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

US20100014762A1 CATEGORIZER WITH USER-CONTROLLABLE CALIBRATION 有权
标题翻译：具有用户可控校准的分类器
公开(公告)号：US20100014762A1
公开(公告)日：2010-01-21
申请号：US12174721
申请日：2008-07-17
申请人： Jean-Michel Renders , Caroline Privault , Eric H. Cheminot
发明人： Jean-Michel Renders , Caroline Privault , Eric H. Cheminot
IPC分类号： G06K9/62
CPC分类号： G06K9/6277
摘要： A calibrated categorizer comprises: a multi-class categorizer configured to output class probabilities for an input object corresponding to a set of classes; a class probabilities rescaler configured to rescale class probabilities to generate rescaled class probabilities; and a resealing model learner configured to learn calibration parameters for the class probabilities rescaler based on (i) class probabilities output by the multi-class categorizer for a calibration set of class-labeled objects, (ii) confidence measures output by the multi-class categorizer for the calibration set of class-labeled objects, and (iii) class labels of the calibration set of class-labeled objects, the class probabilities rescaler calibrated by the learned calibration parameters defining a calibrated class probabilities rescaler. In a method embodiment, class probabilities are generated for an input object corresponding to a set of classes using a classifier trained on a first set of objects, and are rescaled to form rescaled class probabilities using a resealing algorithm calibrated using a second set of objects different from the first set of objects. The method may further entail thresholding the rescaled class probabilities using thresholds calibrated using the second set of objects or a third set of objects.
摘要翻译：校准分类器包括：多类分类器，被配置为输出与一组类对应的输入对象的类概率; 类概率重定标器被配置为重新缩放类概率以产生重新缩放的类概率; 以及重新密封的模型学习者，被配置为基于（i）由多类分类器输出的用于类标记对象的校准集的类概率来学习类概率重定标器的校准参数，（ii）由多类输出的置信度度量分类器，用于类标记对象的校准集，以及（iii）类标记对象的校准集的类标签，通过定义校准的类概率重定标器的所学习的校准参数校准的类概率重新计数器。在方法实施例中，针对与使用在第一组对象上训练的分类器相对应的类的集合的输入对象生成类概率，并且使用使用不同对象的第二组对象校准的重新密码算法重新缩放以形成重新缩放的类概率从第一组对象。该方法还可能使用使用第二组对象或第三组对象校准的阈值来限定重新归类的类概率。

2. 发明授权

US08453922B2 Method for one-step document categorization and separation using stamped machine recognizable patterns 有权
标题翻译：使用印字机识别模式进行一步文档分类和分离的方法
公开(公告)号：US08453922B2
公开(公告)日：2013-06-04
申请号：US12702897
申请日：2010-02-09
申请人： Francois Ragnet , John A. Moore , Nicolas Raphaël Saubat , Eric H. Cheminot , Thierry Lehoux
发明人： Francois Ragnet , John A. Moore , Nicolas Raphaël Saubat , Eric H. Cheminot , Thierry Lehoux
IPC分类号： G06F17/00 , G06K19/06
CPC分类号： G06F17/30563 , G06F17/30011
摘要： A method for separating and categorizing documents includes receiving a scanned batch of documents. The batch includes scanned documents to which document separator stamps have been applied before scanning. Each stamp includes machine recognizable patterns applied on a same page of a document, spaced by a designated field for receiving a user-applied category code. The scanned batch of documents is processed to identify pages that contain a document separator, including identifying at least one of two spaced patterns. For a document page for which a document separator is identified, the the corresponding designated field is located and the category code associated with the designated field identified. The document containing the is separated from other documents in the batch based the identified separator and a document category is assigned to the document, based on the identified category code.
摘要翻译：用于分离和分类文档的方法包括接收扫描的文件批次。批次包括在扫描之前应用了文档分隔符的扫描文档。每个印章包括应用在文档的相同页面上的机器可识别图案，间隔有用于接收用户应用的类别代码的指定字段。处理扫描的文档批次以识别包含文档分隔符的页面，包括识别两个间隔图案中的至少一个。对于识别文档分隔符的文档页面，定位相应的指定字段，并且识别与指定字段相关联的类别代码。基于识别的类别代码，将包含该文档的文档与批处理中的其他文档分离，并根据识别的类别代码将文档类别分配给文档。

3. 发明申请

US20120150538A1 VOICE MESSAGE CONVERTER 有权
标题翻译：语音信息转换器
公开(公告)号：US20120150538A1
公开(公告)日：2012-06-14
申请号：US13400288
申请日：2012-02-20
申请人： Denys M. Proux , Eric H. Cheminot
发明人： Denys M. Proux , Eric H. Cheminot
IPC分类号： G10L15/26 , H04W4/12
CPC分类号： H04W4/12 , G10L15/26 , H04M1/72552 , H04M3/42382 , H04M2201/60
摘要： A textual representation of a voice message is provided to a communication device, such as a mobile phone, for example, when the mobile phone is operating in a silent mode. The voice message is input by a caller and the voice message converted to phonemes. A text representation of the voice message is transmitted to the mobile phone. The representation includes characters based on the phonemes with well known words being represented in an easily understood shorthand format.
摘要翻译：语音消息的文本表示例如在移动电话以无声模式操作时被提供给诸如移动电话的通信设备。语音消息由呼叫者输入，语音消息转换为音素。语音消息的文本表示被发送到移动电话。该表示包括基于音素的字符，其中众所周知的词以易于理解的速记格式表示。

4. 发明申请

US20110192894A1 METHOD FOR ONE-STEP DOCUMENT CATEGORIZATION AND SEPARATION 有权
标题翻译：一步文件分类和分离方法
公开(公告)号：US20110192894A1
公开(公告)日：2011-08-11
申请号：US12702897
申请日：2010-02-09
申请人： Francois Ragnet , John A. Moore , Nicolas Raphaël Saubat , Eric H. Cheminot , Thierry Lehoux
发明人： Francois Ragnet , John A. Moore , Nicolas Raphaël Saubat , Eric H. Cheminot , Thierry Lehoux
IPC分类号： G06F17/00 , G06K7/00 , G09F3/00
CPC分类号： G06F17/30563 , G06F17/30011
摘要： A method, apparatus, and hardcopy document are provided. The method provides for separating and categorizing documents and includes receiving a scanned batch of documents. The batch includes a plurality of scanned documents to which document separator stamps have been applied before scanning. Each document separator stamp includes first and second machine recognizable patterns applied on a same page of a document, the first and second patterns being spaced by a designated field for receiving a user-applied category code. The scanned batch of documents is processed to identify pages that contain a document separator, the processing including identifying at least one of the first and second spaced patterns. For each of a plurality of document pages for which a document separator is identified, the method includes locating the corresponding designated field and identifying the category code associated with the designated field. The document containing the identified separator is separated from other documents in the batch based on at least the identified separator and a document category is assigned to the document from a set of document categories, based on the identified category code.
摘要翻译：提供了一种方法，设备和硬拷贝文档。该方法用于分离和分类文档，并包括接收扫描的文件批次。批次包括在扫描之前已经应用了文档分离器标记的多个扫描文档。每个文档分隔符包括应用于文档的同一页面上的第一和第二机器可识别图案，第一和第二图案间隔有用于接收用户应用类别代码的指定字段。处理扫描的文档批次以识别包含文档分隔符的页面，该处理包括识别第一和第二间隔图案中的至少一个。对于识别出文档分离器的多个文档页面中的每一个，该方法包括定位相应的指定字段并且识别与指定字段相关联的类别代码。基于所识别的类别代码，至少基于所标识的分离器将包含所识别的分离符的文档与批处理中的其他文档分开，并且从文档类别集合将文档类别分配给文档。

5. 发明授权

US08600165B2 Optical mark classification system and method 有权
标题翻译：光标分类系统及方法
公开(公告)号：US08600165B2
公开(公告)日：2013-12-03
申请号：US12704792
申请日：2010-02-12
申请人： Nicolas Raphaël Saubat , Francois Ragnet , Philippe Rerole , Eric H. Cheminot , John A. Moore
发明人： Nicolas Raphaël Saubat , Francois Ragnet , Philippe Rerole , Eric H. Cheminot , John A. Moore
IPC分类号： G06K9/46 , G06K9/00 , G06K7/10
CPC分类号： G06K9/3233 , G06K9/2063 , G06K2209/01
摘要： A system, method, and apparatus for mark recognition in an image of an original document are provided. The method/system takes as input an image of an original document in which at least one designated field is provided for accepting a mark applied by a user (which may or may not have been marked). A region of interest (RoI) is extracted from the image, roughly corresponding to the designated field. A center of gravity (CoG) of the RoI is determined, based on a distribution of black pixels in the RoI. Thereafter, for one or more iterations, the RoI is partitioned into sub-RoIs, based on the determined CoG, where at a subsequent iteration, sub-RoIs generated at the prior iteration serve as the RoI partitioned. Data is extracted from the RoI and sub-RoIs at one or more of the iterations, which allows a representation of the entire RoI to be generated which is useful in classifying the designated field, e.g., as positive (marked) or negative (not marked).
摘要翻译：提供了一种用于原始文档的图像中的标记识别的系统，方法和装置。该方法/系统将原始文档的图像作为输入，其中提供至少一个指定字段用于接受用户应用的标记（其可以被标记或可能不被标记）。从图像中提取感兴趣区域（RoI），大致对应于指定字段。基于RoI中的黑色像素的分布，确定RoI的重心（CoG）。此后，对于一次或多次迭代，基于所确定的CoG将RoI划分为子路由，其中在随后的迭代中，在先前迭代中生成的子路由用作RoI分区。在一次或多次迭代中，从RoI和Sub-RoI中提取数据，这允许生成对整个指定字段进行分类的整个RoI的表示，例如作为正（标记）或否定（未标记））。

6. 发明授权

US08244540B2 System and method for providing a textual representation of an audio message to a mobile device 有权
标题翻译：用于向移动设备提供音频消息的文本表示的系统和方法
公开(公告)号：US08244540B2
公开(公告)日：2012-08-14
申请号：US13400288
申请日：2012-02-20
申请人： Denys M. Proux , Eric H. Cheminot
发明人： Denys M. Proux , Eric H. Cheminot
IPC分类号： G10L21/00
CPC分类号： H04W4/12 , G10L15/26 , H04M1/72552 , H04M3/42382 , H04M2201/60
摘要： A textual representation of a voice message is provided to a communication device, such as a mobile phone, for example, when the mobile phone is operating in a silent mode. The voice message is input by a caller and the voice message converted to phonemes. A text representation of the voice message is transmitted to the mobile phone. The representation includes characters based on the phonemes with well known words being represented in an easily understood shorthand format.
摘要翻译：语音消息的文本表示例如在移动电话以无声模式操作时被提供给诸如移动电话的通信设备。语音消息由呼叫者输入，语音消息转换为音素。语音消息的文本表示被发送到移动电话。该表示包括基于音素的字符，其中众所周知的词以易于理解的速记格式表示。

7. 发明授权

US08189930B2 Categorizer with user-controllable calibration 有权
标题翻译：具有用户可控校准的分类器
公开(公告)号：US08189930B2
公开(公告)日：2012-05-29
申请号：US12174721
申请日：2008-07-17
申请人： Jean-Michel Renders , Caroline Privault , Eric H. Cheminot
发明人： Jean-Michel Renders , Caroline Privault , Eric H. Cheminot
IPC分类号： G06K9/74 , G06K9/62
CPC分类号： G06K9/6277
摘要： A calibrated categorizer comprises: a multi-class categorizer configured to output class probabilities for an input object corresponding to a set of classes; a class probabilities rescaler configured to rescale class probabilities to generate rescaled class probabilities; and a resealing model learner configured to learn calibration parameters for the class probabilities rescaler based on (i) class probabilities output by the multi-class categorizer for a calibration set of class-labeled objects, (ii) confidence measures output by the multi-class categorizer for the calibration set of class-labeled objects, and (iii) class labels of the calibration set of class-labeled objects, the class probabilities rescaler calibrated by the learned calibration parameters defining a calibrated class probabilities rescaler. In a method embodiment, class probabilities are generated for an input object corresponding to a set of classes using a classifier trained on a first set of objects, and are rescaled to form rescaled class probabilities using a resealing algorithm calibrated using a second set of objects different from the first set of objects. The method may further entail thresholding the rescaled class probabilities using thresholds calibrated using the second set of objects or a third set of objects.
摘要翻译：校准分类器包括：多类分类器，被配置为输出与一组类对应的输入对象的类概率; 类概率重定标器被配置为重新缩放类概率以产生重新缩放的类概率; 以及重新密封的模型学习者，其被配置为基于（i）由多类分类器输出的用于类标记对象的校准集的类概率来学习类概率重定标器的校准参数，（ii）由多类输出的置信度度量分类器，用于类标记对象的校准集，以及（iii）类标记对象的校准集的类标签，通过定义校准的类概率重定标器的所学习的校准参数校准的类概率重新计数器。在方法实施例中，针对与使用在第一组对象上训练的分类器相对应的类的集合的输入对象生成类概率，并且使用使用不同对象的第二组对象校准的重新密码算法重新缩放以形成重新缩放的类概率从第一组对象。该方法还可能使用使用第二组对象或第三组对象校准的阈值来限定重新归类的类概率。

8. 发明授权

US08204748B2 System and method for providing a textual representation of an audio message to a mobile device 有权
公开(公告)号：US08204748B2
公开(公告)日：2012-06-19
申请号：US11415792
申请日：2006-05-02
申请人： Denys M. Proux , Eric H. Cheminot
发明人： Denys M. Proux , Eric H. Cheminot
IPC分类号： G10L21/00
CPC分类号： H04W4/12 , G10L15/26 , H04M1/72552 , H04M3/42382 , H04M2201/60
摘要： A textual representation of a voice message is provided to a communication device, such as a mobile phone, for example, when the mobile phone is operating in a silent mode. The voice message is input by a caller and the voice message converted to phonemes. A text representation of the voice message is transmitted to the mobile phone. The representation includes characters based on the phonemes with well known words being represented in an easily understood shorthand format.

9. 发明申请

US20110200256A1 OPTICAL MARK CLASSIFICATION SYSTEM AND METHOD 有权
标题翻译：光学标记分类系统和方法
公开(公告)号：US20110200256A1
公开(公告)日：2011-08-18
申请号：US12704792
申请日：2010-02-12
申请人： Nicolas Raphael Saubat , Francois Ragnet , Philippe Rerole , Eric H. Cheminot , John A. Moore
发明人： Nicolas Raphael Saubat , Francois Ragnet , Philippe Rerole , Eric H. Cheminot , John A. Moore
IPC分类号： G06K9/46
CPC分类号： G06K9/3233 , G06K9/2063 , G06K2209/01
摘要： A system, method, and apparatus for mark recognition in an image of an original document are provided. The method/system takes as input an image of an original document in which at least one designated field is provided for accepting a mark applied by a user (which may or may not have been marked). A region of interest (RoI) is extracted from the image, roughly corresponding to the designated field. A center of gravity (CoG) of the RoI is determined, based on a distribution of black pixels in the RoI. Thereafter, for one or more iterations, the RoI is partitioned into sub-RoIs, based on the determined CoG, where at a subsequent iteration, sub-RoIs generated at the prior iteration serve as the RoI partitioned. Data is extracted from the RoI and sub-RoIs at one or more of the iterations, which allows a representation of the entire RoI to be generated which is useful in classifying the designated field, e.g., as positive (marked) or negative (not marked).
摘要翻译：提供了一种用于原始文档的图像中的标记识别的系统，方法和装置。该方法/系统将原始文档的图像作为输入，其中提供至少一个指定字段用于接受用户应用的标记（其可以被标记或可能不被标记）。从图像中提取感兴趣区域（RoI），大致对应于指定字段。基于RoI中的黑色像素的分布，确定RoI的重心（CoG）。此后，对于一次或多次迭代，基于所确定的CoG将RoI划分为子路由，其中在随后的迭代中，在先前迭代中生成的子路由用作RoI分区。在一次或多次迭代中，从RoI和Sub-RoI中提取数据，这允许生成对整个指定字段进行分类的整个RoI的表示，例如作为正（标记）或否定（未标记））。

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