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

US20060078210A1 Tarp filter 有权
标题翻译：篷布过滤器
公开(公告)号：US20060078210A1
公开(公告)日：2006-04-13
申请号：US11287671
申请日：2005-11-28
申请人： Patrice Simard , Henrique Malvar , Dinei Florencio , David Steinkraus
发明人： Patrice Simard , Henrique Malvar , Dinei Florencio , David Steinkraus
IPC分类号： G06K9/36
CPC分类号： G06T9/004 , G06T9/007
摘要： Systems and methods for performing adaptive filtering are disclosed. The present invention generates probabilities that can be used in an encoder, such as an arithmetic encoder and generates those probabilities in a computationally efficient manner. Probabilities of previously encoded coefficients are employed, effectively, in generating probabilities of the coefficients without regard to directional information. Thus, a large amount of information is adaptively and efficiently used in generating the probabilities. For the coefficients, the probability is computed based at least partly on at least one probability of a previously computed probability of a neighboring coefficient. Then, the coefficients are encoded using those computed probabilities.
摘要翻译：公开了用于执行自适应滤波的系统和方法。本发明产生可以在诸如算术编码器的编码器中使用的概率，并以计算有效的方式生成这些概率。先前编码的系数的概率被有效地用于在不考虑方向信息的情况下生成系数的概率。因此，在生成概率时自适应地有效地使用大量的信息。对于系数，概率至少部分地基于先前计算的相邻系数的概率的至少一个概率来计算。然后，使用那些计算的概率对系数进行编码。

2. 发明申请

US20050271281A1 Clustering 有权
标题翻译：聚类
公开(公告)号：US20050271281A1
公开(公告)日：2005-12-08
申请号：US11198562
申请日：2005-08-05
申请人： Patrice Simard , Henrique Malvar , Erin Renshaw
发明人： Patrice Simard , Henrique Malvar , Erin Renshaw
IPC分类号： G06T7/00 , G06F19/00 , G06K9/20 , G06K9/36 , G06K9/46 , G06K9/62 , G06K9/64 , G06K9/68 , G06T5/00 , G06T11/00
CPC分类号： G06K9/00442 , G06K9/46 , G06K9/6202 , G06K2209/01
摘要： Systems and methods for performing clustering of a document image are disclosed. A property of an extracted mark from a document is compared to the properties of the existing clusters. If the property of the mark fails to match any of the properties of the existing clusters, the mark is added as a new cluster to the existing cluster. One property that can be utilized is x size and y size, which is the width and height, of the existing clusters. Another property that can be employed is ink size, which refers to the ratio of black pixels to total pixels in a cluster. Yet another property that can be utilized is a reduced mark or image, which is a pixel size reduced version the bitmap of the mark and/or cluster. The above properties can be employed to identify mismatches and reduce the number of bit by bit comparisons performed.
摘要翻译：公开了用于执行文档图像的聚类的系统和方法。将来自文档的提取标记的属性与现有集群的属性进行比较。如果标记的属性无法匹配现有集群的任何属性，则该标记作为新集群添加到现有集群。可以使用的一个属性是x size和y size，这是现有集群的宽度和高度。可以使用的另一个属性是墨水大小，其指的是群集中黑色像素与总像素的比例。可以使用的另一个属性是缩小的标记或图像，其是像素尺寸缩小版本的标记和/或集群的位图。可以采用上述特性来识别不匹配并减少进行的逐比较比较。

3. 发明申请

US20070025622A1 SEGMENTED LAYERED IMAGE SYSTEM 有权
标题翻译： SEGMENTED层状图像系统
公开(公告)号：US20070025622A1
公开(公告)日：2007-02-01
申请号：US11465087
申请日：2006-08-16
申请人： Patrice Simard , Erin Renshaw , James Rinker , Henrique Malvar
发明人： Patrice Simard , Erin Renshaw , James Rinker , Henrique Malvar
IPC分类号： G06K9/36
CPC分类号： H04N1/403 , G06K9/00456
摘要： Systems and methods for encoding and decoding document images are disclosed. Document images are segmented into multiple layers according to a mask. The multiple layers are non-binary. The respective layers can then be processed and compressed separately in order to achieve better compression of the document image overall. A mask is generated from a document image. The mask is generated so as to reduce an estimate of compression for the combined size of the mask and multiple layers of the document image. The mask is then employed to segment the document image into the multiple layers. The mask determines or allocates pixels of the document image into respective layers. The mask and the multiple layers are processed and encoded separately so as to improve compression of the document image overall and to improve the speed of so doing. The multiple layers are non-binary images and can, for example, comprise a foreground image and a background image.
摘要翻译：公开了用于编码和解码文档图像的系统和方法。根据掩码将文档图像分割成多个图层。多层是非二进制的。然后可以分别对各个层进行处理和压缩，以便对整个文件图像实现更好的压缩。从文档图像生成蒙版。生成掩模，以减少对于掩模和文档图像的多个层的组合大小的压缩估计。然后使用掩模将文档图像分割成多个层。掩模将文档图像的像素确定或分配到各个图层中。掩模和多层被单独处理和编码，以便整体上改善文档图像的压缩并提高这样做的速度。多层是非二进制图像，并且可以例如包括前景图像和背景图像。

4. 发明申请

US20070242888A1 COMPRESSION OF BI-LEVEL IMAGES WITH EXPLICIT REPRESENTATION OF INK CLUSTERS 有权
标题翻译：压缩图像的双层图像与墨盒的突出表现
公开(公告)号：US20070242888A1
公开(公告)日：2007-10-18
申请号：US11734299
申请日：2007-04-12
申请人： Erin Renshaw , Patrice Simard , Henrique Malvar
发明人： Erin Renshaw , Patrice Simard , Henrique Malvar
IPC分类号： G06K9/36
CPC分类号： G06K9/6202 , G06T9/001 , H04N1/4115 , H04N19/97
摘要： A system and method facilitating compression of bi-level images with explicit representation of ink clusters is provided. The present invention includes a cluster shape estimator that analyzes connected component information, extracts clusters and stores the cluster in a global dictionary, a page dictionary or a store of unclustered shapes. A bitmap estimation from clusters component determines dictionary positions for clusters stored in the global dictionary which are then encoded. A cluster position estimator determines page positions of clusters of the global dictionary and/or the page dictionary that are then encoded. Further, the global dictionary, the page dictionary and the store of unclustered shapes are also encoded.
摘要翻译：提供了一种利用墨簇的显式表示促进双层图像压缩的系统和方法。本发明包括分析连接的分量信息的群集形状估计器，提取群集并将群集存储在全局词典，页面字典或非群集形状的存储中。来自簇组件的位图估计确定存储在全局字典中的簇的字典位置，然后对其进行编码。集群位置估计器确定然后被编码的全局字典和/或页字典的集群的页面位置。此外，还编码了全局字典，页字典和未分簇形状的存储。

5. 发明申请

US20060083439A1 "Don't care" pixel interpolation 有权
公开(公告)号：US20060083439A1
公开(公告)日：2006-04-20
申请号：US11286622
申请日：2005-11-23
申请人： Henrique Malvar , Patrice Simard , James Rinker
发明人： Henrique Malvar , Patrice Simard , James Rinker
IPC分类号： G06K9/40 , G06K9/34
CPC分类号： G06T5/005 , G06T5/20 , G06T7/136 , G06T7/194
摘要： A system and method facilitating image smoothing is provided. The invention includes an image processor having an image receptor and an image smoother. The invention provides for the image smoother to alter the value of a don't care pixel based, at least in part, upon a weighted average of care pixels.

6. 发明申请

US20060171604A1 Block retouching 有权
公开(公告)号：US20060171604A1
公开(公告)日：2006-08-03
申请号：US11393297
申请日：2006-03-30
申请人： Patrice Simard , Henrique Malvar
发明人： Patrice Simard , Henrique Malvar
IPC分类号： G06K9/56 , G06K9/44 , G06K9/40
CPC分类号： G06T5/005 , G06T7/194 , H04N19/60 , H04N19/86
摘要： A system and method facilitating image retouching is provided. The invention includes an image retoucher having a boundary detector and an image extender. The invention provides for the image retoucher to extend care pixels of at least one of a foreground and a background near a detected spurious boundary by altering the binary mask used for compression of the foreground and/or the background.

7. 发明申请

US20070003142A1 Ink warping for normalization and beautification / ink beautification 失效
标题翻译：油墨翘曲正常化和美化/油墨美化
公开(公告)号：US20070003142A1
公开(公告)日：2007-01-04
申请号：US11173243
申请日：2005-07-01
申请人： Patrice Simard , Maneesh Agrawala , David Steinkraus
发明人： Patrice Simard , Maneesh Agrawala , David Steinkraus
IPC分类号： G06K9/00
CPC分类号： G06K9/00416
摘要： Systems and methods are disclosed that facilitate normalizing and beautifying digitally generated handwriting, such as can be generated on a tablet PC or via scanning a handwritten document. A classifier can identify extrema in the digital handwriting and label such extrema according to predefined categories (e.g., bottom, baseline, midline, top, other, . . . ). Multi-linear regression, polynomial regression, etc., can be performed to align labeled extrema to respective and corresponding desired points as indicated by the labels. Additionally, displacement techniques can be applied to the regressed handwriting to optimize legibility for reading by a human viewer and/or for character recognition by a handwriting recognition application. The displacement techniques can comprise a “rubber sheet” displacement algorithm in conjunction with a “rubber rod” displacement algorithm, which can collectively preserve spatial features of the handwriting during warping thereof.
摘要翻译：公开了促进数字生成的笔迹的归一化和美化的系统和方法，诸如可以在平板PC上生成或通过扫描手写文档。分类器可以根据预定类别（例如，底部，基线，中线，顶部，其他等）识别数字手写中的极值并标记这样的极值。可以执行多线性回归，多项式回归等，以将标记的极值与标签所示的相应和对应的期望点对齐。此外，位移技术可以应用于回归的笔迹，以优化由人类观察者阅读的可读性和/或通过手写识别应用的字符识别。位移技术可以包括“橡胶片”位移算法，结合“橡胶棒”位移算法，其可以在其翘曲期间共同保留笔迹的空间特征。

8. 发明申请

US20050125369A1 System and method for accelerating and optimizing the processing of machine learning techniques using a graphics processing unit 有权
标题翻译：用于加速和优化使用图形处理单元的机器学习技术的处理的系统和方法
公开(公告)号：US20050125369A1
公开(公告)日：2005-06-09
申请号：US10837382
申请日：2004-04-30
申请人： Ian Buck , Patrice Simard , David Steinkraus
发明人： Ian Buck , Patrice Simard , David Steinkraus
IPC分类号： G06T1/40 , G06F3/14 , G06F15/18 , G06N3/00 , G06N3/063 , G06N3/08 , G06F17/00 , G06N5/02
CPC分类号： G06K9/00986 , G06N3/08
摘要： A system and method for processing machine learning techniques (such as neural networks) and other non-graphics applications using a graphics processing unit (GPU) to accelerate and optimize the processing. The system and method transfers an architecture that can be used for a wide variety of machine learning techniques from the CPU to the GPU. The transfer of processing to the GPU is accomplished using several novel techniques that overcome the limitations and work well within the framework of the GPU architecture. With these limitations overcome, machine learning techniques are particularly well suited for processing on the GPU because the GPU is typically much more powerful than the typical CPU. Moreover, similar to graphics processing, processing of machine learning techniques involves problems with solving non-trivial solutions and large amounts of data.
摘要翻译：一种用于处理机器学习技术（例如神经网络）和使用图形处理单元（GPU）来加速和优化处理的其他非图形应用的系统和方法。该系统和方法传输一种可用于从CPU到GPU的各种机器学习技术的架构。处理到GPU的转移是通过克服这些限制并在GPU架构的框架内工作良好的几种新技术实现的。由于克服了这些限制，机器学习技术特别适用于GPU上的处理，因为GPU通常比典型的CPU功能更强大。此外，类似于图形处理，机器学习技术的处理涉及解决非平凡解决方案和大量数据的问题。

9. 发明申请

US20070211064A1 PROCESSING MACHINE LEARNING TECHNIQUES USING A GRAPHICS PROCESSING UNIT 有权
标题翻译：使用图形处理单元处理机器学习技术
公开(公告)号：US20070211064A1
公开(公告)日：2007-09-13
申请号：US11748474
申请日：2007-05-14
申请人： Ian Buck , Patrice Simard , David Steinkraus
发明人： Ian Buck , Patrice Simard , David Steinkraus
IPC分类号： G06F13/14
CPC分类号： G06N99/005 , G06N3/08
摘要： A system and method for processing machine learning techniques (such as neural networks) and other non-graphics applications using a graphics processing unit (GPU) to accelerate and optimize the processing. The system and method transfers an architecture that can be used for a wide variety of machine learning techniques from the CPU to the GPU. The transfer of processing to the GPU is accomplished using several novel techniques that overcome the limitations and work well within the framework of the GPU architecture. With these limitations overcome, machine learning techniques are particularly well suited for processing on the GPU because the GPU is typically much more powerful than the typical CPU. Moreover, similar to graphics processing, processing of machine learning techniques involves problems with solving non-trivial solutions and large amounts of data.
摘要翻译：一种用于处理机器学习技术（例如神经网络）和使用图形处理单元（GPU）来加速和优化处理的其他非图形应用的系统和方法。该系统和方法传输一种可用于从CPU到GPU的各种机器学习技术的架构。处理到GPU的转移是通过克服这些限制并在GPU架构的框架内工作良好的几种新技术实现的。由于克服了这些限制，机器学习技术特别适用于GPU上的处理，因为GPU通常比典型的CPU功能更强大。此外，类似于图形处理，机器学习技术的处理涉及解决非平凡解决方案和大量数据的问题。

10. 发明申请

US20070086655A1 Unfolded convolution for fast feature extraction 有权
标题翻译：用于快速特征提取的展开卷积
公开(公告)号：US20070086655A1
公开(公告)日：2007-04-19
申请号：US11250819
申请日：2005-10-14
申请人： Patrice Simard , David Steinkraus , Kumar Chellapilla
发明人： Patrice Simard , David Steinkraus , Kumar Chellapilla
IPC分类号： G06K9/46 , G06K9/64
CPC分类号： G06K9/4628 , G06K2209/01
摘要： Systems and methods are described that facilitate performing feature extraction across multiple received input features to reduce computational overhead associated with feature processing related to, for instance, optical character recognition. Input feature information can be unfolded and concatenated to generate an aggregated input matrix, which can be convolved with a kernel matrix to produce output feature information for multiple output features concurrently.
摘要翻译：描述了有助于在多个接收到的输入特征之间执行特征提取的系统和方法，以减少与例如光学字符识别相关的特征处理相关联的计算开销。输入特征信息可以展开并连接以生成聚合输入矩阵，其可以与内核矩阵进行卷积以同时产生多个输出特征的输出特征信息。

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