公开(公告)号：US5479570A

公开(公告)日：1995-12-26

申请号：US130851

申请日：1993-10-04

申请人： Taro Imagawa ,  Toshiyuki Kouda ,  Yoshihiro Kojima ,  Susumu Maruno ,  Yasuharu Shimeki

发明人： Taro Imagawa ,  Toshiyuki Kouda ,  Yoshihiro Kojima ,  Susumu Maruno ,  Yasuharu Shimeki

IPC分类号： G06K9/68 ,  G06N3/08 ,  G06F15/18

CPC分类号： G06N3/08 ,  G06K9/6807

摘要： A learning and recognition machine has a major classification section for classifying an input pattern into a plurality of category groups and calculating a group belongingness to each category group and a plurality of fine classification sections for calculating a similarity within each category group. The machine causes the plurality of fine classification sections to learn in a coordinated manner by reflecting the group belongingness of the input pattern to update of a weight factor implemented in the fine classification sections, thereby allowing a recognition rate of a pattern situated at the boundary of the category groups to be improved and an effective supplemental learning to be performed.

摘要翻译： 学习识别机具有主要的分类部分，用于将输入模式分类成多个类别组并计算每个类别组的属性，以及用于计算每个类别组内的相似度的多个精细分类部分。 机器使多个精细分类部通过反映输入图案的组属性来更新在精细分类部中实现的权重因子，从而以协调的方式学习，从而允许位于边界处的图案的识别率 要改进的类别组和有效的补充学习。

公开(公告)号：US5987170A

公开(公告)日：1999-11-16

申请号：US965534

申请日：1997-11-06

申请人： Hiroshi Yamamoto ,  Hisao Niwa ,  Yoshihiro Kojima ,  Susumu Maruno ,  Kazuhiro Kayashima ,  Yasuharu Shimeki ,  Toshiyuki Kouda ,  Hidetsugu Maekawa ,  Satoru Ito

发明人： Hiroshi Yamamoto ,  Hisao Niwa ,  Yoshihiro Kojima ,  Susumu Maruno ,  Kazuhiro Kayashima ,  Yasuharu Shimeki ,  Toshiyuki Kouda ,  Hidetsugu Maekawa ,  Satoru Ito

IPC分类号： G06K9/72

CPC分类号： G06K9/726 ,  G06K2209/01

摘要： There is disclosed a character recognition machine adapted to recognize Japanese characters such as kanjis and kanas. The machine comprises a character string storage portion, a character extraction portion, a character recognition portion, and a language processing portion. A character string to be recognized is stored as an image in the storage portion. The character extraction portion comprises a network consisting a plurality of interconnected operators each of which has numerous inputs and outputs. An evaluation function which assumes its minimum value when a character extraction produces the best results is calculated by the operators simultaneously so as to minimize the value of the function. The character recognition portion calculates degrees of similarity of a character pattern to various character categories, the character pattern being applied from the character extraction portion. The language processing portion receives these degrees of similarity and selects a character category which seems to provide the most correct combination of characters in terms of vocabulary and grammar.

摘要翻译： 公开了一种适于识别诸如kanjis和kanas之类的日本字符的字符识别机。 机器包括字符串存储部分，字符提取部分，字符识别部分和语言处理部分。 要识别的字符串作为图像存储在存储部分中。 字符提取部分包括由多个互连操作器组成的网络，每个操作器具有许多输入和输出。 当字符提取产生最佳结果时，假设其最小值的评估函数由运算符同时计算，以便使函数的值最小化。 字符识别部分从字符提取部分计算字符图案与各种字符类别的相似度，字符图案被应用。 语言处理部分接收这些相似度，并且选择似乎在词汇和语法方面提供最正确的字符组合的字符类别。

公开(公告)号：US6041141A

公开(公告)日：2000-03-21

申请号：US513294

申请日：1995-08-10

申请人： Hiroshi Yamamoto ,  Hisao Niwa ,  Yoshihiro Kojima ,  Susumu Maruno ,  Kazuhiro Kayashima ,  Toshiyuki Kouda ,  Hidetsugu Maekawa ,  Satoru Ito ,  Yasuharu Shimeki

发明人： Hiroshi Yamamoto ,  Hisao Niwa ,  Yoshihiro Kojima ,  Susumu Maruno ,  Kazuhiro Kayashima ,  Toshiyuki Kouda ,  Hidetsugu Maekawa ,  Satoru Ito ,  Yasuharu Shimeki

IPC分类号： G06K9/72 ,  G06K9/68

CPC分类号： G06K9/726 ,  G06K2209/01

摘要： There is disclosed a character recognition machine adapted to recognize Japanese characters such as kanjis and kanas. The machine comprises a character string storage portion, a character extraction portion, a character recognition portion, and a language processing portion. A character string to be recognized is stored as an image in the storage portion. The character extraction portion comprises a network consisting a plurality of interconnected operators each of which has numerous inputs and outputs. An evaluation function which assumes its minimum value when a character extraction produces the best results is calculated by the operators simultaneously so as to minimize the value of the function. The character recognition portion calculates degrees of similarity of a character pattern to various character categories, the character pattern being applied from the character extraction portion. The language processing portion receives these degrees of similarity and selects a character category which seems to provide the must correct combination of characters in terms of vocabulary and grammar.

摘要翻译： 公开了一种适于识别诸如kanjis和kanas之类的日本字符的字符识别机。 机器包括字符串存储部分，字符提取部分，字符识别部分和语言处理部分。 要识别的字符串作为图像存储在存储部分中。 字符提取部分包括由多个互连操作器组成的网络，每个操作器具有许多输入和输出。 当字符提取产生最佳结果时，假设其最小值的评估函数由运算符同时计算，以便使函数的值最小化。 字符识别部分从字符提取部分计算字符图案与各种字符类别的相似度，字符图案被应用。 语言处理部分接收这些相似程度，并且选择似乎在词汇和语法方面提供必须正确的字符组合的字符类别。

公开(公告)号：US5802505A

公开(公告)日：1998-09-01

申请号：US577347

申请日：1995-12-22

申请人： Susumu Maruno ,  Sigeo Sakaue ,  Yasuharu Simeki ,  Taro Imagawa ,  Toshiyuki Kouda

发明人： Susumu Maruno ,  Sigeo Sakaue ,  Yasuharu Simeki ,  Taro Imagawa ,  Toshiyuki Kouda

IPC分类号： G11B20/10 ,  G05B13/00 ,  G06F15/18

CPC分类号： G11B20/10009

摘要： A learning type signal recording and reproducing apparatus has a signal detector for detecting signals recorded on recording media, a teaching signal generator for generating reference teaching signals having predetermined waveform signal patterns, and a learning type waveform converter for generating converting rules from signals recorded on the recording medium to original signals corresponding to the recorded signals, by learning the relationship between the detection results by the signal detector of teaching signals recorded on the recording media and reference teaching signals outputted by the teaching signal generator. With this apparatus, signals can be stably reproduced even if the signals contain distortion caused by noise or difference in the recording media.

摘要翻译： 学习型信号记录和再现装置具有用于检测记录在记录介质上的信号的信号检测器，用于产生具有预定波形信号图形的参考教学信号的教学信号发生器，以及学习型波形转换器， 通过学习信号检测器对记录在记录媒体上的教导信号的检测结果与由教学信号发生器输出的参考教学信号之间的关系，将记录介质记录到与记录信号相对应的原始信号。 利用该装置，即使信号包含由噪声引起的失真或记录介质的差异，也能够稳定地再现信号。

公开(公告)号：US5606538A

公开(公告)日：1997-02-25

申请号：US614102

申请日：1996-03-12

申请人： Susumu Maruno ,  Toshiyuki Kouda ,  Taro Imagawa

发明人： Susumu Maruno ,  Toshiyuki Kouda ,  Taro Imagawa

IPC分类号： G11B20/10 ,  H04L25/03 ,  G11B7/00

CPC分类号： H04L25/03165 ,  G11B20/10 ,  G11B20/10009 ,  H04L2025/03464

摘要： The signal recording and reproducing apparatus of this invention includes: a signal detector for detecting a teacher signal and an information signal recorded on a recording medium; a converting section for converting the teacher signal and the information signal detected by the signal detector into a reproduction teacher signal and a reproduction information signal, respectively, based on a predetermined conversion rule; and a teacher signal generator for generating a reference teacher signal, wherein the teacher signal is first detected before the detection of the information signal, and the converting means includes a learning type waveform converting section for automatically establishing the predetermined conversion rule based on the reproduction teacher signal and the reference teacher signal.

摘要翻译： 本发明的信号记录和再现装置包括：信号检测器，用于检测教师信号和记录在记录介质上的信息信号; 转换部分，用于基于预定的转换规则将教师信号和由信号检测器检测到的信息信号分别转换成再现教师信号和再现信息信号; 以及用于产生参考教师信号的教师信号发生器，其中在信息信号的检测之前首先检测教师信号，并且转换装置包括学习型波形转换部分，用于基于再现教师自动建立预定的转换规则 信号和参考教师信号。

公开(公告)号：US5452402A

公开(公告)日：1995-09-19

申请号：US155865

申请日：1993-11-23

申请人： Shiro Sakiyama ,  Masakatsu Maruyama ,  Hiroyuki Nakahira ,  Toshiyuki Kouda ,  Susumu Maruno

发明人： Shiro Sakiyama ,  Masakatsu Maruyama ,  Hiroyuki Nakahira ,  Toshiyuki Kouda ,  Susumu Maruno

IPC分类号： G06F15/18 ,  G06N3/04 ,  G06N3/08 ,  G06N99/00 ,  G06T7/00 ,  G06F15/00

CPC分类号： G06K9/62 ,  G06N3/08 ,  G06N3/082

摘要： In a multi-layered neural network circuit provided with an input layer having input vectors, an intermediate layer having networks in tree-like structure whose outputs are necessarily determined by the values of the input vectors and whose number corresponds to the number of the input vectors of the input layer, and an output layer having plural output units for integrating all outputs of the intermediate layer, provided are learning-time memories for memorizing the numbers of times at learning in paths between the intermediate layer and the respective output units, threshold processing circuits for threshold-processing the outputs of the leaning-time memories, and connection control circuits to be controlled by the outputs of the threshold processing circuits for controlling connection of paths between the intermediate layer and the output units. The outputs of the intermediate layer connected by the connection control circuits are summed in each output unit. Thus, the neural network circuit for recognizing an image or the like can execute recognition and learning of data to be recognized at high speed with small circuit size, and the recognition accuracy for unlearned data is high.

摘要翻译： 在设置有具有输入向量的输入层的多层神经网络电路中，具有树状结构的网络的中间层，其输出必须由输入向量的值决定，其数量对应于输入向量的数量 以及输出层，具有用于积分中间层的所有输出的多个输出单元，所述输出层是用于存储中间层和各个输出单元之间的路径中学习次数的学习时间存储器，阈值处理 用于对倾斜时间存储器的输出进行阈值处理的电路和由用于控制中间层和输出单元之间的路径连接的阈值处理电路的输出来控制的连接控制电路。 由连接控制电路连接的中间层的输出在每个输出单元中相加。 因此，用于识别图像等的神经网络电路可以以较小的电路尺寸执行高速识别的数据的识别和学习，并且未被读取的数据的识别精度高。

公开(公告)号：US5621862A

公开(公告)日：1997-04-15

申请号：US281683

申请日：1994-07-28

申请人： Hiroyuki Nakahira ,  Masakatsu Maruyama ,  Shiro Sakiyama ,  Susumu Maruno ,  Toshiyuki Kouda ,  Masaru Fukuda

发明人： Hiroyuki Nakahira ,  Masakatsu Maruyama ,  Shiro Sakiyama ,  Susumu Maruno ,  Toshiyuki Kouda ,  Masaru Fukuda

IPC分类号： G06K9/66 ,  G06N3/08 ,  G06N3/10 ,  G06F15/18

CPC分类号： G06K9/00986 ,  G06K9/6267 ,  G06N3/082 ,  G06N3/10

摘要： In an information processing apparatus for implementing a neural network, if an input vector is inputted to a calculating unit, a neuron which responds to the input vector is retrieved in accordance with network interconnection information stored in a first storage unit and the neuron number indicating the retrieved neuron is written in a first register. The calculating unit reads out the internal information of the neuron stored in a second storage unit by using the neuron number, writes it in a second register, and calculates the sum of products of the outputs of the neurons and the connection loads of synapses connected to the neurons. By repeating the sequence of operations by the number of times corresponding to the total number of input vectors, a recognition process is executed. The neural network can easily be expanded by rewriting the contents of the first and second storage units.

摘要翻译： 在用于实现神经网络的信息处理装置中，如果将输入向量输入到计算单元，则根据存储在第一存储单元中的网络互连信息来检索响应于输入向量的神经元，并且指示 检索到的神经元被写入第一个寄存器。 计算单元通过使用神经元号读取存储在第二存储单元中的神经元的内部信息，将其写入第二寄存器，并且计算神经元的输出和连接到的突触的连接负载的乘积之和 神经元。 通过将操作序列重复与输入向量的总数相对应的次数，执行识别处理。 可以通过重写第一和第二存储单元的内容来容易地扩展神经网络。

公开(公告)号：US06636631B2

公开(公告)日：2003-10-21

申请号：US09325546

申请日：1999-06-04

申请人： Keiichi Miyazaki ,  Masato Minami ,  Toshiyuki Kouda

发明人： Keiichi Miyazaki ,  Masato Minami ,  Toshiyuki Kouda

IPC分类号： G06K900

CPC分类号： G06K9/00449 ,  G06K9/48 ,  G06K9/50 ,  G06K2209/01

摘要： A method of recognizing characters of a document including ruled lines. After separating the characters from the ruled lines, a bounding box and a corresponding character pattern are extracted for each character (hereinafter, “the character”). Contour information and ground (white pel area) information are extracted as fundamental features from the character pattern. Various statistical features are extracted based on the fundamental features. Various structural features are extracted based on the fundamental features and the character pattern. On the basis of the extracted statistical features, some candidates for the character and corresponding degrees of similarity are found to provide at least such one of the candidates as has largest degree(s) of similarity and degree(s) of similarity associated with the provided candidate(s). A final candidate for the character pattern is output based on the provided candidate(s), the provided degree(s) of similarity, the structural features and the bounding box.

摘要翻译： 一种识别包括格线的文档的字符的方法。 在将字符与格线分开之后，为每个字符（以下称为“字符”）提取边框和相应的字符图案。 从字符模式中提取轮廓信息和地面（白色区域）信息作为基本特征。 根据基本特征提取各种统计特征。 根据基本特征和字符模式提取各种结构特征。 在提取的统计特征的基础上，发现一些候选人的字符和相应的相似度被提供至少具有与所提供的相似性相似度和相似程度相关程度最大的候选者 候选人）。 基于提供的候选者，提供的相似度，结构特征和边界框输出字符模式的最终候选。