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. 发明授权

US08625887B2 Systems and methods for matching visual object components 有权
标题翻译：用于匹配视觉对象组件的系统和方法
公开(公告)号：US08625887B2
公开(公告)日：2014-01-07
申请号：US13182076
申请日：2011-07-13
申请人： Yuan Li , Hartwig Adam
发明人： Yuan Li , Hartwig Adam
IPC分类号： G06K9/62
CPC分类号： G06K9/6256 , G06K9/00624 , G06K9/00718 , G06K9/6201
摘要： Systems and methods for modeling the occurrence of common image components (e.g., sub-regions) in order to improve visual object recognition are disclosed. In one example, a query image may be matched to a training image of an object. A matched region within the training image to which the query image matches may be determined and a determination may be made whether the matched region is located within an annotated image component of the training image. When the matched region matches only to the image component, an annotation associated with the component may be identified. In another example, sub-regions within a plurality of training image corpora may be annotated as common image components including associated information (e.g., metadata). Matching sub-regions appearing in many training images of objects may be down-weighted in the matching process to reduce possible false matches to query images including common image components.
摘要翻译：公开了用于对共同图像分量（例如，子区域）的发生进行建模以便改进视觉对象识别的系统和方法。在一个示例中，查询图像可以与对象的训练图像匹配。可以确定训练图像中与查询图像匹配的匹配区域，并且可以确定匹配区域是否位于训练图像的注释图像分量内。当匹配区域仅与图像分量匹配时，可以识别与该组件相关联的注释。在另一示例中，多个训练图像语料库中的子区域可以被注释为包括关联信息（例如，元数据）的公共图像分量。出现在对象的许多训练图像中的匹配子区域可以在匹配处理中被加权，以减少对包括公共图像分量的查询图像的可能的假匹配。

2. 发明申请

US20130016899A1 Systems and Methods for Matching Visual Object Components 有权
标题翻译：用于匹配可视对象组件的系统和方法
公开(公告)号：US20130016899A1
公开(公告)日：2013-01-17
申请号：US13182076
申请日：2011-07-13
申请人： Yuan Li , Hartwig Adam
发明人： Yuan Li , Hartwig Adam
IPC分类号： G06K9/62
CPC分类号： G06K9/6256 , G06K9/00624 , G06K9/00718 , G06K9/6201
摘要： Systems and methods for modeling the occurrence of common image components (e.g., sub-regions) in order to improve visual object recognition are disclosed. In one example, a query image may be matched to a training image of an object. A matched region within the training image to which the query image matches may be determined and a determination may be made whether the matched region is located within an annotated image component of the training image. When the matched region matches only to the image component, an annotation associated with the component may be identified. In another example, sub-regions within a plurality of training image corpora may be annotated as common image components including associated information (e.g., metadata). Matching sub-regions appearing in many training images of objects may be down-weighted in the matching process to reduce possible false matches to query images including common image components.
摘要翻译：公开了用于对共同图像分量（例如，子区域）的发生进行建模以便改进视觉对象识别的系统和方法。在一个示例中，查询图像可以与对象的训练图像匹配。可以确定训练图像中与查询图像匹配的匹配区域，并且可以确定匹配区域是否位于训练图像的注释图像分量内。当匹配区域仅与图像分量匹配时，可以识别与该组件相关联的注释。在另一示例中，多个训练图像语料库中的子区域可以被注释为包括关联信息（例如，元数据）的公共图像分量。出现在对象的许多训练图像中的匹配子区域可以在匹配处理中被加权，以减少对包括公共图像分量的查询图像的可能的假匹配。

3. 发明授权

US08577131B1 Systems and methods for visual object matching 有权
公开(公告)号：US08577131B1
公开(公告)日：2013-11-05
申请号：US13181015
申请日：2011-07-12
申请人： Yuan Li , Hartwig Adam
发明人： Yuan Li , Hartwig Adam
IPC分类号： G06K9/62
CPC分类号： G06K9/66 , G06K9/6256
摘要： Systems and methods for improving visual object recognition by analyzing query images are disclosed. In one example, a visual object recognition module may determine query images matching objects of a training corpus utilized by the module. Matched query images may be added to the training corpus as training images of a matched object to expand the recognition of the object by the module. In another example, relevant candidate image corpora from a pool of image data may be automatically selected by matching the candidate image corpora against user query images. Selected image corpora may be added to a training corpus to improve recognition coverage. In yet another example, objects unknown to a visual object recognition module may be discovered by clustering query images. Clusters of similar query images may be annotated and added into a training corpus to improve recognition coverage.

4. 发明授权

US08438163B1 Automatic learning of logos for visual recognition 有权
标题翻译：自动学习视觉识别标志
公开(公告)号：US08438163B1
公开(公告)日：2013-05-07
申请号：US13314061
申请日：2011-12-07
申请人： Yuan Li , Hartwig Adam
发明人： Yuan Li , Hartwig Adam
IPC分类号： G06F17/30
CPC分类号： G06F17/30247 , G06F17/30265 , G06F17/3028 , G06F17/30598 , G06K9/00536 , G06K9/6255 , G06K9/6807 , G06K2209/21
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically extracting logos from images. Methods include generating a query list including a plurality of logo search queries, for each logo search query of the plurality of logo search queries: generating a plurality of image search results, each image search result including image data, and clustering the plurality of image search results into a plurality of clusters, each cluster including a plurality of images of the plurality of image search results, extracting, for each cluster of the plurality of clusters, a representative image to provide a plurality of representative images, and a name corresponding to the representative image to provide a plurality of names, and providing the plurality of representative images and the plurality of names to a logo index, the logo index being accessible to identify one or more logo images in a query image.
摘要翻译：方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于从图像自动提取徽标。方法包括为多个标识搜索查询的每个标识搜索查询生成包括多个徽标搜索查询的查询列表：生成多个图像搜索结果，每个图像搜索结果包括图像数据，并且对多个图像搜索进行聚类结果为多个群集，每个群集包括所述多个图像搜索结果的多个图像，针对所述多个群集中的每个群集提取代表图像以提供多个代表图像，以及与所述多个群集对应的名称代表性图像以提供多个名称，并且将多个代表图像和多个名称提供给标识索引，所述标识索引可被访问以识别查询图像中的一个或多个标志图像。

5. 发明授权

US09852156B2 Hybrid use of location sensor data and visual query to return local listings for visual query 有权
公开(公告)号：US09852156B2
公开(公告)日：2017-12-26
申请号：US12855563
申请日：2010-08-12
申请人： David Petrou , John Flynn , Hartwig Adam , Hartmut Neven
发明人： David Petrou , John Flynn , Hartwig Adam , Hartmut Neven
IPC分类号： G06F17/30 , H04W4/02 , H04W64/00
CPC分类号： G06F17/30247 , G06F17/30241 , G06F17/30389 , G06F17/30528 , H04W4/02 , H04W64/00
摘要： A visual query is received from a client system, along with location information for the client system, and processed by a server system. The server system sends the visual query and the location information to a visual query search system, and receives from the visual query search system enhanced location information based on the visual query and the location information. The server system then sends a search query, including the enhanced location information, to a location-based search system. The search system receives and provides to the client one or more search results to the client system.

6. 发明授权

US09137308B1 Method and apparatus for enabling event-based media data capture 有权
标题翻译：用于启用基于事件的媒体数据捕获的方法和装置
公开(公告)号：US09137308B1
公开(公告)日：2015-09-15
申请号：US13346529
申请日：2012-01-09
申请人： David Petrou , Laura Garcia-Barrio , Hartmut Neven , Hartwig Adam
发明人： David Petrou , Laura Garcia-Barrio , Hartmut Neven , Hartwig Adam
IPC分类号： G06F15/16 , H04L29/08 , G06F17/30
CPC分类号： H04L67/12 , G06F17/30 , H04W4/043 , H04W4/185
摘要： A method and apparatus for enabling media data capture based on a real-world user experience is described herein. According to embodiments of the invention, media data is captured by a mobile computing device and transmitted to a server computer system in response to identifying one or more events from sensor data. The server computer system adds the captured media data, along with data identifying the event that initiated the capture of the media data, to a history of real-world experiences of a user of the mobile computing device. The server computer system may further perform one or more recognition processes on the captured media data and, when the one or more recognition processes find a match, associate the recognized items to the captured media data.
摘要翻译：本文描述了一种基于真实用户体验实现媒体数据捕获的方法和装置。根据本发明的实施例，响应于识别来自传感器数据的一个或多个事件，媒体数据由移动计算设备捕获并被发送到服务器计算机系统。服务器计算机系统将所捕获的媒体数据以及识别发起媒体数据捕获的事件的数据与移动计算设备的用户的真实体验的历史相加。服务器计算机系统可以进一步对所捕获的媒体数据执行一个或多个识别过程，并且当一个或多个识别过程找到匹配时，将所识别的项目与所捕获的媒体数据相关联。

7. 发明申请

US20150169987A1 METHOD AND APPARATUS FOR SEMANTIC ASSOCIATION OF IMAGES WITH AUGMENTATION DATA 有权
标题翻译：具有附加数据的图像的语义关联的方法和装置
公开(公告)号：US20150169987A1
公开(公告)日：2015-06-18
申请号：US13151626
申请日：2011-06-02
申请人： Shailesh Nalawadi , Hartmut Neven , Hartwig Adam
发明人： Shailesh Nalawadi , Hartmut Neven , Hartwig Adam
IPC分类号： G06F17/30 , G06K9/46 , G06K9/00 , G06K9/62
CPC分类号： G06F17/3028 , G06F17/30247 , G06K9/00671
摘要： A method and apparatus for enabling semantic association of images with augmentation data is described. The method may include receiving digital image data captured by a mobile device. The method may also include performing image recognition analysis on an object within the digital image data to identify the object. The method may also include querying a semantic associations database based on a determined identify of the object to determine a secondary meaning associated with the object, and transmitting augmentation data to the mobile device that is semantically relevant to the object based on the secondary meaning.
摘要翻译：描述了用于使得具有增强数据的图像的语义关联的方法和装置。该方法可以包括接收由移动设备捕获的数字图像数据。该方法还可以包括对数字图像数据内的对象执行图像识别分析以识别对象。该方法还可以包括基于所确定的对象的标识来查询语义关联数据库，以确定与对象相关联的次要含义，以及基于次要含义将增加数据发送到与对象语义相关的移动设备。

8. 发明申请

US20150169558A1 IDENTIFYING RESPONSIVE RESOURCES ACROSS STILL IMAGES AND VIDEOS 有权
标题翻译：通过图像和视频识别响应性资源
公开(公告)号：US20150169558A1
公开(公告)日：2015-06-18
申请号：US13098368
申请日：2011-04-29
申请人： Ming Zhao , Yang Song , Hartwig Adam , Ullas Gargi , Yushi Jing , Henry A. Rowley
发明人： Ming Zhao , Yang Song , Hartwig Adam , Ullas Gargi , Yushi Jing , Henry A. Rowley
IPC分类号： G06K9/62 , G06F17/10 , G06F17/30
CPC分类号： G06F17/3005 , G06F17/10 , G06F17/3002 , G06F17/30029 , G06F17/3079 , G06F17/30864 , G06F19/00 , G06K9/00751 , G06K9/629
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for associating still images and videos. One method includes receiving a plurality of images and a plurality of videos and determining whether the images are related to the videos. The determining includes, for an image and a video, extracting features from the image and extracting features frames of the video, and comparing the features to determine whether the image is related to the video. The method further includes maintaining a data store storing data associating each image with each video determined to be related to the image.
摘要翻译：方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于关联静止图像和视频。一种方法包括接收多个图像和多个视频并确定图像是否与视频相关。该确定包括对于图像和视频，从图像中提取特征并提取视频的特征帧，并且比较特征以确定图像是否与视频相关。该方法还包括维护数据存储器，存储将每个图像与确定为与图像相关的每个视频相关联的数据。

9. 发明申请

US20150169525A1 AUGMENTED REALITY IMAGE ANNOTATION 审中-公开
标题翻译：已实现的现实图像注释
公开(公告)号：US20150169525A1
公开(公告)日：2015-06-18
申请号：US13619457
申请日：2012-09-14
申请人： Leon Gomes Palm , Hartwig Adam , Dmytro Kalenichenko
发明人： Leon Gomes Palm , Hartwig Adam , Dmytro Kalenichenko
IPC分类号： G06F17/24 , G06F17/30
CPC分类号： G06F17/241 , G06F16/9558 , G06Q10/10 , G06Q50/01
摘要： A method and system for performing augmented reality processing generates annotation information for display on a device. An annotation request for an image is sent to an annotation service. The annotation service identifies elements in the image indicative of an individual and obtains user profile results for the individual. The user profile results are used to generate annotation information, which is presented for display on a device as an overlay to the image. The annotation information may include links to information that are selectable by a user of the device.
摘要翻译：用于执行增强现实处理的方法和系统产生用于在设备上显示的注释信息。图像的注释请求被发送到注释服务。注释服务识别图像中指示个体的元素，并获得个人的用户简档结果。用户简档结果用于生成注释信息，其被呈现以在设备上显示为图像的覆盖。注释信息可以包括可由设备的用户选择的信息的链接。

10. 发明授权

US07697735B2 Image based multi-biometric system and method 有权
标题翻译：基于图像的多生物识别系统和方法
公开(公告)号：US07697735B2
公开(公告)日：2010-04-13
申请号：US11158906
申请日：2005-06-21
申请人： Hartwig Adam , Hartmut Neven , Johannes B. Steffens
发明人： Hartwig Adam , Hartmut Neven , Johannes B. Steffens
IPC分类号： G06K9/00
CPC分类号： G06K9/6293 , G06K9/00221 , G06K9/00281 , G06K9/00597 , G06K9/0061 , G06K9/00885
摘要： This disclosure describes methods to integrate face, skin and iris recognition to provide a biometric system for identifying individuals. These methods only require a digital image depicting a human face as source data.
摘要翻译：本公开描述了整合面部，皮肤和虹膜识别以提供用于识别个体的生物识别系统的方法。这些方法只需要将人脸描绘成源数据的数字图像。

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