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
    • 14. 发明授权
    • Information processing method, information processing apparatus, and
storage medium
    • 信息处理方法,信息处理装置和存储介质
    • US5982933A
    • 1999-11-09
    • US777249
    • 1996-12-31
    • Hiroto YoshiiTsunekazu AraiEiji Takasu
    • Hiroto YoshiiTsunekazu AraiEiji Takasu
    • G06K9/62G06K9/00
    • G06K9/6282
    • This relates to a classification generation method whereby, in order to efficiently and accurately recognize a pattern having a large number of characteristics, a pattern classification tree is generated, with which a macro structural characteristic of a pattern is appropriately reflected and a competitive relationship between categories is adequately reflected, and to a method for recognizing an input pattern by using the generated classification tree. When an input pattern is formed using strokes, a training stroke is divided into a plurality of segments, and vector quantization is performed for the strokes in the segments. Among the quantized strokes in the segments, adjacent stroke sets are synthesized to repetitively generate upper rank stroke vectors. A stroke vector for which a predetermined entropy function is maximized is selected from the upper rank stroke vectors in a layered stroke vector series, and development is performed extending down into the lower rank stroke vector sets. As a result, a classification tree is prepared.
    • 这涉及一种分类生成方法,为了有效且准确地识别具有大量特征的图案,生成了模式分类树,其中模式的宏观结构特征被适当地反映,并且类别之间的竞争关系 以及通过使用生成的分类树来识别输入模式的方法。 当使用笔画形成输入图案时,将训练笔划分成多个段,并且对段中的笔画执行向量量化。 在片段中的量化笔画中,合成相邻的笔画集以重复地产生上级笔画矢量。 从分层笔画矢量序列中的上位行程矢量中选择预定熵函数最大化的笔画矢量,并且进行向下延伸到下级笔画矢量集的显影。 结果,准备了分类树。
    • 15. 发明授权
    • Pattern recognition apparatus and method utilizing conversion to a common scale by a linear function
    • 利用线性函数将模式识别装置和方法转换成公共尺度
    • US06671403B1
    • 2003-12-30
    • US08715121
    • 1996-09-17
    • Eiji TakasuTsunekazu AraiHiroto Yoshii
    • Eiji TakasuTsunekazu AraiHiroto Yoshii
    • G06K900
    • G06K9/6292
    • Two different recognition processing units respectively perform a plurality of different recognition processing operations for the pattern to be recognized input from a character input unit, and acquire a plurality of recognition candidates and recognition scores. An accuracy calculation unit converts the recognition scores obtained by the two recognition processing units into accuracies based on a scale common to the plurality of different recognition processing operations using parameters stored in a parameter storage unit. A determination unit generates a recognition candidate sequence by determining the order of the recognition candidates obtained by the two recognition processing units on the basis of the accuracies converted by the accuracy calculation unit.
    • 两个不同的识别处理单元分别对从字符输入单元输入的图案进行多个不同的识别处理操作,并且获取多个识别候选和识别分数。 准确度计算单元使用存储在参数存储单元中的参数,将由两个识别处理单元获得的识别分数转换为基于与多个不同识别处理操作共同的标度的精度。 确定单元通过基于由精度计算单元转换的精度来确定由两个识别处理单元获得的识别候选的顺序来生成识别候选序列。
    • 17. 发明授权
    • Character recognition method and apparatus
    • 字符识别方法和装置
    • US6035062A
    • 2000-03-07
    • US703799
    • 1996-08-28
    • Eiji TakasuTsunekazu AraiHiroto Yoshii
    • Eiji TakasuTsunekazu AraiHiroto Yoshii
    • G06K9/62G06K9/68G06K9/00
    • G06K9/6807
    • A character registered in a user's dictionary by a user is outputted prior to other character in a character recognition process. To realize this operation, the character recognition apparatus comprises a user's dictionary (105) and a basic dictionary (103), and a user's unique handwritten character is registered in the user's dictionary (105). In addition, a priority order associated with the handwritten character is simultaneously designated to a priority designation section (109) and stored in a priority storing section (108). When character recognition operation is performed, the basic dictionary (103) and the user's dictionary (105) are utilized; and the recognition result from the basic dictionary and the recognition result from the user's dictionary are adjusted at a result adjusting section (107), by utilizing the priority obtained from the priority storing section (108). Those characters registered in the user's dictionary (105) are outputted prior to other characters in a subsequent recognition operation.
    • 用户在用户字典中登记的字符在字符识别处理之前被输出到其他字符之前。 为了实现该操作,字符识别装置包括用户字典(105)和基本词典(103),并且用户的唯一手写字符被登记在用户的字典(105)中。 此外,与手写字符相关联的优先顺序同时指定给优先级指定部分(109)并存储在优先级存储部分(108)中。 当执行字符识别操作时,利用基本字典(103)和用户字典(105); 并且通过利用从优先级存储部分(108)获得的优先级,在结果调整部分(107)调整来自基本词典的识别结果和用户辞典的识别结果。 在随后的识别操作中,在用户字典(105)中登记的字符在其他字符之前被输出。