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

EP2551792A3 System and method for computing the visual profile of a place 有权
标题翻译：系统和方法，用于计算图的视觉简档
公开(公告)号：EP2551792A3
公开(公告)日：2014-06-18
申请号：EP12175851.0
申请日：2012-07-11
申请人： Xerox Corporation
发明人： Perronnin, Florent , Guerin, Nicolas , Saunders, Craig John
IPC分类号： G06K9/00
CPC分类号： G06K9/00476
摘要： A system and method for computing a place profile are disclosed. The method includes providing (S104) a geographical definition of a place, retrieving (S106) a set of images based on the geographical place definition. With a classifier, image-level statistics for the retrieved images are generated (S108). The classifier has been trained to generate image-level statistics for a finite set of classes, such as different activities. The image-level statistics are aggregated (S110) to generate a place profile for the defined place which may be displayed to a user who has provided information for generating the geographical definition or used in an application such as a recommender system or to generate a personal profile for the user.

2. 发明公开

EP2579211A3 Graph-based segmentation integrating visible and NIR information 有权
标题翻译： Graphbasierte Segmentierung，die sichtbare und NIR information integriert
公开(公告)号：EP2579211A3
公开(公告)日：2014-05-07
申请号：EP12187071.1
申请日：2012-10-03
申请人： Xerox Corporation
发明人： Salamati, Neda , Larlus-Larrondo, Diane , Csurka, Gabriela , Saunders, Craig John
IPC分类号： G06T7/00
CPC分类号： G06T7/0087 , G06T7/143 , G06T7/162 , G06T2207/10048 , G06T2207/20072 , G06T2207/20076 , G06T2207/20081
摘要： A system and a method for segmenting an image are disclosed which can leverage different types of information from the image. An image to be segmented is received (S104). Unary potentials (S112) for pixels of the input image are extracted. These can be based for each of a set of possible labels, on information for a first channel in the image, such as in the visible range of the spectrum. Pairwise potentials are extracted (S114) for neighboring pairs of pixels of the image. These can be based on information for a second channel in the image, such as in the infrared range of the spectrum. An objective function is optimized over pixels of the input image to identify labels for the pixels. The objective function is based on a combination of ones of the extracted unary and pairwise potentials. The image is then segmented, based on the identified pixel labels. The method and system can provide an improvement in segmentation over methods which use only the visible information.
摘要翻译：公开了一种用于分割图像的系统和方法，其可以利用来自图像的不同类型的信息。接收要分割的图像（S104）。提取输入图像的像素的一次电位（S112）。这些可以基于用于图像中的第一通道的信息的一组可能的标签中的每一个，例如在可见光谱范围内。对于图像的相邻像素对，提取成对电位（S114）。这些可以基于图像中的第二通道的信息，例如在光谱的红外范围中。在输入图像的像素上优化目标函数以识别像素的标签。目标函数基于提取的一元和成对电位的组合。然后基于所识别的像素标签来分割图像。该方法和系统可以提供仅使用可见信息的方法的分割的改进。

3. 发明公开

EP2551792A2 System and method for computing the visual profile of a place 有权
标题翻译：系统和Verfahren zur Berechnung des visuellen Profils eines Ortes
公开(公告)号：EP2551792A2
公开(公告)日：2013-01-30
申请号：EP12175851.0
申请日：2012-07-11
申请人： Xerox Corporation
发明人： Perronnin, Florent , Guerin, Nicolas , Saunders, Craig John
IPC分类号： G06K9/00
CPC分类号： G06K9/00476
摘要： A system and method for computing a place profile are disclosed. The method includes providing (S104) a geographical definition of a place, retrieving (S106) a set of images based on the geographical place definition. With a classifier, image-level statistics for the retrieved images are generated (S108). The classifier has been trained to generate image-level statistics for a finite set of classes, such as different activities. The image-level statistics are aggregated (S110) to generate a place profile for the defined place which may be displayed to a user who has provided information for generating the geographical definition or used in an application such as a recommender system or to generate a personal profile for the user.
摘要翻译：公开了一种用于计算地点轮廓的系统和方法。该方法包括提供（S104）地点的地理定义，基于地理位置定义检索（S106）一组图像。利用分类器，生成检索图像的图像级统计信息（S108）。已经对分类器进行了训练，以生成有限集合类的图像级统计信息，例如不同的活动。聚集图像级统计信息（S110）以生成可以向已经提供用于生成地理定义的信息的用户显示的定义的地点的位置简档，或者在诸如推荐系统的应用中使用或用于生成个人用户配置文件。

4. 发明授权

EP2595092B1 Methods and systems for improved license plate signature matching 有权转让
标题翻译：方法和系统改进的车牌特征比较
公开(公告)号：EP2595092B1
公开(公告)日：2016-03-02
申请号：EP12192069.8
申请日：2012-11-09
申请人： Xerox Corporation
发明人： Rodriguez Serrano, Jose A. , Bala, Raja , Perronnin, Florent , Saunders, Craig John , Zhao, Yonghui
IPC分类号： G06K9/62
CPC分类号： G06K9/6255 , G06K9/6217 , G06K2209/15

5. 发明授权

EP2579211B1 Graph-based segmentation integrating visible and NIR information 有权
标题翻译：基于图形的分割，可见光和近红外信息集成
公开(公告)号：EP2579211B1
公开(公告)日：2015-12-30
申请号：EP12187071.1
申请日：2012-10-03
申请人： Xerox Corporation
发明人： Salamati, Neda , Larlus-Larrondo, Diane , Csurka, Gabriela , Saunders, Craig John
IPC分类号： G06T7/00
CPC分类号： G06T7/0087 , G06T7/143 , G06T7/162 , G06T2207/10048 , G06T2207/20072 , G06T2207/20076 , G06T2207/20081

6. 发明公开

EP2595092A2 Methods and systems for improved license plate signature matching 有权转让
标题翻译：方法和系统改进的车牌特征比较
公开(公告)号：EP2595092A2
公开(公告)日：2013-05-22
申请号：EP12192069.8
申请日：2012-11-09
申请人： Xerox Corporation
发明人： Rodriguez Serrano, Jose A. , Bala, Raja , Perronnin, Florent , Saunders, Craig John , Zhao, Yonghui
IPC分类号： G06K9/62
CPC分类号： G06K9/6255 , G06K9/6217 , G06K2209/15
摘要： Methods and systems for improved license plate signature matching by similarity learning on synthetic images comprise generating (224) a plurality of synthetic license plate images; applying (230) one or more transformations to the synthetic license plate images to cause the synthetic license plate images to more closely resemble authentic license plate image captures; and providing the synthetic license plate images as inputs to a machine distance learning algorithm in which weighted similarity scores are calculated between signatures of analogous and non-analogous license plate images and one or more sets of signature weights are iteratively adjusted to increase the likelihood that comparing analogous license plate images results in high weighted signature similarity scores and comparing non-analogous license plate images results in low weighted signature similarity scores.

7. 发明公开

EP2565804A1 Text-based searching of image data 失效转让
标题翻译： Textbasierte Suche nach Bilddaten
公开(公告)号：EP2565804A1
公开(公告)日：2013-03-06
申请号：EP12181281.2
申请日：2012-08-22
申请人： Xerox Corporation
发明人： Rodriguez, Jose-Antonio , Perronnin, Florent , Saunders, Craig John
IPC分类号： G06F17/30
CPC分类号： G06F17/30256 , G06F17/30265 , G06F17/30277 , G06K9/3258 , G06K9/4676 , G06K9/6277 , G06K2209/01 , G06K2209/15
摘要： A method and system are disclosed for conducting text-based searches of images using a visual signature associated with each image. A measure of string similarity between a query and an annotation associated with each entry in a first database is computed (S212), and based upon the computed string similarity measures, a set of entries from the first database is selected (S220). Each entry of the first database also includes an associated visual signature. At least one entry is then retrieved from a second database based upon a measure of visual similarity between a visual signature of each of the entries in the second database and the visual signatures of the entries in the selected set. Information corresponding to the retrieved entries from the second database is then generated.
摘要翻译：公开了一种用于使用与每个图像相关联的视觉签名进行基于图像的基于文本的搜索的方法和系统。计算与第一数据库中的每个条目相关联的查询和注释之间的字符串相似度的度量（S212），并且基于所计算的字符串相似性度量，选择来自第一数据库的一组条目（S220）。第一数据库的每个条目还包括相关联的视觉签名。基于第二数据库中的每个条目的视觉签名与所选集合中的条目的视觉签名之间的视觉相似度的度量，从第二数据库检索至少一个条目。然后生成与从第二数据库检索到的条目相对应的信息。

8. 发明授权

EP2565804B1 Text-based searching of image data 失效转让
公开(公告)号：EP2565804B1
公开(公告)日：2018-10-17
申请号：EP12181281.2
申请日：2012-08-22
申请人： Xerox Corporation
发明人： Rodriguez, Jose-Antonio , Perronnin, Florent , Saunders, Craig John
IPC分类号： G06F17/30
CPC分类号： G06F17/30256 , G06F17/30265 , G06F17/30277 , G06K9/3258 , G06K9/4676 , G06K9/6277 , G06K2209/01 , G06K2209/15
摘要： A method and system are disclosed for conducting text-based searches of images using a visual signature associated with each image. A measure of string similarity between a query and an annotation associated with each entry in a first database is computed (S212), and based upon the computed string similarity measures, a set of entries from the first database is selected (S220). Each entry of the first database also includes an associated visual signature. At least one entry is then retrieved from a second database based upon a measure of visual similarity between a visual signature of each of the entries in the second database and the visual signatures of the entries in the selected set. Information corresponding to the retrieved entries from the second database is then generated.

9. 发明授权

EP2551792B1 System and method for computing the visual profile of a place 有权
标题翻译：系统和方法，用于计算图的视觉简档
公开(公告)号：EP2551792B1
公开(公告)日：2016-05-18
申请号：EP12175851.0
申请日：2012-07-11
申请人： Xerox Corporation
发明人： Perronnin, Florent , Guerin, Nicolas , Saunders, Craig John
IPC分类号： G06K9/00
CPC分类号： G06K9/00476

10. 发明公开

EP2897082A1 Methods and systems for improved license plate signature matching 有权转让
标题翻译： Verfahren und Systeme zum动词dessertenen Nummernschildsignaturvergleichen
公开(公告)号：EP2897082A1
公开(公告)日：2015-07-22
申请号：EP15154270.1
申请日：2012-11-09
申请人： Xerox Corporation
发明人： Serrano, Jose A Rodriguez , Bala, Raja , Perronnin, Florent , Saunders, Craig John , Zhao, Yonghui
IPC分类号： G06K9/62
CPC分类号： G06K9/6255 , G06K9/6217 , G06K2209/15
摘要： Methods and systems for improved license plate signature matching by similarity learning on synthetic images comprise generating (224) a plurality of synthetic license plate images; applying (230) one or more transformations to the synthetic license plate images to cause the synthetic license plate images to more closely resemble authentic license plate image captures; and providing the synthetic license plate images as inputs to a machine distance learning algorithm in which weighted similarity scores are calculated between signatures of analogous and non-analogous license plate images and one or more sets of signature weights are iteratively adjusted to increase the likelihood that comparing analogous license plate images results in high weighted signature similarity scores and comparing non-analogous license plate images results in low weighted signature similarity scores.
摘要翻译：用于通过合成图像上的相似性学习改进车牌签名匹配的方法和系统包括生成（224）多个合成车牌图像; 对合成车牌图像应用（230）一个或多个变换，以使合成车牌图像更接近于真正的车牌图像拍摄; 并且将合成车牌图像作为输入提供给机器距离学习算法，其中在类似和非类似车牌图像的签名与一组或多组签名权重之间计算加权相似度分数，以迭代地调整比较的可能性类似车牌图像导致高加权签名相似性得分，并且比较非类似车牌图像导致低加权签名相似性得分。

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