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

EP2426622A2 Finding low variance regions in document images for generating image anchor templates for content anchoring, data extraction, and document classification 有权
标题翻译：发现低方差文档图像的区域，用于生成图像模板锚用于锚定内容，数据提取和文件分类
公开(公告)号：EP2426622A2
公开(公告)日：2012-03-07
申请号：EP11177531.8
申请日：2011-08-15
申请人： Palo Alto Research Center Incorporated , Xerox Corporation
发明人： Saund, Eric , Sarkar, Prateek , Brito, Alejandro E. , Bern, Marshall W. , Ragnet, Francois
IPC分类号： G06K9/20 , G06K9/62 , G06K9/46
CPC分类号： G06K9/2054 , G06K9/4671 , G06K9/6255 , G06K2209/01
摘要： Methods of generating image anchor templates from low variance regions of document images of a first class are provided. The methods select (102) a document image from the document images of the first class and align (104) the other document images of the first class to the selected document image. Low variance regions are then determined (106) by comparing the aligned document images and the selected document image and used to generate (108) image anchor templates.
摘要翻译：设置产生从第一类的原稿图像的低方差区域图像锚模板的方法。的方法，由所述第一类的原稿图像中选择（102）的文件图像和对准（104）所述第一类的其它原稿图像到所选择的文档图像。低方差的区域中，然后通过比较对齐原稿图像和所选择的文档图像确定性开采（106）和用于生成（108）图像锚模板。

2. 发明授权

EP2426622B1 Finding low variance regions in document images for generating image anchor templates for content anchoring, data extraction, and document classification 有权
标题翻译：发现低方差文档图像的区域，用于生成图像模板锚用于锚定内容，数据提取和文件分类
公开(公告)号：EP2426622B1
公开(公告)日：2016-03-30
申请号：EP11177531.8
申请日：2011-08-15
申请人： Palo Alto Research Center Incorporated , Xerox Corporation
发明人： Saund, Eric , Sarkar, Prateek , Brito, Alejandro E. , Bern, Marshall W. , Ragnet, Francois
IPC分类号： G06K9/20 , G06K9/62 , G06K9/46
CPC分类号： G06K9/2054 , G06K9/4671 , G06K9/6255 , G06K2209/01

3. 发明公开

EP2426622A3 Finding low variance regions in document images for generating image anchor templates for content anchoring, data extraction, and document classification 有权
标题翻译：发现低方差文档图像的区域，用于生成图像模板锚用于锚定内容，数据提取和文件分类
公开(公告)号：EP2426622A3
公开(公告)日：2013-05-01
申请号：EP11177531.8
申请日：2011-08-15
申请人： Palo Alto Research Center Incorporated , Xerox Corporation
发明人： Saund, Eric , Sarkar, Prateek , Brito, Alejandro E. , Bern, Marshall W. , Ragnet, Francois
IPC分类号： G06K9/20 , G06K9/62 , G06K9/46
CPC分类号： G06K9/2054 , G06K9/4671 , G06K9/6255 , G06K2209/01
摘要： Methods of generating image anchor templates from low variance regions of document images of a first class are provided. The methods select (102) a document image from the document images of the first class and align (104) the other document images of the first class to the selected document image. Low variance regions are then determined (106) by comparing the aligned document images and the selected document image and used to generate (108) image anchor templates.

4. 发明授权

EP1850581B1 Method for tetrahedral interpolation computations using data-level parallelism 有权
公开(公告)号：EP1850581B1
公开(公告)日：2018-12-26
申请号：EP07106837.3
申请日：2007-04-24
申请人： Xerox Corporation
发明人： Brito, Alejandro E. , Kletter, Doron
IPC分类号： H04N1/60
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.

5. 发明公开

EP1850581A2 Method for tetrahedral interpolation computations using data-level parallelism 有权
标题翻译： VerfahrenfürBerechnungen der Interpolation von TetraedernüberdieDatenebenenparallelität
公开(公告)号：EP1850581A2
公开(公告)日：2007-10-31
申请号：EP07106837.3
申请日：2007-04-24
申请人： Xerox Corporation
发明人： Brito, Alejandro E. , Kletter, Doron
IPC分类号： H04N1/60
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。如果三维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复制管道的实现以客户规格要求的所需性能速率工作，同时获得所需的产品设计速度。

6. 发明公开

EP1850581A3 Method for tetrahedral interpolation computations using data-level parallelism 有权
标题翻译：一种用于经由数据平面并行四面体插值的计算方法
公开(公告)号：EP1850581A3
公开(公告)日：2009-10-21
申请号：EP07106837.3
申请日：2007-04-24
申请人： Xerox Corporation
发明人： Brito, Alejandro E. , Kletter, Doron
IPC分类号： H04N1/60
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.

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