专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US5479570A Learning and recognition machine 失效
标题翻译：学习识别机
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。

2. 发明授权

US5329594A Recognizing and judging apparatus 失效
标题翻译：识别和判断装置
公开(公告)号：US5329594A
公开(公告)日：1994-07-12
申请号：US845248
申请日：1992-03-03
申请人： Susumu Maruno , Shigeo Sakaue , Toshiyuki Kohda , Yoshihiro Kojima
发明人： Susumu Maruno , Shigeo Sakaue , Toshiyuki Kohda , Yoshihiro Kojima
IPC分类号： G06K9/66 , G06N3/04 , G06K9/62
CPC分类号： G06N3/04 , G06K9/66
摘要： A recognizing and judging apparatus has a network organized in a multilayered hierarchical manner and a plurality of branched tree structures corresponding to the number of inputted data. The branched tree structures are organized by a plurality of recognition units, each of which includes a signal input section and a quantizer for performing a quantization according to a signal inputted from the signal input section. Each of the recognition units further includes a path input section having at least one path input terminal, a path output section having at least one path output terminal, and a path selecting section operatively coupled with both the path input section and the path output section for performing a selection of paths according to an output of the quantizer.
摘要翻译：识别和判断装置具有以多层次分层方式组织的网络和对应于输入数据数量的多个分支树结构。分支树结构由多个识别单元组织，每个识别单元包括信号输入部分和用于根据从信号输入部分输入的信号进行量化的量化器。每个识别单元还包括具有至少一个路径输入端的路径输入部分，具有至少一个路径输出端的路径输出部分和与路径输入部分和路径输出部分可操作地耦合的路径选择部分，用于根据量化器的输出执行路径选择。

3. 发明授权

US5296920A Color gradation correction method and apparatus 失效
标题翻译：彩色灰度校正方法和装置
公开(公告)号：US5296920A
公开(公告)日：1994-03-22
申请号：US945626
申请日：1992-09-16
申请人： Shigeo Sakaue , Susumu Maruno , Haruo Yamashita , Yasuki Matsumoto , Hideshi Ishihara
发明人： Shigeo Sakaue , Susumu Maruno , Haruo Yamashita , Yasuki Matsumoto , Hideshi Ishihara
IPC分类号： B41J2/52 , G06T5/00 , G09G5/00 , G09G5/02 , H04N1/00 , H04N1/60 , H04N9/69 , H04N9/77
CPC分类号： H04N1/00795 , H04N1/6027 , H04N9/69
摘要： A gradation correction apparatus for processing R, G, and B input signals includes a luminance signal conversion device for obtaining the original luminance signal, which is before gamma conversion, from the input signals, a luminance gamma conversion device for gamma converting the original luminance signal to the desired gradation characteristics to obtain a gamma converted luminance signal, a correction coefficient calculation means for obtaining a ratio of the gamma converted luminance signal to the original luminance signal, a first RGB operation means for multiplying the ratio by each of the R, G, and B input signals for obtaining primary gradation-corrected R, G, and B signals; a color difference signal operation means for producing a difference between each of the R, G, and B input signals and the original luminance signal; a second RGB operation means for adding the gamma converted luminance signal to each of the difference for obtaining secondary gradation-corrected R, G, and B signals; and an RGB determination means for obtaining final gradation-corrected R, G, B signals based on the primary and secondary gradation-corrected R, G, and B signals.
摘要翻译：用于处理R，G和B输入信号的灰度校正装置包括用于从输入信号获得伽马变换之前的原始亮度信号的亮度信号转换装置，用于伽马转换原始亮度信号的亮度伽玛转换装置获得所需的灰度特性以获得伽马转换的亮度信号;校正系数计算装置，用于获得伽马转换的亮度信号与原始亮度信号的比率;第一RGB操作装置，用于将该比率乘以每个R，G 和B输入信号，用于获得初级灰度校正的R，G和B信号; 用于产生R，G和B每个输入信号与原始亮度信号之间的差的色差信号操作装置; 第二RGB操作装置，用于将伽马转换的亮度信号加到每个差值上，以获得二次灰度校正的R，G和B信号; 以及RGB确定装置，用于基于一次和二次灰度校正的R，G和B信号获得最终灰度校正的R，G，B信号。

4. 发明授权

US4401998A Magnetic fluid recording apparatus 失效
标题翻译：磁性流体记录装置
公开(公告)号：US4401998A
公开(公告)日：1983-08-30
申请号：US330607
申请日：1981-12-14
申请人： Masaharu Ushihara , Michinori Nagahiro , Humio Yamazaki , Masami Nakagawa , Noboru Miyaji , Susumu Maruno
发明人： Masaharu Ushihara , Michinori Nagahiro , Humio Yamazaki , Masami Nakagawa , Noboru Miyaji , Susumu Maruno
IPC分类号： B41J2/06 , B41J2/065 , G01D15/16
CPC分类号： B41J2/065
摘要： A plurality of magnetic styli are arranged in a row for effecting a line recording. A magnetic styli are magnetized by a magnet held in contact with these styli so that a magnetic fluid attaching to the styli is protruded from each stylus to form continuous wave-like protrusions along the row of the styli. The magnetic fluid protruded from the styli is to fly or migrate as a high voltage is applied selectively between the styli and a control electrode which opposes to the styli across the recording paper, due to a Coulomb force acting on the ends of the protrusions. In consequence, a recording is made by the magnetic fluid serving as an ink on the recording paper in accordance with a recording signal. A predetermined head or height differential is preserved between the magnet and an ink tank. The magnet and the ink tank are connected to each other by means of a pipe filled with the magnetic fluid. A slight gap is formed in the connection between the pipe and the magnet. This gap, however, is completely covered and closed by the magnetic fluid attaching to the magnet so that the ambient air is prevented from coming into the pipe. A vacuum is generated in the pipe due to the aforementioned height differential to control the amount of the magnetic fluid supplied to the magnet. As the magnetic fluid is consumed progressively at the ends of the protrusions, the magnetic fluid is supplied to the protrusions from the ink tank through the pipe and the gap. In consequence, various troubles such as printing failure due to magnetic thickening of the magnetic fluid which inevitably takes place in the conventional apparatus incorporating an elongated magnet type ink supplying device, is completely eliminated to ensure a stable printing of a high quality.
摘要翻译：多个磁针被排列成一行以进行线记录。一个磁性测针由与这些测针保持接触的磁体磁化，使得附着在测针上的磁性流体从每个触针突出，以沿着测针的一行形成连续的波浪形突起。由于作用在突起的端部上的库仑力，由于从触针突出的磁性流体是飞行的或迁移的，因为高电压被选择性地施加在触针和与记录纸对准的测针的控制电极之间。因此，根据记录信号，通过用作墨水的磁性流体在记录纸上进行记录。在磁体和墨水罐之间保留预定的头部或高度差。磁体和墨水罐通过填充有磁性流体的管道相互连接。在管和磁体之间的连接中形成微小的间隙。然而，该间隙被附着在磁体上的磁性流体完全覆盖和闭合，从而防止环境空气进入管道。由于上述高度差，在管中产生真空，以控制供给到磁体的磁性流体的量。当磁性流体在突起的端部逐渐消耗时，磁性流体通过管道和间隙从墨水罐供应到突起。结果，完全消除了在包含细长磁体型供墨装置的传统装置中不可避免地发生的磁性流体的磁性增厚引起的打印故障等各种问题，以确保高质量的稳定印刷。

5. 发明授权

US06993517B2 Information retrieval system for documents 失效
标题翻译：信息检索系统文件
公开(公告)号：US06993517B2
公开(公告)日：2006-01-31
申请号：US09859609
申请日：2001-05-17
申请人： Eiichi Naito , Shoichi Araki , Hiroshi Kutsumi , Jun Ozawa , Susumu Maruno
发明人： Eiichi Naito , Shoichi Araki , Hiroshi Kutsumi , Jun Ozawa , Susumu Maruno
IPC分类号： G06F17/30
CPC分类号： G06F17/3071 , G06F17/30634 , G06F17/3069 , Y10S707/99933 , Y10S707/99943
摘要： Questions and answers associated with each other are stored in a document storage section. A clustering section classifies the answers in the document storage section into clusters based on feature vectors of the answers. When a natural language question is input by the user, a database retrieval/updating section retrieves a question similar to the input question, and presents answers associated with the retrieved question together for each cluster to the user or an expert. In addition, the database retrieval/updating section automatically updates the document storage section based on an answer selected as most appropriate by the user or the expert if selected, or based on an answer newly input by the expert if no appropriate answer is available. The natural language answer input by the expert is presented to the user as it is.
摘要翻译：彼此相关的问题和答案存储在文档存储部分中。聚类部分将文档存储部分中的答案根据答案的特征向量进行分类。当用户输入自然语言问题时，数据库检索/更新部分检索类似于输入问题的问题，并且将与检索到的问题相关联的答案一起呈现给用户或专家的每个聚类。此外，数据库检索/更新部分基于如果选择了用户或专家最适合的答案，或者如果没有适当的答案可用，则基于由专家新输入的答案，自动更新文档存储部分。由专家输入的自然语言答案按原样呈现给用户。

6. 发明授权

US6041141A Character recognition machine utilizing language processing 失效
标题翻译：字符识别机利用语言处理
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。

7. 发明授权

US6004015A Optimization adjusting method and optimization adjusting apparatus 失效
公开(公告)号：US6004015A
公开(公告)日：1999-12-21
申请号：US561708
申请日：1995-11-22
申请人： Tatsumi Watanabe , Hideyuki Takagi , Kazuaki Obara , Susumu Maruno
发明人： Tatsumi Watanabe , Hideyuki Takagi , Kazuaki Obara , Susumu Maruno
IPC分类号： G06N3/12 , G06Q10/00 , H04R25/00 , G06F15/18
CPC分类号： G06F17/505 , G06N3/126 , G06Q10/04 , H04R25/70 , G06F2217/08
摘要： At the start of a process, an information presenting section presents information expressed by a solution vector, while an auxiliary information presenting section presents information for facilitating comparative evaluation of multiple pieces of information being presented simultaneously. Based on these pieces of information, the user evaluates each solution vector. A model estimation executing section generates an evaluation model for an adjustment process from a user evaluation history, and thereafter, a model evaluation calculating section performs evaluation using the evaluation model. A fitness calculating section calculates fitness from the evaluation made by the user or by the model, and in accordance with the thus calculated fitness, a recombination operation section performs an arithmetical recombination operation. The above process is iteratively performed to carry out optimum adjustment of solution vectors.

8. 发明授权

US5754709A Method and apparatus for gradation correction and image edge extraction 失效
标题翻译：灰度校正和图像边缘提取的方法和装置
公开(公告)号：US5754709A
公开(公告)日：1998-05-19
申请号：US508037
申请日：1995-07-27
申请人： Michiyo Moriya , Hiroshi Yamamoto , Taro Imagawa , Susumu Maruno , Toshiyuki Koda
发明人： Michiyo Moriya , Hiroshi Yamamoto , Taro Imagawa , Susumu Maruno , Toshiyuki Koda
IPC分类号： G06T3/00 , G06T5/00 , G06T7/60 , G06K9/40 , G06K9/34 , G06K9/48 , G06K9/52
CPC分类号： G06T7/0083 , G06T2207/10016 , G06T2207/20021
摘要： The present invention relates to an image processing apparatus in which gradation correction on each partial region is performed between an image input means and an edge extracting means so that an edge of a region within an image is accurately extracted. An image dividing means 2, which had already learned a relationship between the condition of an image and the necessity of image division so as to judge the condition of the image based on learning results and divide the image appropriately, divides an input image from an image input means 1 into a plurality of image blocks. An image correction information extracting means 3 calculates correction information on each image block. A gradation correction means 4, which had already learned a relationship between correction information and non-linear correction curves to judge correction information based on learning results and perform gradation correction on a target image block using a selected curve, performs gradation correction and enhances an edge which is to be extracted. An image synthesizing means 5 recombines the respective corrected image blocks. An edge extracting means 6 extracts an edge from a synthesized image. An image output means 7 outputs an edge image.
摘要翻译：本发明涉及一种图像处理装置，其中在图像输入装置和边缘提取装置之间执行每个部分区域的灰度校正，使得图像内的区域的边缘被精确地提取。已经学习了图像的状态与图像分割的必要性之间的关系的图像分割装置2，以便基于学习结果来判断图像的状况并适当地分割图像，从图像中分割输入图像输入装置1形成多个图像块。图像校正信息提取装置3计算每个图像块的校正信息。已经学习了校正信息和非线性校正曲线之间的关系的灰度校正装置4，以基于学习结果来判断校正信息，并且使用所选曲线对目标图像块执行灰度校正，执行灰度校正并增强边缘这将被提取。图像合成装置5将各个校正图像块复合。边缘提取装置6从合成图像中提取边缘。图像输出装置7输出边缘图像。

9. 发明授权

US5636327A Neural network circuit 失效
标题翻译：神经网络电路
公开(公告)号：US5636327A
公开(公告)日：1997-06-03
申请号：US409949
申请日：1995-03-23
申请人： Hiroyuki Nakahira , Shiro Sakiyama , Masakatsu Maruyama , Susumu Maruno
发明人： Hiroyuki Nakahira , Shiro Sakiyama , Masakatsu Maruyama , Susumu Maruno
IPC分类号： G06N3/063 , G06F15/18
CPC分类号： G06K9/4628 , G06K9/00986 , G06N3/063
摘要： In a multilayered neural network for recognizing and processing characteristic data of images and the like by carrying out network arithmetical operations, characteristic data memories store the characteristic data of the layers. Coefficient memories store respective coupling coefficients of the layers other than the last layer. A weight memory stores weights of neurons of the last layer. Address converters carry out arithmetical operations to find out addresses of nets of the network whose coupling coefficients are significant. A table memory outputs a total coupling coefficient obtained by inter-multiplying the significant coupling coefficients read out from the coefficient memories of the layers. A cumulative operation unit performs cumulative additions of the product of the total coupling coefficient times the weight of the weight memory. Arithmetical operations are carried out only on particular nets with a significant coupling coefficient value. The speed of operation and recognition can be improved.
摘要翻译：在通过进行网络算术运算来识别和处理图像等的特征数据的多层神经网络中，特征数据存储器存储层的特征数据。系数存储器存储不同于最后层的层的相应耦合系数。体重记忆存储最后层的神经元的权重。地址转换器进行算术运算，找出耦合系数很大的网络网络地址。表存储器输出通过相互乘以从层的系数存储器读出的有效耦合系数而获得的总耦合系数。累积操作单元执行总耦合系数乘以权重存储器的权重的乘积的累积加法。仅对具有显着耦合系数值的特定网络进行算术运算。可以提高运行和识别的速度。

10. 发明授权

US5621862A Information processing apparatus for implementing neural network 失效
标题翻译：用于实现神经网络的信息处理设备
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。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式