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
    • 2. 发明授权
    • Apparatus for recognizing input character strings by inference
    • 用于通过推理识别输入字符串的装置
    • US06751605B2
    • 2004-06-15
    • US09789820
    • 2001-02-22
    • Keiko GunjiKoyo KatsuraSoshiro KuzunukiMasaki MiuraToshimi Yokota
    • Keiko GunjiKoyo KatsuraSoshiro KuzunukiMasaki MiuraToshimi Yokota
    • G06F1730
    • G06K9/72G06K2209/01Y10S707/99931Y10S707/99933
    • A character recognition apparatus for inferring the entire character string solely from a user-input handwritten keyword and displaying the inferred result as a candidate character string. The apparatus of the invention comprises: a word string includes a word hierarchy and for recognizing each of the words within the hierarchy; a character transition probability table a4 storing probabilities of transitions from any one character to another, and those pieces of the word identification information which correspond to combinations of characters resulting from the transitions; and an optimization unit for using the character transition probability table in optimizing candidate character strings obtained by a recognition unit. The word dictionary is searched for a word defined by the word identification information which corresponds to the optimized candidate character string, whereby the searched word is retrieved which applies to the hierarchy information and which has yet to be input.
    • 一种字符识别装置,用于仅从用户输入的手写关键词中推断出整个字符串,并将推测的结果显示为候选字符串。本发明的装置包括:字串包括字层级,并用于识别每个字 在层次结构中 存储从任何一个字符到另一个字符的转换概率的字符转换概率表a4,以及对应于由转换产生的字符的组合的那些字识别信息; 以及优化单元,用于在通过识别单元获得的优化候选字符串中使用字符转换概率表。 搜索单词词典由对应于优化的候选字符串的单词识别信息定义的单词,由此检索适用于层级信息并且尚未被输入的搜索词。
    • 3. 发明授权
    • Apparatus for recognizing input character strings by inference
    • 用于通过推理识别输入字符串的装置
    • US6097841A
    • 2000-08-01
    • US859410
    • 1997-05-20
    • Keiko GunjiKoyo KatsuraSoshiro KuzunukiMasaki MiuraToshimi Yokota
    • Keiko GunjiKoyo KatsuraSoshiro KuzunukiMasaki MiuraToshimi Yokota
    • G06K9/72
    • G06K9/72G06K2209/01Y10S707/99931Y10S707/99933
    • A character recognition apparatus for inferring the entire character string solely from a user-input handwritten keyword and displaying the inferred result as a candidate character string. The apparatus of the invention comprises: a word dictionary storing word identification information and hierarchy information for layering a plurality of words into a hierarchy and for recognizing each of the words within the hierarchy; a character transition probability table a4 storing probabilities of transitions from any one character to another, and those pieces of the word identification information which correspond to combinations of characters resulting from the transitions; and an optimization unit for using the character transition probability table in optimizing candidate character strings obtained by a recognition unit. The word dictionary is searched for a word defined by the word identification information which corresponds to the optimized candidate character string, whereby the searched word is retrieved which applies to the hierarchy information and which has yet to be input.
    • 一种字符识别装置,用于仅从用户输入的手写关键字中推断整个字符串,并将推测的结果显示为候选字符串。 本发明的装置包括:存储字识别信息和层级信息的单词字典,用于将多个单词分层为层次结构,并用于识别层次结构内的每个单词; 存储从任何一个字符到另一个字符的转换概率的字符转换概率表a4,以及对应于由转换产生的字符的组合的那些字识别信息; 以及优化单元,用于在通过识别单元获得的优化候选字符串中使用字符转换概率表。 搜索单词词典由对应于优化的候选字符串的单词识别信息定义的单词,由此检索适用于层级信息并且尚未被输入的搜索词。
    • 9. 发明授权
    • Character recognizer
    • 字符识别器
    • US06718060B1
    • 2004-04-06
    • US09509076
    • 2000-06-13
    • Toshimi YokotaSoshiro KuzunukiMasaki MiuraKeiko GunjiKoyo Katsura
    • Toshimi YokotaSoshiro KuzunukiMasaki MiuraKeiko GunjiKoyo Katsura
    • G06K900
    • G06K9/6814G06K9/00409G06K9/00429
    • A character recognizing apparatus capable of recognizing discriminatively characters written continuously, irregularly and/or containing modification is provided which apparatus includes an input unit for allowing a handwritten character to be inputted to thereby output coordinate-points string, a dictionary for storing therein a plurality of character codes and character patterns corresponding to the character codes, respectively, an element decomposition module for decomposing the coordinates string outputted from the input unit into a plurality of elements which constitute the character, and a matching module for determining corresponding distance values for the elements of the character pattern stored in the dictionary and the elements of character pattern of the inputted character for each of the character patterns stored in the dictionary, to thereby correct the distance values determined on the basis of the elements bearing no correspondence.
    • 提供一种字符识别装置,其能够识别识别连续地,不规则地和/或包含修改的字符的字符,该装置包括用于输入手写字符的输入单元,从而输出坐标点串,其中存储多个 分别对应于字符代码的字符代码和字符模式,用于将从输入单元输出的坐标串分解为构成字符的多个元素的元素分解模块,以及用于确定构成该字符的多个元素的匹配模块 存储在字典中的字符模式和存储在字典中的每个字符模式的输入字符的字符模式的元素,从而校正基于不具有对应关系的元素确定的距离值。