会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 51. 发明授权
    • Matching CCITT compressed document images
    • 匹配CCITT压缩文档图像
    • US06546136B1
    • 2003-04-08
    • US09604783
    • 2000-06-26
    • Jonathan J. Hull
    • Jonathan J. Hull
    • G06K962
    • G06K9/00442
    • A fast, memory efficient, and accurate document image matching system is disclosed. Document image matching is based on identifying anchor points of characters in the document. The document matching process includes a feature extraction step where anchor points, e.g., points representing approximate locations of characters, are identified as features for matching. In a particularly efficient implementation, the anchor points are “pass codes” in a two dimensionally encoded representation of a document image.
    • 公开了一种快速,记忆效率高,准确的文件图像匹配系统。 文档图像匹配基于识别文档中的字符的锚点。 文档匹配过程包括特征提取步骤,其中锚点(例如,表示字符的大致位置的点)被识别为用于匹配的特征。 在特别有效的实现中,锚点是文档图像的二维编码表示中的“密码”。
    • 52. 发明授权
    • Search and retrieval using document decomposition
    • 使用文档分解进行搜索和检索
    • US06397213B1
    • 2002-05-28
    • US09311200
    • 1999-05-12
    • John F. CullenJonathan J. Hull
    • John F. CullenJonathan J. Hull
    • G06F1730
    • G06K9/00483G06F17/30017G06F17/30253G06K9/00463Y10S707/99935
    • Document query and search techniques in which documents to be searched are “decomposed” into “zones,” with each zone representing a grouping of text or graphical image or a combination thereof. The zones are defined within, and associated with a document page. One or more zones in the documents are selected for annotation with text (e.g., keywords), image features, or a combination of both. Document query and search are based on a combination of text annotations and image features. In one implementation for operating a document retrieval system, an unindexed (also referred to as a “query” or “search key”) document is captured into electronic form and decomposed into a number of zones. The zones can be segmented into text zones and image zones. Descriptors are formed for at least one of the zones. The descriptors can include text annotations for text zones, and text annotations and image features for image zones. Documents in a document database are searched, based on the formed descriptors for the unindexed document and the descriptors for the documents in the database. At least one document in the database is identifying as matching the unindexed document and reported as such.
    • 将要搜索的文档“分解”成“区域”的文档查询和搜索技术,每个区域表示文本或图形图像的分组或其组合。 区域被定义在文档页面内并与文档页面相关联。 选择文档中的一个或多个区域用于具有文本(例如,关键字),图像特征或两者的组合的注释。 文档查询和搜索基于文本注释和图像特征的组合。 在用于操作文档检索系统的一个实现中,未索引(也称为“查询”或“搜索关键字”)文档被捕获为电子形式并且被分解成多个区域。 区域可以分割成文本区域和图像区域。 为至少一个区域形成描述符。 描述符可以包括文本区域的文本注释,以及图像区域的文本注释和图像特征。 基于形成的无索引文档的描述符和数据库中文档的描述符,搜索文档数据库中的文档。 数据库中至少有一个文档被识别为与无索引文档匹配并按原样报告。
    • 55. 发明授权
    • Relaxation word recognizer
    • 放松字识别器
    • US5617488A
    • 1997-04-01
    • US381767
    • 1995-02-01
    • Tao HongJonathan J. Hull
    • Tao HongJonathan J. Hull
    • G06K9/72G06F15/02G06K9/62
    • G06K9/726G06K2209/01
    • A word recognizer system 10 has a probabilistic relaxation process that improves the performance of an image text recognition technique by propagating the influence of word collocation statistics. Word collocation refers to the likelihood that two words co-occur within a fixed distance of one another. The word recognizer 10 receives groups of visually similar decisions (called neighborhoods) for words in a running text. The position of decisions within the neighborhoods are modified based on how often they co-occur with decisions in the neighborhoods of other nearby words. This process is iterated a number of times effectively propagating the influence of the collocation statistics across an input text.
    • 字识别器系统10具有通过传播单词搭配统计的影响来改善图像文本识别技术的性能的概率松弛处理。 词拼合是指两个词在彼此的固定距离内共同出现的可能性。 单词识别器10接收用于正在运行的文本中的词的视觉上类似的决定(称为邻域)的组。 根据与其他附近单词的邻域中的决定共同出现的频率来修改社区内的决策的位置。 这个过程被迭代了很多次,有效地传播了跨输入文本的并置统计的影响。
    • 58. 发明授权
    • Database for mixed media document system
    • 混合媒体文件系统数据库
    • US09405751B2
    • 2016-08-02
    • US11461164
    • 2006-07-31
    • Jonathan J. HullDar-Shyang LeeKurt W. Piersol
    • Jonathan J. HullDar-Shyang LeeKurt W. Piersol
    • G06F17/30
    • G06F17/3002G06F17/30047
    • A Mixed Media Reality (MMR) system and associated techniques are disclosed. The MMR system provides mechanisms for forming a mixed media document that includes media of at least two types (e.g., printed paper as a first medium and digital content and/or web link as a second medium). In one particular embodiment, the MMR system includes a content-based retrieval database configured with an index table to represent two-dimensional geometric relationships between objects extracted from a printed document in a way that allows look-up using a text-based index. A ranked set of document, page and location hypotheses can be computed given data from the index table. The techniques effectively transform features detected in an image patch into textual terms (or other searchable features) that represent both the features themselves and the geometric relationship between them. A storage facility can be used to store additional characteristics about each document image patch.
    • 公开了混合媒体现实(MMR)系统及其相关技术。 MMR系统提供用于形成包括至少两种类型的媒体(例如,作为第一媒体的打印纸和作为第二媒体的数字内容和/或web链接)的混合媒体文档的机制。 在一个具体实施例中,MMR系统包括配置有索引表的基于内容的检索数据库,以表示以允许使用基于文本的索引进行查找的方式从打印文档提取的对象之间的二维几何关系。 可以根据索引表中的数据计算一组排序的文档,页面和位置假设。 这些技术有效地将图像补丁中检测到的特征转换成代表特征本身和它们之间的几何关系的文本术语(或其他可搜索特征)。 可以使用存储设备来存储关于每个文档图像补丁的附加特征。