Compressed data image object feature extraction, ordering, and delivery
    1.
    发明申请
    Compressed data image object feature extraction, ordering, and delivery 有权
    压缩数据图像对象特征提取,排序和传递

    公开(公告)号:US20070201752A1

    公开(公告)日:2007-08-30

    申请号:US11365442

    申请日:2006-02-28

    IPC分类号: G06K9/36

    CPC分类号: G06K9/00442

    摘要: A method and apparatus is disclosed herein for processing document images. In one embodiment, the method comprises extracting one or more features corresponding to one or more objects from a JPM compressed file, including extracting at least one of the one or more features without decoding, ranking document objects based on a task being performed by an application, and the one or more extracted features, and selecting a set of the document objects based on rank and at least one constraint.

    摘要翻译: 本文公开了用于处理文档图像的方法和装置。 在一个实施例中,该方法包括从JPM压缩文件提取与一个或多个对象相对应的一个或多个特征,包括提取一个或多个特征中的至少一个而不进行解码,基于由应用执行的任务对文档对象进行排序 以及一个或多个提取的特征,以及基于等级和至少一个约束来选择一组文档对象。

    Compressed data image object feature extraction, ordering, and delivery
    2.
    发明授权
    Compressed data image object feature extraction, ordering, and delivery 有权
    压缩数据图像对象特征提取,排序和传递

    公开(公告)号:US08081827B2

    公开(公告)日:2011-12-20

    申请号:US11365442

    申请日:2006-02-28

    IPC分类号: G06K9/36

    CPC分类号: G06K9/00442

    摘要: A method and apparatus is disclosed herein for processing document images. In one embodiment, the method comprises extracting one or more features corresponding to one or more objects from a JPM compressed file, including extracting at least one of the one or more features without decoding, ranking document objects based on a task being performed by an application, and the one or more extracted features, and selecting a set of the document objects based on rank and at least one constraint.

    摘要翻译: 本文公开了用于处理文档图像的方法和装置。 在一个实施例中,该方法包括从JPM压缩文件提取与一个或多个对象相对应的一个或多个特征,包括提取一个或多个特征中的至少一个而不进行解码,基于由应用执行的任务对文档对象进行排序 以及一个或多个提取的特征,以及基于等级和至少一个约束来选择一组文档对象。

    Method and apparatus for risk analysis of published logs
    3.
    发明授权
    Method and apparatus for risk analysis of published logs 有权
    发布日志的风险分析方法和设备

    公开(公告)号:US08255340B2

    公开(公告)日:2012-08-28

    申请号:US12244707

    申请日:2008-10-02

    IPC分类号: G06N5/00

    CPC分类号: G06Q10/10 G06Q10/0635

    摘要: A method and apparatus for analyzing risk associated with published logs are described. In one embodiment, the method comprises accessing a first log published to one or more logs. In one embodiment, the method may also comprise estimating a probability that an entry within the first log will not be verifiable from a second entry selected from one o the one or more logs.

    摘要翻译: 描述了用于分析与已发布日志相关联的风险的方法和装置。 在一个实施例中,该方法包括访问发布到一个或多个日志的第一日志。 在一个实施例中,该方法还可以包括估计第一日志中的条目将不能从从一个或多个日志中的一个中选择的第二条目验证的概率。

    Header-based processing of image compressed using multi-scale transforms
    4.
    发明申请
    Header-based processing of image compressed using multi-scale transforms 有权
    基于标题的处理使用多尺度变换压缩的图像

    公开(公告)号:US20080095452A1

    公开(公告)日:2008-04-24

    申请号:US11787993

    申请日:2007-04-17

    IPC分类号: G06K9/34

    摘要: A method and apparatus is described for segmenting an image, for adaptively scaling an image, and for automatically scaling and cropping an image based on codestream headers data. In one embodiment, a file that can provide a header that contains multi-scale entropy distribution information on blocks of an image is received. For each block, the block is assigned to a scale from a set of scales that maximizes a cost function. The cost function is a product of a total likelihood and a prior. The total likelihood is a product of likelihoods of the blocks. The image is segmented by grouping together blocks that have been assigned equivalent scales. In one embodiment, the file represents an image in JPEG 2000 format.

    摘要翻译: 描述了用于分割图像,自适应地缩放图像以及基于码流头部数据自动缩放和裁剪图像的方法和装置。 在一个实施例中,可以接收可以提供包含图像块上的多尺度熵分布信息的报头的文件。 对于每个块,块被分配给从一组成本函数最大化的一组比例尺。 成本函数是一个总可能性和先前的乘积。 总可能性是块的可能性的乘积。 通过将已经分配了等效尺度的块分组在一起来分割图像。 在一个实施例中,文件表示JPEG 2000格式的图像。

    Header-based processing of images compressed using multi-scale transforms
    5.
    发明申请
    Header-based processing of images compressed using multi-scale transforms 有权
    基于标题的处理使用多尺度变换压缩的图像

    公开(公告)号:US20080044091A1

    公开(公告)日:2008-02-21

    申请号:US11787836

    申请日:2007-04-17

    IPC分类号: G06K9/36

    摘要: A method and apparatus is described for segmenting an image, for adaptively scaling an image, and for automatically scaling and cropping an image based on codestream headers data. In one embodiment, a file that can provide a header that contains multi-scale entropy distribution information on blocks of an image is received. For each block, the block is assigned to a scale from a set of scales that maximizes a cost function. The cost function is a product of a total likelihood and a prior. The total likelihood is a product of likelihoods of the blocks. The image is segmented by grouping together blocks that have been assigned equivalent scales. In one embodiment, the file represents an image in JPEG 2000 format.

    摘要翻译: 描述了用于分割图像,自适应地缩放图像以及基于码流头部数据自动缩放和裁剪图像的方法和装置。 在一个实施例中,可以接收可以提供包含图像块上的多尺度熵分布信息的报头的文件。 对于每个块,块被分配给从一组成本函数最大化的一组比例尺。 成本函数是一个总可能性和先前的乘积。 总可能性是块的可能性的乘积。 通过将已经分配了等效尺度的块分组在一起来分割图像。 在一个实施例中,文件表示JPEG 2000格式的图像。