10

申请人： Xerox Corporation

发明人： Privault, Caroline ,  Poirier, Herve

IPC分类号： G06F17/27

CPC分类号： G06F17/2755 ,  G06F17/277 ,  G06F17/2775

摘要： Words of an input string are morphologically analyzed to identify their alternative base forms and parts of speech. The analyzed words of the input string are used to compile the input string into a first finite-state network. The first finite-state network is matched with a second finite-state network of multiword expressions to identify all subpaths of the first finite-state network that match one or more complete paths in the second finite-state network. Each matching subpath of the first finite-state network and path of the second finite-state network identify a multiword expression in the input string. The morphological analysis is performed without disambiguating words and without segmenting the input string into sentences in the input string to compile the first finite-state network with at least one path that identifies alternative base forms or parts of speech of a word in the input string.

公开(公告)号：EP2846290A3

公开(公告)日：2015-08-26

申请号：EP14179609.4

申请日：2014-08-01

申请人： Xerox Corporation

发明人： Sandhawalia, Harsimrat Singh ,  Rodriguez Serrano, Jose Antonio ,  Poirier, Herve ,  Csurka, Gabriela

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62

CPC分类号： G01B11/24 ,  G01B11/2518 ,  G06K9/0014 ,  G06K9/00147 ,  G06K9/00187 ,  G06K9/00214 ,  G06K9/4676 ,  G06K9/54 ,  G06K9/6247

摘要： Methods, systems and processor-readable media for vehicle classification. In general, one or more vehicles can be scanned utilizing a laser scanner to compile data indicative of an optical profile of the vehicle(s). The optical profile associated with the vehicle(s) is then pre-processed. Particular features are extracted from the optical profile following pre-processing of the optical profile. The vehicle(s) can be then classified based on the particular features extracted from the optical feature. A segmented laser profile is treated as an image and profile features that integrate the signal in one of the two directions of the image and Fisher vectors which aggregate statistics of local "patches" of the image are computed and utilized as part of the extraction and classification process.

摘要翻译： 用于车辆分类的方法，系统和处理器可读介质。 通常，可以利用激光扫描仪来扫描一个或多个车辆以编译指示车辆的光学轮廓的数据。 然后对与车辆相关联的光学轮廓进行预处理。 在光学轮廓的预处理之后从光学轮廓提取特定特征。 然后可以基于从光学特征提取的特定特征对车辆进行分类。 分段激光轮廓被视为图像和轮廓特征，其将图像的两个方向中的一个上的信号整合，并且计算图像的局部“斑块”的统计数据的Fisher向量作为提取和分类的一部分 处理。

公开(公告)号：EP1429257A2

公开(公告)日：2004-06-16

申请号：EP03028508.4

申请日：2003-12-10

申请人： Xerox Corporation

发明人： Privault, Caroline ,  Poirier, Herve

IPC分类号： G06F17/27

CPC分类号： G06F17/2755 ,  G06F17/277 ,  G06F17/2775

摘要： Words of an input string are morphologically analyzed to identify their alternative base forms and parts of speech. The analyzed words of the input string are used to compile the input string into a first finite-state network. The first finite-state network is matched with a second finite-state network of multiword expressions to identify all subpaths of the first finite-state network that match one or more complete paths in the second finite-state network. Each matching subpath of the first finite-state network and path of the second finite-state network identify a multiword expression in the input string. The morphological analysis is performed without disambiguating words and without segmenting the input string into sentences in the input string to compile the first finite-state network with at least one path that identifies alternative base forms or parts of speech of a word in the input string.

摘要翻译： 输入字符串的词语进行形态分析，以确定其替代基本形式和词性。 输入字符串的分析词用于将输入字符串编译成第一个有限状态网络。 第一有限状态网络与多字表达式的第二有限状态网络匹配，以识别与第二有限状态网络中的一个或多个完整路径匹配的第一有限状态网络的所有子路径。 第一有限状态网络的每个匹配子路径和第二有限状态网络的路径在输入字符串中标识多字表达式。 进行形态分析而不消除歧义词语，而不将输入字符串分割成输入字符串中的句子，以编译第一有限状态网络，其中至少一个路径识别输入字符串中单词的替代基本形式或词性。

公开(公告)号：EP1018683A2

公开(公告)日：2000-07-12

申请号：EP99125248.7

申请日：1999-12-17

申请人： Xerox Corporation

发明人： Poirier, Herve ,  Tarbouriech, Nelly ,  Harrus, Gilbert

IPC分类号： G06F9/44

CPC分类号： G06F8/30 ,  G06F17/289

摘要： An executable for a new linguistic service is produced using preexisting source code for an ancestor service that is a less specified ancestor of the new linguistic service in a hierarchy. The preexisting source code is modified, such as by further specifying it, to produce modified source code for responding to requests for the new linguistic service, where each request identifies the new linguistic service and indicates linguistic data on which it is to be performed. The modified source code is then used to produce the executable for the new linguistic service. The preexisting source code can, for example, define a top-level class in an object-oriented programming language, with common parameters including input parameters with information for obtaining the linguistic data and result parameters with information for returning results of the new linguistic service.

摘要翻译： 用于新语言服务的可执行程序是使用先前存在的源代码来生成的，祖先服务是层次结构中新语言服务的较少指定的祖先。 预先存在的源代码被修改，例如通过进一步指定它来产生用于响应新语言服务的请求的修改的源代码，其中每个请求标识新的语言服务并指示要在其上执行的语言数据。 然后，修改的源代码用于生成新语言服务的可执行文件。 例如，预先存在的源代码可以定义面向对象的编程语言中的顶级类，其中包含具有用于获得语言数据和结果参数的信息的输入参数的公共参数以及用于返回新语言服务结果的信息。

公开(公告)号：EP2887333A1

公开(公告)日：2015-06-24

申请号：EP14195978.3

申请日：2014-12-02

申请人： Xerox Corporation

发明人： Meunier, Jean-Luc ,  Estehghari, Saghar ,  Poirier, Herve

IPC分类号： G08G1/017 ,  G08G1/04 ,  H04L9/08 ,  H04L9/32 ,  G08G1/054

CPC分类号： G06K9/00161 ,  G06K9/00577 ,  G06K2009/0059 ,  G08G1/0175 ,  G08G1/04 ,  G08G1/054 ,  H04L9/0866 ,  H04L9/0872 ,  H04L9/3247

摘要： A system and method for preserving privacy of evidence are provided. In the method, an encrypted first image is generated by encrypting a first image acquired at a first location with a symmetric cryptographic key that is based on first information such as a license plate number extracted from the first image and first metadata associated with the first image, such as a time at which the first image was acquired. When a link is established between a second image and the first image, for example, through visual signature matching, the symmetric cryptographic key can be reconstructed, without having access to the first image, but based instead on the first metadata and information extracted from the second image. The reconstructed symmetric cryptographic key can then be used for decryption of the encrypted image to establish evidence that the license plate number was indeed extracted from the first image.

摘要翻译： 提供了一种保护证据隐私的系统和方法。 在该方法中，通过使用基于从第一图像提取的第一信息（例如从第一图像提取的车牌号码）和与第一图像相关联的第一元数据的对称密码密钥来加密在第一位置处获取的第一图像来生成加密的第一图像 ，例如获取第一图像的时间。 当在第二图像和第一图像之间建立链接时，例如通过视觉签名匹配，可以在不访问第一图像的情况下重构对称密码密钥，而是基于第一元数据和从第 第二张图片。 然后可以将重建的对称加密密钥用于加密图像的解密，以建立从第一图像确实提取牌照号码的证据。

公开(公告)号：EP2863338A3

公开(公告)日：2015-05-06

申请号：EP14187389.3

申请日：2014-10-01

申请人： Xerox Corporation

发明人： Rodriguez-Serrano, Jose Antonio ,  Perronnin, Florent C. ,  Poirier, Herve ,  Roulland, Frederic ,  Ciriza, Victor

IPC分类号： G06K9/00 ,  G06K9/32

CPC分类号： G06K9/3258 ,  G06F17/30253 ,  G06K9/00791 ,  G06K9/6212 ,  G06K9/6277 ,  G06K2209/15 ,  G06K2209/27

摘要： A method for recognition of an identifier such as a license plate includes storing first visual signatures, each extracted from a first image of a respective object, such as a vehicle, captured at a first location, and first information associated with the first captured image, such as a time stamp. A second visual signature is extracted from a second image of a second object captured at a second location and second information associated with the second captured image is acquired. A measure of similarity is computed between the second visual signature and at least some of the first visual signatures to identify a matching one. A test is performed, which is a function of the first and the second information associated with the matching signatures. Only when it is confirmed that the test has been met, identifier recognition is performed to identify the identifier of the second object.

摘要翻译： 用于识别诸如车牌的标识符的方法包括存储从在第一位置捕获的诸如车辆的相应对象的第一图像提取的第一视觉签名以及与第一拍摄图像相关联的第一信息， 如时间戳。 从第二位置拍摄的第二物体的第二图像提取第二视觉特征，并且获取与第二拍摄图像相关联的第二信息。 在第二视觉签名和至少一些第一视觉签名之间计算相似度的度量以识别匹配的一个。 执行测试，其是与匹配签名相关联的第一和第二信息的函数。 只有当确认已经满足测试时，才执行标识符识别以识别第二对象的标识符。

公开(公告)号：EP2863338A2

公开(公告)日：2015-04-22

申请号：EP14187389.3

申请日：2014-10-01

申请人： Xerox Corporation

发明人： Rodriguez-Serrano, Jose Antonio ,  Perronnin, Florent C. ,  Poirier, Herve ,  Roulland, Frederic ,  Ciriza, Victor

IPC分类号： G06K9/00 ,  G06K9/32

CPC分类号： G06K9/3258 ,  G06F17/30253 ,  G06K9/00791 ,  G06K9/6212 ,  G06K9/6277 ,  G06K2209/15 ,  G06K2209/27

摘要： A method for recognition of an identifier such as a license plate includes storing first visual signatures, each extracted from a first image of a respective object, such as a vehicle, captured at a first location, and first information associated with the first captured image, such as a time stamp. A second visual signature is extracted from a second image of a second object captured at a second location and second information associated with the second captured image is acquired. A measure of similarity is computed between the second visual signature and at least some of the first visual signatures to identify a matching one. A test is performed, which is a function of the first and the second information associated with the matching signatures. Only when it is confirmed that the test has been met, identifier recognition is performed to identify the identifier of the second object.

摘要翻译： 一种用于识别诸如牌照的标识符的方法包括：存储第一视觉特征，每个第一视觉特征从在第一位置处捕捉的诸如车辆的相应对象的第一图像中提取，以及与第一捕捉图像相关联的第一信息， 如时间戳。 从在第二位置处捕捉的第二对象的第二图像中提取第二视觉特征，并且获取与第二捕捉图像相关联的第二信息。 在第二视觉签名和至少一些第一视觉签名之间计算相似性度量以识别匹配的一个。 执行测试，其是与匹配签名相关联的第一和第二信息的函数。 只有当确认已经满足测试时，才执行标识符识别以识别第二对象的标识符。