Ink warping for normalization and beautification / ink beautification
    1.
    发明授权
    Ink warping for normalization and beautification / ink beautification 失效
    油墨翘曲正常化和美化/油墨美化

    公开(公告)号:US07593574B2

    公开(公告)日:2009-09-22

    申请号:US11173243

    申请日:2005-07-01

    IPC分类号: G06K9/18

    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。

    Elastic distortions for automatic generation of labeled data
    2.
    发明授权
    Elastic distortions for automatic generation of labeled data 有权
    用于自动生成标记数据的弹性失真

    公开(公告)号:US07418128B2

    公开(公告)日:2008-08-26

    申请号:US10631511

    申请日:2003-07-31

    IPC分类号: G06K9/62

    CPC分类号: G06K9/6256

    摘要: A system that facilitates generation of data that can be employed in connection with training a classifier. The system comprises a component that receives a data set that is employed in connection with training the classifier, and an expansion component that applies elastic distortion algorithm(s) to a subset of the data set to generate additional labeled training data.

    摘要翻译: 一种有助于产生可以与训练分类器结合使用的数据的系统。 该系统包括接收与训练分类器结合使用的数据集的组件以及将弹性失真算法应用于数据集的子集以产生附加标记的训练数据的扩展组件。

    System and method for accelerating and optimizing the processing of machine learning techniques using a graphics processing unit
    3.
    发明授权
    System and method for accelerating and optimizing the processing of machine learning techniques using a graphics processing unit 有权
    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:US07219085B2

    公开(公告)日:2007-05-15

    申请号:US10837382

    申请日:2004-04-30

    IPC分类号: G06F15/80

    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。

    Unfolded convolution for fast feature extraction
    4.
    发明授权
    Unfolded convolution for fast feature extraction 有权
    用于快速特征提取的展开卷积

    公开(公告)号:US07634137B2

    公开(公告)日:2009-12-15

    申请号:US11250819

    申请日:2005-10-14

    IPC分类号: G06K9/46

    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。

    Processing machine learning techniques using a graphics processing unit
    5.
    发明授权
    Processing machine learning techniques using a graphics processing unit 有权
    处理机器学习技术使用图形处理单元

    公开(公告)号:US07548892B2

    公开(公告)日:2009-06-16

    申请号:US11748474

    申请日:2007-05-14

    IPC分类号: G06F15/18 G06K9/62

    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。

    Logical structure layout identification and classification for offline character recognition
    6.
    发明授权
    Logical structure layout identification and classification for offline character recognition 有权
    逻辑结构布局识别和离线字符识别分类

    公开(公告)号:US07844114B2

    公开(公告)日:2010-11-30

    申请号:US11299873

    申请日:2005-12-12

    IPC分类号: G06K9/18

    CPC分类号: G06K9/80

    摘要: A method and system for implementing character recognition is described herein. An input character is received. The input character is composed of one or more logical structures in a particular layout. The layout of the one or more logical structures is identified. One or more of a plurality of classifiers are selected based on the layout of the one or more logical structures in the input character. The entire character is input into the selected classifiers. The selected classifiers classify the logical structures. The outputs from the selected classifiers are then combined to form an output character vector.

    摘要翻译: 本文描述了用于实现字符识别的方法和系统。 接收到一个输入字符。 输入字符由特定布局中的一个或多个逻辑结构组成。 识别一个或多个逻辑结构的布局。 基于输入字符中的一个或多个逻辑结构的布局来选择多个分类器中的一个或多个。 整个字符被输入到所选择的分类器中。 所选分类器对逻辑结构进行分类。 然后将所选分类器的输出组合以形成输出字符向量。

    Activity detector
    9.
    发明授权
    Activity detector 有权
    活动检测器

    公开(公告)号:US07386171B2

    公开(公告)日:2008-06-10

    申请号:US11845588

    申请日:2007-08-27

    申请人: Patrice Y. Simard

    发明人: Patrice Y. Simard

    IPC分类号: G06K9/46

    CPC分类号: G06K9/00456

    摘要: A system and method facilitating activity (e.g., dithering/half toning and/or noise) detection is provided. The invention includes an activity detection system having a connected component analyzer and an activity detector. The invention provides for the quantity of connected component(s) in and/or intersecting a region surrounding a pixel to be determined. The activity detector provides an activity map output based, at least in part, upon the quantity of connected component(s) in and/or intersecting the region. The invention further provides for an optional image processor. In one example, if the quantity exceeds a first threshold, dithering/half toning is detected and appropriate action can be taken. Additionally, if the quantity is less than a second threshold, noise is detected and appropriate action can be taken.

    摘要翻译: 提供了促进活动(例如,抖动/半色调和/或噪声)检测的系统和方法。 本发明包括具有连接分量分析器和活动检测器的活动检测系统。 本发明提供在要确定的像素周围的区域中和/或相交的连接分量的量。 活动检测器至少部分地基于在区域中和/或与该区域相交的连接分量的量来提供活动图输出。 本发明还提供了一种可选的图像处理器。 在一个示例中,如果数量超过第一阈值,则检测到抖动/半色调,并且可以采取适当的动作。 此外,如果数量小于第二阈值,则检测噪声并且可以采取适当的动作。

    System and method facilitating pattern recognition
    10.
    发明授权
    System and method facilitating pattern recognition 有权
    系统和方法促进模式识别

    公开(公告)号:US07286699B2

    公开(公告)日:2007-10-23

    申请号:US11327913

    申请日:2006-01-09

    IPC分类号: G06K9/00 G06K9/62

    摘要: A system and method facilitating pattern recognition is provided. The invention includes a pattern recognition system having a convolutional neural network employing feature extraction layer(s) and classifier layer(s). The feature extraction layer(s) comprises convolutional layers and the classifier layer(s) comprises fully connected layers. The pattern recognition system can be trained utilizing a calculated cross entropy error. The calculated cross entropy error is utilized to update trainable parameters of the pattern recognition system.

    摘要翻译: 提供了一种促进模式识别的系统和方法。 本发明包括具有使用特征提取层和分类器层的卷积神经网络的模式识别系统。 特征提取层包括卷积层,分类层包括完全连接的层。 可以使用计算的交叉熵误差来训练模式识别系统。 计算的交叉熵误差用于更新模式识别系统的可训练参数。