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

WO2011017653A1 FACIAL RECOGNITION WITH SOCIAL NETWORK AIDING 审中-公开
标题翻译：社会网络援助的真实认可
公开(公告)号：WO2011017653A1
公开(公告)日：2011-02-10
申请号：PCT/US2010/044771
申请日：2010-08-06
申请人： GOOGLE INC. , PETROU, David , RABINOVICH, Andrew , ADAM, Hartwig
发明人： PETROU, David , RABINOVICH, Andrew , ADAM, Hartwig
IPC分类号： G06F17/30 , G06K9/00
CPC分类号： G06F17/30268 , G06F17/30256 , G06F17/30277 , G06F17/3053 , G06F17/30867 , G06K9/00288 , G06K9/00677
摘要： A facial recognition search system identifies one or more likely names (or other personal identifiers) corresponding to the facial image(s) in a query as follows. After receiving the visual query with one or more facial images, the system identifies images that potentially match the respective facial image in accordance with visual similarity criteria. Then one or more persons associated with the potential images are identified. For each identified person, person-specific data comprising metrics of social connectivity to the requester are retrieved from a plurality of applications such as communications applications, social networking applications, calendar applications, and collaborative applications. An ordered list of persons is then generated by ranking the identified persons in accordance with at least metrics of visual similarity between the respective facial image and the potential image matches and with the social connection metrics. Finally, at least one person identifier from the list is sent to the requester.
摘要翻译：面部识别搜索系统如下所述在查询中识别与面部图像相对应的一个或多个可能的名称（或其他个人标识符）。在接收到具有一个或多个面部图像的视觉查询之后，系统根据视觉相似性标准识别潜在地匹配相应面部图像的图像。然后识别与潜在图像相关联的一个或多个人。对于每个已识别的人，从诸如通信应用，社交网络应用，日历应用和协作应用的多个应用中检索包括对请求者的社交连接性度量的个人特定数据。然后通过根据相应的面部图像和潜在图像匹配之间的视觉相似性的度量以及与社会连接度量进行评估来对所识别的人进行排名来生成有序的人物列表。最后，从列表中至少有一个人标识符被发送到请求者。

2. 发明申请

WO2011062911A1 AUTOMATICALLY MINING PERSON MODELS OF CELEBRITIES FOR VISUAL SEARCH APPLICATIONS 审中-公开
标题翻译：自动采矿人员视觉搜索应用人员模型
公开(公告)号：WO2011062911A1
公开(公告)日：2011-05-26
申请号：PCT/US2010/056869
申请日：2010-11-16
申请人： GOOGLE INC. , ROSS, David , RABINOVICH, Andrew , PILLAI, Anand , ADAM, Hartwig
发明人： ROSS, David , RABINOVICH, Andrew , PILLAI, Anand , ADAM, Hartwig
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/622 , G06K9/00295
摘要： Methods and systems for automated identification of celebrity face images are provided that generate a name list of prominent celebrities, obtain a set of images and corresponding feature vectors for each name, detect faces within the set of images, and remove non-face images. An analysis of the images is performed using an intra-model analysis, an inter-model analysis, and a spectral analysis to return highly accurate biometric models for each of the individuals present in the name list. Recognition is then performed based on precision and recall to identify the face images as belonging to a celebrity or indicate that the face is unknown.
摘要翻译：提供用于自动识别名人脸图像的方法和系统，其产生着名名人的名单，获得一组图像和每个名称的相应特征向量，检测该图像集内的面部，并且去除非面部图像。使用模型内分析，模型间分析和光谱分析来执行图像的分析，以返回列表中存在的每个个体的高度精确的生物特征模型。然后基于精度和召回来执行识别，以将脸部图像识别为属于名人，或指示脸部未知。

3. 发明申请

WO2004111930A9 COLOR UNMIXING AND REGION OF INTEREST DETECTION IN TISSUE SAMPLES 审中-公开
标题翻译：组织样本中色彩的兴趣和兴趣区域的检测
公开(公告)号：WO2004111930A9
公开(公告)日：2005-05-06
申请号：PCT/US2004016858
申请日：2004-05-28
申请人： RABINOVICH ANDREW M
发明人： RABINOVICH ANDREW M
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62 , G06T20060101
CPC分类号： G06K9/0014 , G06K9/00127 , G06K9/4619 , G06K9/624
摘要： In a method and system and machine-readable medium, colors in an image (200) are unmixed (202) using a matrix X = AS, where A is a ns. x nd matrix of spectral definitions, where s is the number of spectral components and d is the number of dyes into which the image is decomposed, and where S is a ns x l matrix of amounts of each dye at every pixel, where l is the number of pixels; the matrix X is constrained for solution by an unsupervised matrix decomposition method having constraints consistent with properties of an additive color model; and nd is determined. A texture is determined to identify areas of interest. Further processing may automatically measure cell dye concentration in the determined regions of interest.
摘要翻译：在方法和系统和机器可读介质中，图像（200）中的颜色使用矩阵X = AS而不混合（202），其中A是ns。光谱定义的第x个矩阵，其中s是光谱分量的数量，d是图像分解成的染料的数量，其中S是每个像素处的每个染料的量的ns×1矩阵，其中l是像素数; 通过具有与加性颜色模型的属性一致的约束的无监督矩阵分解方法来限制矩阵X的解; 并确定nd。确定纹理以识别感兴趣的区域。进一步的处理可以自动测量所确定的感兴趣区域中的细胞染料浓度。

4. 发明申请

WO2004111930A3 COLOR UNMIXING AND REGION OF INTEREST DETECTION IN TISSUE SAMPLES 审中-公开
标题翻译：彩色人体组织样本和感兴趣区域检测
公开(公告)号：WO2004111930A3
公开(公告)日：2005-03-24
申请号：PCT/US2004016858
申请日：2004-05-28
申请人： RABINOVICH ANDREW M
发明人： RABINOVICH ANDREW M
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62 , G06T20060101
CPC分类号： G06K9/0014 , G06K9/00127 , G06K9/4619 , G06K9/624
摘要： In a method and system and machine-readable medium, colors in an image (200) are unmixed (202) using a matrix X = AS, where A is a ns. x nd matrix of spectral definitions, where s is the number of spectral components and d is the number of dyes into which the image is decomposed, and where S is a ns x l matrix of amounts of each dye at every pixel, where l is the number of pixels; the matrix X is constrained for solution by an unsupervised matrix decomposition method having constraints consistent with properties of an additive color model; and nd is determined. A texture is determined to identify areas of interest. Further processing may automatically measure cell dye concentration in the determined regions of interest.
摘要翻译：在方法和系统以及机器可读介质中，使用矩阵X = AS将图像（200）中的颜色解混（202），其中A是ns。 x是光谱定义的矩阵，其中s是光谱分量的数量，并且d是图像被分解成的染料的数量，并且其中S是在每个像素处的每种染料的量的ns×1矩阵，其中l是像素数量; 通过具有与加性颜色模型的性质一致的约束的无监督矩阵分解方法来约束矩阵X以求解; 并且nd被确定。纹理被确定以识别感兴趣的区域。进一步处理可以自动测量所确定的感兴趣区域中的细胞染料浓度。

5. 发明申请

WO2004111930A2 COLOR UNMIXING AND REGION OF INTEREST DETECTION IN TISSUE SAMPLES 审中-公开
标题翻译：组织样本中色彩的兴趣和兴趣区域的检测
公开(公告)号：WO2004111930A2
公开(公告)日：2004-12-23
申请号：PCT/US2004/016858
申请日：2004-05-28
申请人： RABINOVICH, Andrew, M.
发明人： RABINOVICH, Andrew, M.
IPC分类号： G06T
CPC分类号： G06K9/0014 , G06K9/00127 , G06K9/4619 , G06K9/624
摘要： In a method and system and machine-readable medium, colors in an image are unmixed using a matrix X = AS, where A is a n s . x n d matrix of spectral definitions, where s is the number of spectral components and d is the number of dyes into which the image is decomposed, and where S is a n s x / matrix of amounts of each dye at every pixel, where / is the number of pixels; the matrix X is constrained for solution by an unsupervised matrix decomposition method having constraints consistent with properties of an additive color model; and n d is determined. A texture is determined to identify areas of interest. Further processing may automatically measure cell dye concentration in the determined regions of interest.
摘要翻译：在方法和系统和机器可读介质中，图像中的颜色使用矩阵X = AS而不混合，其中A是ns。光谱定义的第x个矩阵，其中s是光谱分量的数量，d是图像被分解成的染料的数量，其中S是每个像素处的每个染料的量的ns×/矩阵，其中，像素数; 通过具有与加性颜色模型的属性一致的约束的无监督矩阵分解方法来限制矩阵X的解; 并确定nd。确定纹理以识别感兴趣的区域。进一步的处理可以自动测量所确定的感兴趣区域中的细胞染料浓度。

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