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. 发明专利

JP2010277446A Apparatus and method for processing barcode 有权
标题翻译：装置和方法来处理条形码
公开(公告)号：JP2010277446A
公开(公告)日：2010-12-09
申请号：JP2009131126
申请日：2009-05-29
申请人： Toshiba Corp , 株式会社東芝
发明人： MAEDA MASAYA , IRIE BUNPEI , NATORI NAOKI , HAMAMURA TOMOYUKI
IPC分类号： G06K7/015 , G06K7/00 , G06K7/10
CPC分类号： G06K7/14 , B07C3/14 , G06K7/10861
摘要： PROBLEM TO BE SOLVED: To provide a barcode processing apparatus superior in recognition accuracy of a barcode in a slant state. SOLUTION: The barcode processing apparatus includes: a reading unit configured to read an image of a barcode configured by a plurality of bars laid out at predetermined intervals, each of which is formed by a plurality of ink dots; and a barcode recognition unit configured to filter the read image using a mask having a width smaller than the predetermined interval and larger than a width of one bar and corresponding to a length of one bar, so as to extract a group of a plurality of ink dots, to couple the plurality of ink dots in the extracted group, to detect one bar based on the coupling results, and to recognize a barcode configured by a plurality of detected bars. COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：提供一种在倾斜状态下条形码识别精度优异的条形码处理装置。条形码处理装置包括：读取单元，被配置为读取由以多个墨点形成的以预定间隔布置的多个条形码构成的条形码图像; 以及条形码识别单元，被配置为使用具有小于预定间隔的宽度并且大于一个条的宽度并且对应于一个条的长度的掩模来对所读取的图像进行过滤，从而提取一组多个墨点，以便将所提取的组中的多个墨点耦合，以基于耦合结果来检测一个条，并识别由多个检测到的条组成的条形码。版权所有（C）2011，JPO＆INPIT

2. 发明专利

JP2010072931A License plate reader 有权
标题翻译：许可证读卡器
公开(公告)号：JP2010072931A
公开(公告)日：2010-04-02
申请号：JP2008239453
申请日：2008-09-18
申请人： Toshiba Corp , 株式会社東芝
发明人： AOKI YASUHIRO , KONO YUKA , NATORI NAOKI , IRIE BUNPEI
IPC分类号： G08G1/04 , G08G1/015 , G08G1/017
摘要： PROBLEM TO BE SOLVED: To provide a license plate reader which can select and read one license plate candidate assumed as a reading object, even if a plurality of license plate candidates exist in an input image of a vehicle.
SOLUTION: When reading a license plate from the input image of the vehicle, and when a plurality of the license plate candidates exist, the license plate reader selects a license plate candidate of a car type defined beforehand out of a plurality of license plate candidates as a reading object, performs reading processing to this selected license plate candidate, and when a single license plate candidate is extracted, performs the reading processing to the license plate candidate.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：即使在车辆的输入图像中存在多个车牌候选，也可以提供一种能够选择和读取被认为是读取对象的一个车牌候选者的牌照读取器。解决方案：当从车辆的输入图像读取车牌时，并且当存在多个牌照候选者时，牌照阅读器从多个许可证中选择预先定义的轿厢类型的车牌候选板候选人作为读取对象，对所选择的车牌候选者执行读取处理，并且当提取单个牌照候选者时，对车牌候选者执行读取处理。版权所有（C）2010，JPO＆INPIT

3. 发明专利

JP2005040786A Classification device and method for address information identification 审中-公开
标题翻译：用于寻址信息识别的分类设备和方法
公开(公告)号：JP2005040786A
公开(公告)日：2005-02-17
申请号：JP2004185430
申请日：2004-06-23
申请人： Toshiba Corp , 株式会社東芝
发明人： AOKI YASUHIRO , IRIE BUNPEI , AKAGI TAKUMA , HAMAMURA TOMOYUKI , HORIUCHI HIDEO , NATORI NAOKI , NAKAO AKIHIKO
IPC分类号： B07C3/14
摘要： PROBLEM TO BE SOLVED: To efficiently identify address information of a delivery such as mail.
SOLUTION: An international delivery identification section 60A judges whether the mail is for abroad or not, based on each collation result by every collation section comprising a sticker-carried information collation section 51, an address format collation section 52, an address word collation section 53, a delivery zone code form collation section 54, and a country name identification word collation section 55 (or, by part of the collation sections). When the mail is judged to be for abroad by the international delivery identification section 60A, a country name identification section 60B identifies the name of the country to which the mail is addressed, based on each collation result by every collation section comprising the sticker-carried information collation section 51, the address format collation section 52, the address word collation section 53, the delivery zone code form collation section 54, and the country name identification word collation section 55 (or, by part of the collation sections).
COPYRIGHT: (C)2005,JPO&NCIPI
摘要翻译：要解决的问题：有效地识别诸如邮件的传递的地址信息。
解决方案：国际寄送识别部分60A基于每个对照部分的每个对照结果判断邮件是否在国外，包括贴纸信息对照部分51，地址格式对照部分52，地址字输出区域代码形式对照部分54，以及国家名称识别单词对照部分55（或通过对照部分的一部分）。国际名称识别部分60B在由国际传送识别部分60A判断为国外的邮件时，基于每个对照部分的每个核对结果，识别邮件被寻址的国家的名称，信息对照部分51，地址格式对照部分52，地址字对照部分53，传送区域编码形式对照部分54和国家名称识别字对照部分55（或通过部分对照部分）。版权所有（C）2005，JPO＆NCIPI

4. 发明专利

JP2014063347A Character reader and paper sheet processing device 有权
标题翻译：字符读取器和纸张处理装置
公开(公告)号：JP2014063347A
公开(公告)日：2014-04-10
申请号：JP2012207977
申请日：2012-09-21
申请人： Toshiba Corp , 株式会社東芝
发明人： HASEBE MITSUTAKE , NATORI NAOKI
IPC分类号： G06K9/34 , G06K9/20 , G07D7/12
摘要： PROBLEM TO BE SOLVED: To provide a character reader capable of reading characters on a paper sheet with higher accuracy, and a paper sheet processing device.SOLUTION: The character reader relating to an embodiment includes an image acquiring part for acquiring an image of a conveyed paper sheet, a character area identification part for identifying a character area on the image of the paper sheet, a memory for storing a reference feature in which a color feature of a character pixel is previously subjected to vector quantization, a character pixel extraction part for extracting a character pixel in the character area by a scale corresponding to a distance between each pixel in the character area and the reference feature, and a character recognition part for recognizing characters in the character area on the basis of the extracted character pixel in the character area and a preset standard pattern in each character.
摘要翻译：要解决的问题：提供一种能够以更高精度读取纸张上的字符的字符读取器和纸张处理装置。解决方案：与实施例有关的字符读取器包括图像获取部分，用于获取传送的图像的图像纸张，用于识别纸张图像上的字符区域的字符区域识别部分，用于存储其中字符像素的颜色特征预先经过矢量量化的参考特征的存储器，用于以与所述字符区域中的每个像素之间的距离相对应的比例与所述参考特征提取所述字符区域中的字符像素;以及字符识别部，用于基于所提取的字符中的字符像素识别所述字符区域中的字符区域和每个字符预设的标准模式。

5. 发明专利

JP2012079066A Conveyance paper sheet contamination degree determination device and paper sheet processing device 有权
标题翻译：输送纸张污染度测定装置和纸张处理装置
公开(公告)号：JP2012079066A
公开(公告)日：2012-04-19
申请号：JP2010223194
申请日：2010-09-30
申请人： Toshiba Corp , 株式会社東芝
发明人： HASEBE KOI , NATORI NAOKI
IPC分类号： G07D7/12 , G07D3/00 , G07D7/04 , G07D7/20 , G07D9/00
摘要： PROBLEM TO BE SOLVED: To provide a conveyance paper sheet contamination degree determination device capable of determining contamination degree with high accuracy and paper sheet processing device.SOLUTION: The conveyance paper sheet contamination degree determination device includes a conveyance path for conveying paper sheet, reading means provided midway through the conveyance path for reading reflected light from conveyed paper sheets, difference calculation means for obtaining a difference between an output by the reading means when there is no paper sheet and an output by the reading means when there is a paper sheet, appearance extraction means for extracting an appearance of the paper sheet based on the output of the difference calculation means, margin area setting means for setting a margin area of the paper sheet as a determination area from the appearance of the paper sheet extracted by the appearance extraction means, and contamination degree determination means for determining a contamination degree on the margin area of the paper sheet based on the output of the reading means corresponding to the margin area set by the margin area setting means.
摘要翻译：要解决的问题：提供能够以高精度确定污染程度的纸张输送纸张污染度确定装置和纸张处理装置。
解决方案：输送纸张污染度确定装置包括用于传送纸张的输送路径，设置在输送路径的中途的读取装置，用于读取来自输送纸张的反射光;差分计算装置，用于获得输出纸张的输出当存在纸张时，当没有纸张和读取装置的输出时，读取装置是根据差分计算装置的输出提取纸张的外观的外观提取装置，用于设置纸张的边缘区域设置装置作为从外观提取装置提取的纸张的外观的确定区域的纸张的边缘区域;以及污染程度确定装置，用于基于读取的输出来确定纸张的边缘区域的污染程度对应于由边缘区域设置装置设置的边缘区域的装置。版权所有（C）2012，JPO＆INPIT

6. 发明专利

JP2011028512A Method for creating dictionary for fitness determination of paper sheet, paper sheet processing apparatus, and paper sheet processing method 审中-公开
标题翻译：用于创建纸张适合性确定的纸张的方法，纸张处理装置和纸张处理方法
公开(公告)号：JP2011028512A
公开(公告)日：2011-02-10
申请号：JP2009173504
申请日：2009-07-24
申请人： Toshiba Corp , 株式会社東芝
发明人： NATORI NAOKI
IPC分类号： G07D7/00 , G06T1/00 , G07D7/12 , G07D7/20
CPC分类号： G07D7/187 , G07D7/2075
摘要： PROBLEM TO BE SOLVED: To provide a method for creating a dictionary for fitness determination of paper sheets for use with a paper sheet processing apparatus which enables more accurate fitness determination of paper sheets, and a paper sheet processing apparatus and paper sheet processing method using a dictionary.
SOLUTION: The dictionary creation method includes dividing a sensible area in first and second input adjustment images into a plurality of areas, calculating first and second feature amounts of each divided area of the first and second adjustment images, respectively, calculating means and variances of the first and second feature amounts of each area, respectively, setting weight information for each area based on the calculated means and variances, and storing the weight information for each area together with soil detection thresholds as determinative of soil detection.
COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：提供一种用于创建用于纸张处理设备的纸张的适合度确定的字典的方法，该纸张处理设备能够更准确地确定纸张的适当性，以及纸张处理设备和纸张处理方法使用字典。解决方案：字典创建方法包括将第一和第二输入调整图像中的感觉区域分成多个区域，分别计算第一和第二调整图像的每个划分区域的第一和第二特征量，计算装置和各区域的第一特征量和第二特征量的变化分别基于所计算的平均值和方差来设定每个区域的权重信息，并将每个区域的权重信息与作为土壤检测的土壤检测阈值一起存储。版权所有（C）2011，JPO＆INPIT

7. 发明专利

JP2010039765A Stain determination device, paper sheets processing apparatus, and stain determination method 有权
标题翻译：污染测定装置，纸张处理装置和污染物测定方法
公开(公告)号：JP2010039765A
公开(公告)日：2010-02-18
申请号：JP2008202069
申请日：2008-08-05
申请人： Toshiba Corp , 株式会社東芝
发明人： NATORI NAOKI
IPC分类号： G07D7/00 , G07D7/12 , G07D7/20
CPC分类号： G06K9/6247 , G06T7/0004 , G06T2207/10024 , G06T2207/30144 , H04N1/00005 , H04N1/00023 , H04N1/00037 , H04N1/00047 , H04N1/0005 , H04N1/00063 , H04N1/00068 , H04N1/00087 , H04N1/0009 , H04N1/40
摘要： PROBLEM TO BE SOLVED: To provide a stain determination device highly accurately determining the degree of stain included in image information of a read image or the like of a printed matter. SOLUTION: An input processing part inputs image information including peculiar variations not relating to stain; a feature extraction part 72 extracts a plurality of pieces of feature information from the image information input by the input processing part 71; a separation part 73 separates a set of the plurality of pieces of feature information extracted by the feature extraction part 72, into components of peculiar variations and the other residual components; and a determination part 74 extracts a main component of stain variations showing the degree of stain in the image information inputted by the input processing part 71, from the residual components separated by the separation part 73, and determines the degree of stain in the image information on the basis of the size of the extracted main component of stain variations. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供一种高精度地确定印刷物的读取图像等的图像信息中包含的污渍程度的污点测定装置。输入处理部输入图像信息，该图像信息包括与染色不相关的特殊变化; 特征提取部分72从由输入处理部分71输入的图像信息中提取多条特征信息; 分离部分73将由特征提取部分72提取的多条特征信息的集合分离成特殊变化的分量和其它残差分量; 确定部分74从分离部分73分离出的残留分量中提取表示由输入处理部分71输入的图像信息中的污点程度的污点变化的主要成分，并确定图像信息中的污点基于提取的主要成分的污渍变化的大小。版权所有（C）2010，JPO＆INPIT

8. 发明专利

JP2009199256A Pattern recognition method, character recognition method, pattern recognition program, and character recognition program 有权
标题翻译：图案识别方法，字符识别方法，图案识别程序和字符识别程序
公开(公告)号：JP2009199256A
公开(公告)日：2009-09-03
申请号：JP2008039137
申请日：2008-02-20
申请人： Toshiba Corp , 株式会社東芝
发明人： HAMAMURA TOMOYUKI , IRIE BUNPEI , NATORI NAOKI , AKAGI TAKUMA
IPC分类号： G06K9/72
摘要： PROBLEM TO BE SOLVED: To provide a pattern recognition method, a character recognition method, a pattern recognition program and a character recognition program for quickening processing by performing processing to efficiently recognize a pattern. SOLUTION: The pattern recognition method which is applied to processing of causing an information processor to recognize a pattern in a plurality of steps includes: detecting recognition candidates which can be recognition candidates of each step (S11); expanding the recognition candidates of the next step belonging to each recognition candidate of each step (S15); calculating the evaluation value of each expanded recognition candidate based on an a posterior probability on condition of all recognition processing results for a recognition candidate which has undergone recognition processing (S16); selecting recognition candidates based on the calculated evaluation value of each recognition candidate (S18); and determining a recognition result based on the selected recognition candidates (S21). COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：提供一种模式识别方法，字符识别方法，模式识别程序和用于通过执行有效识别模式的处理的加速处理的字符识别程序。解决方案：应用于使信息处理器在多个步骤中识别模式的处理的模式识别方法包括：检测可以是每个步骤的识别候选的识别候选（S11）; 扩展属于每个步骤的每个识别候选的下一步骤的识别候选（S15）; 基于已进行识别处理的识别候选的所有识别处理结果的条件的后验概率来计算每个扩展识别候选的评估值（S16）; 基于所计算的每个识别候选的评估值来选择识别候选（S18）; 以及基于所选择的识别候选来确定识别结果（S21）。版权所有（C）2009，JPO＆INPIT

9. 发明专利

JP2008204362A Printed matter recognition device and printed matter recognition method 审中-公开
标题翻译：印刷物识别装置和印刷物识别方法
公开(公告)号：JP2008204362A
公开(公告)日：2008-09-04
申请号：JP2007042398
申请日：2007-02-22
申请人： Toshiba Corp , 株式会社東芝
发明人： NATORI NAOKI
IPC分类号： G07D7/12 , G06T1/00
CPC分类号： G07D7/20 , G06K9/03 , G06K2209/01 , G07D7/183
摘要： PROBLEM TO BE SOLVED: To provide a printed matter recognition device for further precisely recognizing paper money by obtaining an input pattern extremely close to true data than a conventional manner. SOLUTION: This printed matter recognition device for recognizing the type or authenticity of paper money is configured to detect the edge fold of paper money in an input pattern acquired from both the sides of paper money, and to apply predetermined working processing to at least either an input pattern or a dictionary pattern by using a geometrical fold model when the edge fold is detected, and to recognize the type of paper money by collating the input pattern with the dictionary pattern. COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：提供一种印刷物识别装置，用于通过获得与常规方式非常接近真实数据的输入图案来进一步精确地识别纸币。解决方案：用于识别纸币的类型或真实性的该打印物识别装置被配置为以从纸币两侧获得的输入图案中检测纸币的边缘折叠，并且将预定的工作处理应用于当检测到边缘折叠时，通过使用几何折叠模型来最小化输入图案或字典图案，并且通过将输入图案与字典图案进行对照来识别纸币的类型。版权所有（C）2008，JPO＆INPIT

10. 发明专利

JPH11272802A Device and method for character recognition 失效
标题翻译：用于字符识别的装置和方法
公开(公告)号：JPH11272802A
公开(公告)日：1999-10-08
申请号：JP7198498
申请日：1998-03-20
申请人： Toshiba Comput Eng Corp , Toshiba Corp , 東芝コンピュータエンジニアリング株式会社 , 株式会社東芝
发明人： TOUCHI YOJIRO , KAWAMURA AKINORI , NATORI NAOKI , KOYAMA KAZUO , SAKAI ICHIRO
IPC分类号： G06K9/68
摘要： PROBLEM TO BE SOLVED: To increase the probability that a correct answer character becomes a candidate of high order. SOLUTION: A recognition part 102 receives the handwriting pattern of a character handwritten on the tablet surface of a character input device 101 from an input device 101, recognizes the handwritten character, and outputs its recognition candidate. A matching part 104 detects all similar characters by retrieval from a similar character dictionary 105 with each candidate character from the recognition part 102. A candidate connection part 106 connects respective candidate characters from the recognition part 102 and respective similar characters from the matching part 104 and outputs all results as recognition candidates. A detailed discrimination part 107 evaluates the similarities of the respective recognition candidates from the candidate connection part 106 by comparing features of the handwriting pattern from the character input device 101 with standard patterns in a corresponding detailed discrimination dictionary 108 and sequences the respective recognition candidates according to the evaluation results.
摘要翻译：要解决的问题：增加正确答案字符成为高阶候选者的可能性。解决方案：识别部分102从输入装置101接收手写在字符输入装置101的平板电脑表面上的字符的手写图案，识别手写字符，并输出其识别候选。匹配部分104通过从与识别部分102的每个候选字符相似的字典105检索来检测所有相似的字符。候选连接部分106将来自识别部分102的相应候选字符和相应的相似字符从匹配部分104连接起来，输出所有结果作为识别候选者。详细鉴别部分107通过将来自字符输入装置101的手写图案的特征与相应的详细鉴别词典108中的标准图案进行比较来评估来自候选连接部分106的各个识别候选者的相似性，并根据评估结果。

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