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

US20100191743A1 Contextual similarity measures for objects and retrieval, classification, and clustering using same 有权
标题翻译：使用相同的对象和检索，分类和聚类的上下文相似性度量
公开(公告)号：US20100191743A1
公开(公告)日：2010-07-29
申请号：US12361157
申请日：2009-01-28
申请人： Florent C. Perronnin , Yan Liu
发明人： Florent C. Perronnin , Yan Liu
IPC分类号： G06F17/30
CPC分类号： G06F17/30253 , G06K9/6215 , G06K9/72
摘要： A method of comparing first and second objects in a context comprises: maximizing or minimizing a quantitative comparison of the first object and a mixture of the second object and the context respective to a weighting parameter that controls the mixture; and outputting a comparison value based on the value of the weighting parameter determined by the maximizing or minimizing.
摘要翻译：在上下文中比较第一和第二对象的方法包括：最大化或最小化第一对象与第二对象与上下文的混合的定量比较，与控制混合的加权参数相对应; 并且基于由最大化或最小化确定的加权参数的值来输出比较值。

2. 发明授权

US08150858B2 Contextual similarity measures for objects and retrieval, classification, and clustering using same 有权
标题翻译：使用相同的对象和检索，分类和聚类的上下文相似性度量
公开(公告)号：US08150858B2
公开(公告)日：2012-04-03
申请号：US12361157
申请日：2009-01-28
申请人： Florent C. Perronnin , Yan Liu
发明人： Florent C. Perronnin , Yan Liu
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30253 , G06K9/6215 , G06K9/72
摘要： A method of comparing first and second objects in a context comprises: maximizing or minimizing a quantitative comparison of the first object and a mixture of the second object and the context respective to a weighting parameter that controls the mixture; and outputting a comparison value based on the value of the weighting parameter determined by the maximizing or minimizing.
摘要翻译：在上下文中比较第一和第二对象的方法包括：最大化或最小化第一对象与第二对象与上下文的混合的定量比较，与控制混合的加权参数相对应; 并且基于由最大化或最小化确定的加权参数的值来输出比较值。

3. 发明申请

US20100098343A1 MODELING IMAGES AS MIXTURES OF IMAGE MODELS 有权
标题翻译：将图像建模为图像模型的混合
公开(公告)号：US20100098343A1
公开(公告)日：2010-04-22
申请号：US12252531
申请日：2008-10-16
申请人： Florent C. Perronnin , Yan Liu
发明人： Florent C. Perronnin , Yan Liu
IPC分类号： G06K9/62
CPC分类号： G06K9/6226
摘要： A system and method for generating an image representation are provided. The image is modeled as a set of mixture weights, one for each of a set of reference image models, such as Gaussian mixture models (GMMs). The weights are derived by optimizing an objective function in which each reference image model is associated with its respective weight.
摘要翻译：提供了一种用于生成图像表示的系统和方法。图像被建模为一组混合权重，一组用于一组参考图像模型，例如高斯混合模型（GMM）。权重通过优化每个参考图像模型与其相应权重相关联的目标函数而导出。

4. 发明授权

US08463051B2 Modeling images as mixtures of image models 有权
标题翻译：将图像建模为图像模型的混合
公开(公告)号：US08463051B2
公开(公告)日：2013-06-11
申请号：US12252531
申请日：2008-10-16
申请人： Florent C. Perronnin , Yan Liu
发明人： Florent C. Perronnin , Yan Liu
IPC分类号： G06K9/62 , G06K9/74 , G06K9/32
CPC分类号： G06K9/6226
摘要： A system and method for generating an image representation are provided. The image is modeled as a set of mixture weights, one for each of a set of reference image models, such as Gaussian mixture models (GMMs). The weights are derived by optimizing an objective function in which each reference image model is associated with its respective weight.
摘要翻译：提供了一种用于生成图像表示的系统和方法。图像被建模为一组混合权重，一组用于一组参考图像模型，例如高斯混合模型（GMM）。权重通过优化每个参考图像模型与其相应权重相关联的目标函数而导出。

5. 发明授权

US08380647B2 Training a classifier by dimension-wise embedding of training data 有权
标题翻译：通过在维度上嵌入训练数据来训练分类器
公开(公告)号：US08380647B2
公开(公告)日：2013-02-19
申请号：US12541636
申请日：2009-08-14
申请人： Florent C. Perronnin , Jorge Sanchez , Yan Liu
发明人： Florent C. Perronnin , Jorge Sanchez , Yan Liu
IPC分类号： G06F17/00 , G06N5/00
CPC分类号： G06K9/6247 , G06K9/6232 , G06K9/6269 , G06N99/005
摘要： A classifier training method and apparatus for training, a linear classifier trained by the method, and its use, are disclosed. In training the linear classifier, signatures for a set of training samples, such as images, in the form of multi-dimension vectors in a first multi-dimensional space, are converted to a second multi-dimension space, of the same or higher dimensionality than the first multi-dimension space, by applying a set of embedding functions, one for each dimension of the vector space. A linear classifier is trained in the second multi-dimension space. The linear classifier can approximate the accuracy of a non-linear classifier in the original space when predicting labels for new samples, but with lower computation cost in the learning phase.
摘要翻译：公开了一种用于训练的分类器训练方法和装置，通过该方法训练的线性分类器及其用途。在训练线性分类器时，在第一多维空间中以多维向量的形式的一组训练样本（诸如图像）的签名被转换成具有相同或更高维度的第二多维空间比第一个多维空间，通过应用一组嵌入函数，一个用于向量空间的每个维度。在第二个多维空间中训练线性分类器。当预测新样本的标签时，线性分类器可以近似原始空间中的非线性分类器的精度，但在学习阶段具有较低的计算成本。

6. 发明申请

US20110040711A1 TRAINING A CLASSIFIER BY DIMENSION-WISE EMBEDDING OF TRAINING DATA 有权
标题翻译：通过维度训练数据的嵌入式训练分类器
公开(公告)号：US20110040711A1
公开(公告)日：2011-02-17
申请号：US12541636
申请日：2009-08-14
申请人： Florent C. Perronnin , Jorge Sanchez , Yan Liu
发明人： Florent C. Perronnin , Jorge Sanchez , Yan Liu
IPC分类号： G06F15/18 , G06N5/02
CPC分类号： G06K9/6247 , G06K9/6232 , G06K9/6269 , G06N99/005
摘要： A classifier training method and apparatus for training, a linear classifier trained by the method, and its use, are disclosed. In training the linear classifier, signatures for a set of training samples, such as images, in the form of multi-dimension vectors in a first multi-dimensional space, are converted to a second multi-dimension space, of the same or higher dimensionality than the first multi-dimension space, by applying a set of embedding functions, one for each dimension of the vector space. A linear classifier is trained in the second multi-dimension space. The linear classifier can approximate the accuracy of a non-linear classifier in the original space when predicting labels for new samples, but with lower computation cost in the learning phase.
摘要翻译：公开了一种用于训练的分类器训练方法和装置，通过该方法训练的线性分类器及其用途。在训练线性分类器时，在第一多维空间中以多维向量的形式的一组训练样本（诸如图像）的签名被转换成具有相同或更高维度的第二多维空间比第一个多维空间，通过应用一组嵌入函数，一个用于向量空间的每个维度。在第二个多维空间中训练线性分类器。当预测新样本的标签时，线性分类器可以近似原始空间中的非线性分类器的精度，但在学习阶段具有较低的计算成本。

7. 发明授权

US08566349B2 Handwritten document categorizer and method of training 有权
标题翻译：手写文件分类器和培训方法
公开(公告)号：US08566349B2
公开(公告)日：2013-10-22
申请号：US12567920
申请日：2009-09-28
申请人： Francois Ragnet , Florent C. Perronnin , Thierry Lehoux
发明人： Francois Ragnet , Florent C. Perronnin , Thierry Lehoux
IPC分类号： G06F17/30
CPC分类号： G06F17/30705 , G06K9/00879 , G06K9/2054 , G06K9/6256 , G06K2209/01
摘要： A method and an apparatus for training a handwritten document categorizer are disclosed. For each category in a set into which handwritten documents are to be categorized, discriminative words are identified from the OCR output of a training set of typed documents labeled by category. A group of keywords is established including some of the discriminative words identified for each category. Samples of each of the keywords in the group are synthesized using a plurality of different type fonts. A keyword model is then generated for each keyword, parameters of the model being estimated, at least initially, based on features extracted from the synthesized samples. Keyword statistics for each of a set of scanned handwritten documents labeled by category are generated by applying the generated keyword models to word images extracted from the scanned handwritten documents. The categorizer is trained with the keyword statistics and respective handwritten document labels.
摘要翻译：公开了一种用于训练手写文档分类器的方法和装置。对于要分类手写文件的集合中的每个类别，根据类别标记的类型文档的训练集的OCR输出来识别歧视性词。建立了一组关键字，其中包括为每个类别确定的某些歧视性词汇。使用多种不同类型的字体来合成组中的每个关键字的样本。然后，基于从合成样本中提取的特征，为每个关键字生成关键字模型，估计模型的参数。通过将生成的关键词模型应用于从扫描的手写文档中提取的单词图像，生成按类别标记的一组扫描手写文档中的每一个的关键字统计。分类程序使用关键字统计信息和各自的手写文档标签进行培训。

8. 发明授权

US08813111B2 Photograph-based game 有权
标题翻译：基于照片的游戏
公开(公告)号：US08813111B2
公开(公告)日：2014-08-19
申请号：US13214661
申请日：2011-08-22
申请人： Nicolas Guérin , Florent C. Perronnin , Craig John Saunders , Sebastien Dabet
发明人： Nicolas Guérin , Florent C. Perronnin , Craig John Saunders , Sebastien Dabet
IPC分类号： H04N7/16 , G06K9/68 , A63F9/24 , A63F13/12 , A63F13/10
CPC分类号： A63F13/655 , A63F13/10 , A63F13/12 , A63F13/213 , A63F13/332 , A63F13/44 , A63F13/46 , A63F2300/6009 , A63F2300/61 , A63F2300/69
摘要： A system and a method for playing a photograph-based game are provided. The method includes establishing a communication link between a game playing system and one or more game playing devices, each of which is operated by a respective player. Game rules are presented to the player(s) on the respective game playing device(s). The game rules include at least one task for the submission of at least one photographic image. Provision is made for receiving a photographic image in the game playing system which has been submitted via the established link from the game playing device in response to the presented task. An image signature is computed for the submitted photographic image based on visual features extracted from the image and a relevance to the task is computed, based on the computed image signature. A score for the game is output for each player, based on the computed relevance of the submitted images for each of the tasks.
摘要翻译：提供了一种用于播放基于照片的游戏的系统和方法。该方法包括建立游戏系统与一个或多个游戏装置之间的通信链接，每个游戏装置由相应的玩家操作。游戏规则被呈现给各个游戏设备上的玩家。游戏规则包括至少一个用于提交至少一个摄影图像的任务。规定用于在游戏系统中接收已经通过建立的来自游戏装置的链接而响应于所呈现的任务提交的摄影图像。基于从图像提取的视觉特征为所提交的摄影图像计算图像签名，并且基于计算的图像签名计算与任务的相关性。基于所计算的每个任务的提交的图像的相关性，为每个玩家输出游戏的分数。

9. 发明授权

US08509537B2 Learning weights of fonts for typed samples in handwritten keyword spotting 有权
标题翻译：学习手写关键词点样中类型样本的字体权重
公开(公告)号：US08509537B2
公开(公告)日：2013-08-13
申请号：US12851092
申请日：2010-08-05
申请人： Florent C. Perronnin , Thierry Lehoux , Francois Ragnet
发明人： Florent C. Perronnin , Thierry Lehoux , Francois Ragnet
IPC分类号： G06K9/18 , G06K9/62 , G06K9/72
CPC分类号： G06K9/00879 , G06K9/6255 , G06K9/6828
摘要： A wordspotting system and method are disclosed. The method includes receiving a keyword and, for each of a set of typographical fonts, synthesizing a word image based on the keyword. A keyword model is trained based on the synthesized word images and the respective weights for each of the set of typographical fonts. Using the trained keyword model, handwritten word images of a collection of handwritten word images which match the keyword are identified. The weights allow a large set of fonts to be considered, with the weights indicating the relative relevance of each font for modeling a set of handwritten word images.
摘要翻译：公开了一种wordspotting系统和方法。该方法包括接收关键字，并且针对一组排版字体中的每一个，基于关键字合成单词图像。基于合成的单词图像和每组排版字体的相应权重来训练关键词模型。使用经过训练的关键词模型，识别与该关键词匹配的手写词图像集合的手写词图像。权重允许考虑一大堆字体，权重指示每个字体的相对相关性，用于对一组手写字图像进行建模。

10. 发明申请

US20100189354A1 Modeling images as sets of weighted features 有权
标题翻译：将图像建模为一组加权特征
公开(公告)号：US20100189354A1
公开(公告)日：2010-07-29
申请号：US12361235
申请日：2009-01-28
申请人： Teofilo E. de Campos , Florent C. Perronnin
发明人： Teofilo E. de Campos , Florent C. Perronnin
IPC分类号： G06F17/30
CPC分类号： G06K9/4671 , G06K9/00597 , G06K9/3233
摘要： An apparatus, method, and computer program product are provided for generating an image representation. The method includes receiving an input digital image, extracting features from the image which are representative of patches of the image, generating weighting factors for the features based on location relevance data for the image, and weighting the extracted features with the weighting factors to form a representation of the image.
摘要翻译：提供了一种用于生成图像表示的装置，方法和计算机程序产品。该方法包括：接收输入数字图像，从代表图像斑块的图像中提取特征，基于图像的位置相关性数据生成特征的加权因子，以及用加权因子加权所提取的特征，以形成图像的表示。

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