专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明授权

US06224189B1 Enhanced text and line-art quality for multi-resolution marking devices 有权
标题翻译：为多分辨率标记设备提供增强的文字和线条画质
公开(公告)号：US06224189B1
公开(公告)日：2001-05-01
申请号：US09383865
申请日：1999-08-26
申请人： Doron Kletter
发明人： Doron Kletter
IPC分类号： B41J221
CPC分类号： H04N1/58 , B41J2/2132 , G06K15/02 , G06K2215/0094
摘要： A technique for producing high quality output on a mixed-resolution color printing device. Unlike current techniques that impose global ink-limit and dot scheduling constraints, the new method can improve the quality of text and line-art features by rendering the outline at the highest resolution yet maintaining an overall ink-limit by compensating the inside density. The new method uses a programmable unsharp mask filter to detect and outline these edges. The system uses bigger black drops than for the three colors, so the big drops have to be treated differently for avoid saturating the paper. The method allows a little saturation, selectively as necessary, and controls the drop spacing and color correction to minimize the problem for nearby pixels. The result is that the quality of rendering is superior to that of the current rendering methods, especially for text and fine line-art graphics. The technique also limits head heating.
摘要翻译：一种用于在混合分辨率彩色打印设备上产生高质量输出的技术。不同于当前施加全局墨水限制和点调度约束的技术，新方法可以通过以最高分辨率渲染轮廓并通过补偿内部密度来保持整体墨水极限来提高文本和线条特征的质量。新方法使用可编程的锐化掩模滤波器来检测和勾勒出这些边。该系统使用比三种颜色更大的黑色液滴，因此大滴必须以不同的方式进行处理，以避免纸张饱和。该方法可根据需要选择一点饱和度，并控制液滴间距和颜色校正，以最小化附近像素的问题。结果是，渲染的质量优于当前的渲染方法，特别是对于文本和细线条图形。该技术还限制了头部加热。

42. 发明授权

US08917908B2 Distributed object tracking for augmented reality application 有权
标题翻译：用于增强现实应用的分布式对象跟踪
公开(公告)号：US08917908B2
公开(公告)日：2014-12-23
申请号：US13548092
申请日：2012-07-12
申请人： Michael Roberts , Doron Kletter , Anselm Hook , James M. A. Begole
发明人： Michael Roberts , Doron Kletter , Anselm Hook , James M. A. Begole
IPC分类号： G06K9/00
CPC分类号： G06F17/30805 , G06F17/3079 , G06F17/3082
摘要： One embodiment of the present invention provides a system for tracking and distributing annotations for a video stream. During operation, the system receives, at an annotation server, the video stream originating from a remote field computer, extracts a number of features from the received video stream, and identifies a group of features that matches a known feature group, which is associated with an annotation. The system further associates the identified group of features with the annotation, and forwards the identified group of features and the annotation to the remote field computer, thereby facilitating the remote field computer to associate the annotation with a group of locally extracted features and display the video stream with the annotation placed in a location based at least on locations of the locally extracted features.
摘要翻译：本发明的一个实施例提供了一种用于跟踪和分发用于视频流的注释的系统。在操作期间，系统在注释服务器处接收来自远程现场计算机的视频流，从接收到的视频流中提取多个特征，并且识别与已知特征组相匹配的一组特征，其与注释。所述系统还将所识别的特征组与所述注释相关联，并且将所识别的特征组和所述注释转发到所述远程现场计算机，从而便于所述远程现场计算机将所述注释与一组本地提取的特征相关联并且显示所述视频至少基于本地提取的特征的位置将注释放置在位置中的流。

43. 发明申请

US20120093354A1 FINDING SIMILAR CONTENT IN A MIXED COLLECTION OF PRESENTATION AND RICH DOCUMENT CONTENT USING TWO-DIMENSIONAL VISUAL FINGERPRINTS 有权
标题翻译：在使用两维视觉指纹的混合收藏中发现类似的内容和丰富的文档内容
公开(公告)号：US20120093354A1
公开(公告)日：2012-04-19
申请号：US12907251
申请日：2010-10-19
申请人： Doron Kletter
发明人： Doron Kletter
IPC分类号： G06K9/00
CPC分类号： G06K9/00456
摘要： Visual fingerprinting is used to provide a robust and highly effective method of finding similar content in a large document collection of rich document content composed of multiple text, line-art, and photo image objects. The visual fingerprints capture unique two-dimensional localized aspects of document appearance. The visual fingerprints are highly distinctive; fast for lookup; compact for storage requirements; and scalable to large document collections.
摘要翻译：视觉指纹用于提供一种在由多个文本，线条艺术和照片图像对象组成的丰富文档内容的大型文档集合中查找类似内容的鲁棒且高效的方法。视觉指纹捕获文件外观的独特二维本地化方面。视觉指纹是非常独特的; 快速查找; 紧凑型存储要求; 并可扩展到大型文档集合。

44. 发明授权

US08144947B2 System and method for finding a picture image in an image collection using localized two-dimensional visual fingerprints 失效
标题翻译：用于使用局部二维视觉指纹在图像集合中查找图像的系统和方法
公开(公告)号：US08144947B2
公开(公告)日：2012-03-27
申请号：US12163186
申请日：2008-06-27
申请人： Doron Kletter
发明人： Doron Kletter
IPC分类号： G06K9/54 , G06K9/00
CPC分类号： G06F17/30256 , G06K9/00442 , G06K9/00744 , G06K9/4676 , G06K9/6282
摘要： An image management method and system provides for storing, indexing, searching and/or retrieving image data. The content of an image collection is pre-processed to identify stable and repeatable keypoints for each image in the collection. Fingerprint information is computed from local groups of keypoints, and the resulting fingerprint information is stored in a compact fingerprint database. The computing of the fingerprint information is based on combinations of a subgroup of the strongest keypoints in an image, called anchor keypoints, in addition to a number of non-anchor keypoints. For each fingerprint in the compact fingerprint database, a sequence of candidate fingerprint combinations is generated and stored in a Fan Tree and/or hashtable and a corresponding fingerprint data structure. The sequence of fingerprint combinations allows several non-anchor keypoints to be missing, while still allowing the system and method to correctly detect fingerprints with high accuracy. A realtime image query is performed by identifying keypoints and computing fingerprints from the query image and matching the query fingerprints to the existing Fan Tree and/or hashtable fingerprint data to determine the best matching image or set of images within the collection. At least one target image is retrieved based on the determining operation, and the retrieved target image is displayed, printed, stored and/or transmitted.
摘要翻译：图像管理方法和系统提供存储，索引，搜索和/或检索图像数据。图像集合的内容被预处理，以识别集合中每个图像的稳定和可重复的关键点。从本地的关键点组计算指纹信息，并将生成的指纹信息存储在紧凑的指纹数据库中。除了多个非锚点关键点之外，指纹信息的计算还基于图像中最强关键点的子组合（称为锚点关键点）的组合。对于紧凑指纹数据库中的每个指纹，生成候选指纹组合序列并存储在风扇树和/或散列表和对应的指纹数据结构中。指纹组合的顺序允许几个非锚点关键点丢失，同时仍允许系统和方法以高精度正确检测指纹。通过识别关键点并从查询图像计算指纹并将查询指纹与现有的风扇树和/或散列表指纹数据进行匹配来确定集合内的最佳匹配图像或图像集来执行实时图像查询。基于确定操作检索至少一个目标图像，并且检索到的目标图像被显示，打印，存储和/或发送。

45. 发明申请

US20110197121A1 EFFECTIVE SYSTEM AND METHOD FOR VISUAL DOCUMENT COMPARISON USING LOCALIZED TWO-DIMENSIONAL VISUAL FINGERPRINTS 有权
标题翻译：使用本地化的二维可视指纹图像进行视觉文档比较的有效系统和方法
公开(公告)号：US20110197121A1
公开(公告)日：2011-08-11
申请号：US12701127
申请日：2010-02-05
申请人： Doron Kletter
发明人： Doron Kletter
IPC分类号： G06F17/00
CPC分类号： G06F17/2211 , G06F17/2288 , G06F17/24
摘要： A method and system detects and highlights changes in documents and displays those documents in a side-by-side aligned view. Aspects of a source document and a revised document are detected and compared. Similarities and/or differences between the source document and the revised document are identified and visual identifiers are introduced to maintain consistent and accurate alignment between content in the source document and content in the revised document. A merged single file is output containing the aligned side-by-side view of the source document and the revised document, with all differences between the source document and the revised document visually identified.
摘要翻译：方法和系统检测并突出显示文档中的更改，并在并排对齐的视图中显示这些文档。检测并比较源文件和修订文档的方面。识别源文档和修订文档之间的相似性和/或差异，并引入视觉标识符，以便在源文档中的内容和修订文档中的内容之间保持一致和准确的对齐。输出合并的单个文件，其中包含源文档和修订文档的并排并排视图，源文档和经修订的文档之间的所有差异都可视化识别。

46. 发明授权

US07835044B2 Method for tetrahedral interpolation computations using data-level parallelism 有权
标题翻译：使用数据级并行的四面插值计算方法
公开(公告)号：US07835044B2
公开(公告)日：2010-11-16
申请号：US11410626
申请日：2006-04-25
申请人： Alejandro Enrique Brito , Doron Kletter
发明人： Alejandro Enrique Brito , Doron Kletter
IPC分类号： H04N1/46 , G03F3/08 , G09G5/02 , G09G5/00
CPC分类号： H04N1/6019
摘要： A system and method for tetrahedral interpolation computations using data-level parallelism that takes advantage of data-level parallelism in media processors. If the tetrahedron points in a 3D lookup table are packed together in a memory, the interpolation computation can be implemented without extra instructions to unpack them. An algebraic manipulation of the interpolation equation allows computing the difference on the fraction coefficients instead of the tetrahedron node values. Not only will this technique preserve the full precision without over or underflow, but the packed data from the 3D lookup can be used directly, thereby allowing a faster implementation of the color space transformation overall and implementing as part of a direct-copy image path on a media processor. Such a system and method allows the implementation of the direct copy pipeline to function at the required performance rate as requested by a customer specification while obtaining the required product design speed.
摘要翻译：使用数据级并行的四面插值计算的系统和方法，其利用媒体处理器中的数据级并行性。如果3D查找表中的四面体指向一个包装在一个存储器中，则可以实现插值计算，而无需额外的指令来解压缩它们。内插方程的代数操作允许计算分数系数的差异而不是四面体节点值。这种技术不仅可以保持完整的精度，而且不会出现上溢或下溢，而是可以直接使用3D查找的打包数据，从而可以更快地实现颜色空间转换，并将其作为直接复制图像路径的一部分媒体处理器。这样的系统和方法允许直接拷贝流水线的实施按照客户规格要求的所需性能速率运行，同时获得所需的产品设计速度。

47. 发明申请

US20090324100A1 METHOD AND SYSTEM FOR FINDING A DOCUMENT IMAGE IN A DOCUMENT COLLECTION USING LOCALIZED TWO-DIMENSIONAL VISUAL FINGERPRINTS 有权
标题翻译：使用本地化的二维可视指纹在文档集合中查找文档图像的方法和系统
公开(公告)号：US20090324100A1
公开(公告)日：2009-12-31
申请号：US12147624
申请日：2008-06-27
申请人： Doron Kletter , Eric Saund , William C. Janssen, JR. , Russel R. Atkinson
发明人： Doron Kletter , Eric Saund , William C. Janssen, JR. , Russel R. Atkinson
IPC分类号： G06K9/68
CPC分类号： G06K9/00442 , G06F17/30256 , G06K9/2054 , G06K9/4676 , G06K2209/01
摘要： An image management method and system provides for storing, indexing, searching, and/or retrieving image data. Keypoints are identified in images, including keypoints in a query image of a query document, and keypoints in potential target document images of a collection of potential target documents. Fingerprint information from the keypoints are generated, and the fingerprint information of a query image is compared with fingerprint information of potential target document images, found in the collection of potential target documents. A best match is determined between the fingerprint information of the query image and the potential target document images. At least one target document image is retrieved based on the determined best match. The retrieved at least one target image may then be displayed, printed or transmitted.
摘要翻译：图像管理方法和系统提供存储，索引，搜索和/或检索图像数据。在图像中识别关键点，包括查询文档的查询图像中的关键点，以及潜在目标文档集合的潜在目标文档图像中的关键点。生成来自关键点的指纹信息，并将查询图像的指纹信息与潜在目标文档集合中发现的潜在目标文档图像的指纹信息进行比较。在查询图像的指纹信息和潜在目标文档图像之间确定最佳匹配。基于确定的最佳匹配来检索至少一个目标文档图像。然后可以显示，打印或发送所检索的至少一个目标图像。

48. 发明申请

US20090324026A1 SYSTEM AND METHOD FOR FINDING A PICTURE IMAGE IN AN IMAGE COLLECTION USING LOCALIZED TWO-DIMENSIONAL VISUAL FINGERPRINTS 失效
标题翻译：使用本地化的二维视觉指纹图像集合中的图像图像的系统和方法
公开(公告)号：US20090324026A1
公开(公告)日：2009-12-31
申请号：US12163186
申请日：2008-06-27
申请人： Doron Kletter
发明人： Doron Kletter
IPC分类号： G06K9/80
CPC分类号： G06F17/30256 , G06K9/00442 , G06K9/00744 , G06K9/4676 , G06K9/6282
摘要： An image management method and system provides for storing, indexing, searching and/or retrieving image data. The content of an image collection is pre-processed to identify stable and repeatable keypoints for each image in the collection. Fingerprint information is computed from local groups of keypoints, and the resulting fingerprint information is stored in a compact fingerprint database. The computing of the fingerprint information is based on combinations of a subgroup of the strongest keypoints in an image, called anchor keypoints, in addition to a number of non-anchor keypoints. For each fingerprint in the compact fingerprint database, a sequence of candidate fingerprint combinations is generated and stored in a Fan Tree and/or hashtable and a corresponding fingerprint data structure. The sequence of fingerprint combinations allows several non-anchor keypoints to be missing, while still allowing the system and method to correctly detect fingerprints with high accuracy. A realtime image query is performed by identifying keypoints and computing fingerprints from the query image and matching the query fingerprints to the existing Fan Tree and/or hashtable fingerprint data to determine the best matching image or set of images within the collection. At least one target image is retrieved based on the determining operation, and the retrieved target image is displayed, printed, stored and/or transmitted.
摘要翻译：图像管理方法和系统提供存储，索引，搜索和/或检索图像数据。图像集合的内容被预处理，以识别集合中每个图像的稳定和可重复的关键点。从本地的关键点组计算指纹信息，并将生成的指纹信息存储在紧凑的指纹数据库中。除了多个非锚点关键点之外，指纹信息的计算还基于图像中最强关键点的子组合（称为锚点关键点）的组合。对于紧凑指纹数据库中的每个指纹，生成候选指纹组合序列并存储在风扇树和/或散列表和对应的指纹数据结构中。指纹组合的顺序允许几个非锚点关键点丢失，同时仍允许系统和方法以高精度正确检测指纹。通过识别关键点并从查询图像计算指纹并将查询指纹与现有的风扇树和/或散列表指纹数据进行匹配来确定集合内的最佳匹配图像或图像集来执行实时图像查询。基于确定操作检索至少一个目标图像，并且检索到的目标图像被显示，打印，存储和/或发送。

49. 发明授权

US07324120B2 Segmentation method and system for scanned documents 有权
标题翻译：扫描文档的分割方法和系统
公开(公告)号：US07324120B2
公开(公告)日：2008-01-29
申请号：US10776516
申请日：2004-02-12
申请人： Donald J. Curry , Asghar Nafarieh , Doron Kletter
发明人： Donald J. Curry , Asghar Nafarieh , Doron Kletter
IPC分类号： G06T11/00
CPC分类号： G06K9/00456 , G06K9/38 , G06K2209/01 , G06T7/11 , G06T7/12 , G06T7/194 , G06T2207/10008 , G06T2207/20012 , G06T2207/20192 , G06T2207/30176 , H04N1/40062
摘要： Methods and systems include a dependent min-max module the receives image data and generates a dependent Min value and a dependent Max value within a window around a pixel of interest. A dynamic threshold module, based on the dependent Min and Max values, generates continuity data and enhanced data suitable for identifying, for example, blobs.
摘要翻译：方法和系统包括依赖的最小 - 最大模块，其接收图像数据，并在感兴趣的像素周围的窗口内生成依赖的最小值和依赖的最大值。动态阈值模块基于相关的最小值和最大值，生成适用于识别例如斑点的连续性数据和增强数据。

50. 发明申请

US20070247648A1 Method for tetrahedral interpolation computations using data-level parallelism 有权
标题翻译：使用数据级并行的四面插值计算方法
公开(公告)号：US20070247648A1
公开(公告)日：2007-10-25
申请号：US11410626
申请日：2006-04-25
申请人： Alejandro Brito , Doron Kletter
发明人： Alejandro Brito , Doron Kletter
IPC分类号： G03F3/08
CPC分类号： H04N1/6019
摘要： A system and method for tetrahedral interpolation computations using data-level parallelism that takes advantage of data-level parallelism in media processors. If the tetrahedron points in a 3D lookup table are packed together in a memory, the interpolation computation can be implemented without extra instructions to unpack them. An algebraic manipulation of the interpolation equation allows computing the difference on the fraction coefficients instead of the tetrahedron node values. Not only will this technique preserve the full precision without over or underflow, but the packed data from the 3D lookup can be used directly, thereby allowing a faster implementation of the color space transformation overall and implementing as part of a direct-copy image path on a media processor. Such a system and method allows the implementation of the direct copy pipeline to function at the required performance rate as requested by a customer specification while obtaining the required product design speed.
摘要翻译：使用数据级并行的四面插值计算的系统和方法，其利用媒体处理器中的数据级并行性。如果3D查找表中的四面体指向一个包装在一个存储器中，则可以实现插值计算，而无需额外的指令来解压缩它们。内插方程的代数操作允许计算分数系数的差异而不是四面体节点值。这种技术不仅可以保持完整的精度，而且不会出现上溢或下溢，而是可以直接使用3D查找的打包数据，从而可以更快地实现颜色空间转换，并将其作为直接复制图像路径的一部分媒体处理器。这样的系统和方法允许直接拷贝流水线的实施按照客户规格要求的所需性能速率运行，同时获得所需的产品设计速度。

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