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

JP2014059770A Delivery object delivery support system and delivery object information management server 审中-公开
标题翻译：交付对象交付支持系统和交付对象信息管理服务器
公开(公告)号：JP2014059770A
公开(公告)日：2014-04-03
申请号：JP2012205015
申请日：2012-09-18
申请人： Toshiba Corp , 株式会社東芝
发明人： MAEDA MASAYA , HAMAMURA TOMOYUKI , KONO YUKA , IRIE BUMPEI , BABA KENJI , SAWADA AKIRA
IPC分类号： G06Q50/28 , G06Q30/02
摘要： PROBLEM TO BE SOLVED: To provide a delivery object delivery support system and a delivery object information management server for enabling a delivery company side to achieve the efficiency of a delivery task, and for enabling a delivery object recipient to easily achieve scheduled recombination corresponding to the reception of a delivery object by enabling the delivery company side and the recipient side to mutually and easily grasp and update situations related to the delivery of the delivery object.SOLUTION: The delivery object delivery support system includes: specification means for specifying the delivery object unique identification information, delivery destination information and attribute information of each delivery object in a delivery object sorting place; a management server in which the specified delivery object unique identification information, delivery destination information and attribute information of the delivery object is registered; route assembly means for assembling the delivery route of the delivery object in accordance with the registered delivery destination information and attribute information of the delivery object; reflection means for reflecting delivery situations in the delivery of the delivery object and the arrival scheduled time of the delivery object to the delivery destination on a display device connected via communication means to the management server; setting means for setting the situations of the delivery object recipient side in the management server by the display device; and notification means for, when the arrival scheduled time of the delivery object is changed from a desired range, notifying the preliminarily registered terminal equipment of the delivery object recipient side of the result.
摘要翻译：要解决的问题：提供递送对象递送支持系统和递送对象信息管理服务器，用于使交付公司方能够实现递送任务的效率，并且使得递送对象接收者能够容易地实现对应于通过使送货公司方和接收方能够相互容易地掌握和更新与交货对象的交付相关的情况来接收交货对象。解决方案：交货对象交付支持系统包括：用于指定交付对象唯一的指定装置识别信息，传送目的地信息和传送对象分拣场所中的每个传送对象的属性信息; 其中注册了指定的递送对象的唯一标识信息，传送目的地信息和传送对象的属性信息的管理服务器; 路线组装装置，用于根据登记的传送目的地信息和传送对象的属性信息组装传送对象的传送路径; 反射装置，用于在通过通信装置连接到显示设备的情况下，将递送对象的传送中的传送情况和传送对象的到达预定时间传送到传送目的地; 用于通过显示装置设置管理服务器中的传送对象接收方的状况的设置装置; 以及通知装置，用于当所述传送对象的到达预定时间从期望的范围改变时，通知所述传送对象接收方的预先注册的终端设备的结果。

2. 发明专利

JP2012187139A Image processing apparatus 有权
标题翻译：图像处理设备
公开(公告)号：JP2012187139A
公开(公告)日：2012-10-04
申请号：JP2011050621
申请日：2011-03-08
申请人： Toshiba Corp , 株式会社東芝
发明人： BOKU HIDE , IRIE BUNPEI , HAMAMURA TOMOYUKI , MAEDA MASAYA , BABA KENJI
IPC分类号： A61B8/00 , G01N29/06
摘要： PROBLEM TO BE SOLVED: To provide an image processing apparatus for objectively classifying a subject into multiple regions and evaluating the classified regions.SOLUTION: The image processing apparatus includes a first calculation part, a first management part, a first evaluation part, a second calculation part, a second management part, and a second evaluation part. The first calculation part calculates feature amounts 0 from image data (S6). The first management part generates and manages an discriminator 0. The first evaluation part evaluates the feature amounts 0 by using the discriminator 0, classifies the image data into multiple region image data, and outputs them (S7-S9). The second calculation part calculates feature amounts i from the region image data. The second management part generates and manages an discriminator i. The second evaluation part evaluates the feature amounts i by using the discriminator i and outputs them.
摘要翻译：要解决的问题：提供一种用于将对象客观地分类为多个区域并评估分类区域的图像处理装置。解决方案：图像处理装置包括第一计算部分，第一管理部分，第一评估部分，第二计算部分，第二管理部分和第二评估部分。第一计算部分从图像数据计算特征量0（S6）。第一管理部分生成并管理鉴别器0.第一评估部通过使用鉴别器0来评估特征量0，将图像数据分类为多个区域图像数据，并将其输出（S7-S9）。第二计算部分从区域图像数据计算特征量i。第二管理部分生成和管理鉴别器i。第二评估部分通过使用鉴别器i来评估特征量i并将其输出。版权所有（C）2013，JPO＆INPIT

3. 发明专利

JP2011194287A Centralized information processing apparatus and system 有权
标题翻译：集中信息处理设备和系统
公开(公告)号：JP2011194287A
公开(公告)日：2011-10-06
申请号：JP2010061538
申请日：2010-03-17
申请人： Toshiba Corp , 株式会社東芝
发明人： MAEDA MASAYA , IRIE BUNPEI , HAMAMURA TOMOYUKI
IPC分类号： B07C3/14 , G06K9/00
CPC分类号： G06K9/033
摘要： PROBLEM TO BE SOLVED: To provide a centralized information processing apparatus and system which enable easy improvement of the rate of recognizing characters written on paper sheets even by a user who is not skilled.SOLUTION: The centralized information processing apparatus includes: a unit 11 for obtaining image data generated from sorting information written on paper sheets, information of sorting destinations of a plurality of top orders having a high score obtained as a result of character recognition and their scores, and taught sorting information; a unit 12 for presenting information related to a recognition rate for each sorting destination based on respective information within a predetermined period of time; a unit 13 for executing simulation of character recognition processing to the image data by using a new parameter value obtained by changing a parameter value forming a score; a unit 14 for generating and presenting a difference list indicating a different content between new sorting information obtained as the simulation result and original sorting information; and a unit 15 for changing the parameter value to the new parameter value when receiving input, indicating that a user accepts the simulation result, from the user.
摘要翻译：要解决的问题：提供一种集中的信息处理装置和系统，其能够容易地提高识别纸张上写入的字符的速率，即使是不熟练的用户。解决方案：集中式信息处理装置包括：单元11，用于获取从写在纸张上的信息分类而生成的图像数据，作为字符识别结果获得的具有高分数的多个顶级顺序的分类目的地的信息及其分数，以及教导分类信息; 用于基于在预定时间段内的各个信息呈现与每个分拣目的地的识别率相关的信息的单元12; 单元13，用于通过使用通过改变形成分数的参数值而获得的新参数值来对图像数据执行字符识别处理的模拟; 用于生成并呈现指示作为模拟结果获得的新排序信息与原始排序信息之间的不同内容的差异列表的单元14; 以及用于当从用户接收输入指示用户接受模拟结果时，将参数值改变为新参数值的单元15。

4. 发明专利

JP2009087087A License plate information processor and license plate information processing method 有权
标题翻译：许可证信息处理器和许可证信息处理方法
公开(公告)号：JP2009087087A
公开(公告)日：2009-04-23
申请号：JP2007256522
申请日：2007-09-28
申请人： Toshiba Corp , 株式会社東芝
发明人： KONO YUKA , AOKI YASUHIRO , HAMAMURA TOMOYUKI
IPC分类号： G06K9/20 , G06K9/32 , G08G1/04
摘要： PROBLEM TO BE SOLVED: To provide a technology for highly precisely extracting a license plate region. SOLUTION: This license plate information processing method includes: detecting a plurality of character candidate regions from an image; voting the position information on each of a plurality of character candidate regions to a voting space configured of the whole or a part of geometrical parameters; selecting voting space coordinates whose vote becomes the largest or the maximum or a prescribed threshold or more; predicting the arrangement of a plurality of character regions in a license plate candidate region from the plurality of character candidate regions according to the value of the parameter corresponding to the voting space coordinates; geometrically converting the template corresponding to the license plate on the basis of the arrangement prediction; approximating the license plate candidate region by the geometrically converted template; and extracting the license plate region on the basis of the approximation result. COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：提供一种用于高精度地提取车牌区域的技术。解决方案：该车牌信息处理方法包括：从图像中检测多个字符候选区域; 将多个字符候选区域中的每一个上的位置信息投票到由整体或一部分几何参数构成的投票空间; 选择投票数最大或最大或者规定阈值以上的投票空间坐标; 根据与投票空间坐标相对应的参数的值，从多个字符候选区域预测车牌候补区域中的多个字符区域的布置; 基于布置预测，几何地转换对应于车牌的模板; 通过几何转换的模板近似牌照候选区域; 并根据近似结果提取牌照区域。版权所有（C）2009，JPO＆INPIT

5. 发明专利

JP2006263512A Address recognition device 有权
标题翻译：地址识别设备
公开(公告)号：JP2006263512A
公开(公告)日：2006-10-05
申请号：JP2005082003
申请日：2005-03-22
申请人： Toshiba Corp , 株式会社東芝
发明人： MAEDA MASAYA , IRIE BUNPEI , ARIYOSHI SHUNJI , HORIUCHI HIDEO , NAKAO AKIHIKO , AKAGI TAKUMA , AOKI YASUHIRO , HAMAMURA TOMOYUKI
IPC分类号： B07C3/14 , G06K9/00
CPC分类号： B07C3/14
摘要： PROBLEM TO BE SOLVED: To prevent effectively wrong recognition of the space for a sender as an address to ensure high-precision recognition of the address.
SOLUTION: An address recognition device recognizing the address of deliveries stores, in database, the description mode including at least the description position and the number and lengths of character rows of the space for the sender in deliveries. When an image is obtained with a scanner, two or more candidate regions 103 in the address region are extracted from the image. It is judged whether or not the description mode of the extracted candidate fits that of the space for the sender stored in the database. When the description mode of the candidate is judged to fit the stored description mode, it is inhibited to recognize the candidate as the address region.
COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：为了有效地错误地识别作为地址的发送者的空间，以确保地址的高精度识别。识别交货地址的地址识别装置在数据库中存储描述模式，该描述模式至少包括交货时发送方的空格的描述位置和字符行的数量和长度。当利用扫描仪获得图像时，从图像中提取地址区域中的两个或更多候选区域103。判断所提取的候选者的描述模式是否适合存储在数据库中的发送者的空间。当候选者的描述模式被判断为符合所存储的描述模式时，禁止将候选者识别为地址区域。版权所有（C）2007，JPO＆INPIT

6. 发明专利

JP2006215964A Character recognition device 审中-公开
标题翻译：字符识别装置
公开(公告)号：JP2006215964A
公开(公告)日：2006-08-17
申请号：JP2005030552
申请日：2005-02-07
申请人： Toshiba Corp , 株式会社東芝
发明人： ARIYOSHI SHUNJI , IRIE BUNPEI , AKAGI TAKUMA , HAMAMURA TOMOYUKI
IPC分类号： G06K9/40 , G06K9/20
CPC分类号： G06K9/36
摘要： PROBLEM TO BE SOLVED: To provide a character recognition device capable of recognizing a character even when an area for writing the character has show-through effects.
SOLUTION: An image for the front face of a document PA is stored as a multivalued image A in an image memory. An image for the back face of the document PA is stored as a multivalued image B in an image memory 44. A CPU 42 extracts the multivalued image A and the multivalued image B for a designated field based on a document format. Then, existence of show-through effects is determined on the extracted multivalued images. That is, the number of pixels with a density value above D is counted in the multivalued image for the back face of the designated field, and when the number of these pixels is N or more, it is determined that show-through effects are present. In the field having the show-through effects, they are removed by a method represented by a formula 2, while they are not removed when they are absent. Then, binarization processing is carried out on the designated field, and character recognition is carried out when images for respective characters are extracted and compared with a character recognition dictionary 45.
COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：即使当用于写入角色的区域具有显示效果时，提供能够识别角色的字符识别装置。解决方案：文件PA的正面的图像作为多值图像A存储在图像存储器中。用于文档PA的背面的图像作为多值图像B存储在图像存储器44中.CPU 42基于文档格式提取用于指定字段的多值图像A和多值图像B. 然后，在提取的多值图像上确定呈现效果的存在。也就是说，在指定字段的背面的多值图像中计数密度值高于D的像素的数量，并且当这些像素的数量为N以上时，确定呈现直通效果。在具有显示效果的领域中，它们通过由公式2表示的方法去除，而当它们不存在时它们不被去除。然后，在指定字段上进行二值化处理，并且当提取用于各个字符的图像并与字符识别字典45进行比较时，执行字符识别。（C）2006年，JPO＆NCIPI

7. 发明专利

JP2003346080A Character recognition method 审中-公开
标题翻译：字符识别方法
公开(公告)号：JP2003346080A
公开(公告)日：2003-12-05
申请号：JP2002147915
申请日：2002-05-22
申请人： Toshiba Corp , 株式会社東芝
发明人： AOKI YASUHIRO , IRIE BUNPEI , HORIUCHI HIDEO , NATORI NAOKI , NAKAO AKIHIKO , AKAGI TAKUMA , HAMAMURA TOMOYUKI
IPC分类号： G06K9/20 , G06K9/03
摘要： PROBLEM TO BE SOLVED: To provide a character recognition method making it possible to enhance the overall processing capability of a character recognition system which requires human verification, by making use of the results of character recognition for input images and their certainty.
SOLUTION: The method includes performing character recognition for an image on an input form; obtaining similarity as the result of this character recognition; comparing the similarity to the previously registered certainty required of the character recognition; and either providing an output indicating that no human verification is required for the result of the character recognition according to the comparison result, or providing an output urging human verification by presenting candidates for character recognition as options for the result of character recognition according to the comparison result, or providing an output urging manual inputting by presenting a manual new input and a determination for the result of the character recognition according to the comparison result.
COPYRIGHT: (C)2004,JPO
摘要翻译：要解决的问题：提供一种字符识别方法，其可以通过利用输入图像的字符识别结果及其确定性来增强需要人类验证的字符识别系统的整体处理能力。解决方案：该方法包括对输入表单上的图像执行字符识别; 作为该字符识别的结果获得相似性; 比较与字符识别所需的先前注册确定性的相似性; 并提供一个输出，指示根据比较结果不需要对人物识别的结果进行人工验证，或者根据比较提供通过提供用于字符识别的候选者来提示人类验证的输出，作为用于字符识别结果的选项或通过根据比较结果提供手动新输入和确定字符识别结果来提供输出，以促进手动输入。版权所有（C）2004，JPO

8. 发明专利

JP2003323586A Document form registering method and document recognizing method 审中-公开
标题翻译：文件格式注册方法和文档识别方法
公开(公告)号：JP2003323586A
公开(公告)日：2003-11-14
申请号：JP2002127021
申请日：2002-04-26
申请人： Toshiba Corp , 株式会社東芝
发明人： AKAGI TAKUMA , IRIE BUNPEI , HORIUCHI HIDEO , NATORI NAOKI , NAKAO AKIHIKO , AOKI YASUHIRO , HAMAMURA TOMOYUKI
IPC分类号： G06K9/20 , G06K9/72 , G06T5/00 , G06T7/00 , G06T7/60
摘要： PROBLEM TO BE SOLVED: To provide a document form registering method extensively reducing labor of a user in form registration, and allowing even an inexperienced user to easily carry out form registration.
SOLUTION: In preregistering a form of a document and recognizing characters written on the document on the basis of the registered form, an image of a blank document with nothing written is captured by using an image inputting means, positions, thicknesses, line types or the like of ruled lines are extracted from the captured image, and information of the extracted ruled lines is registered as form information.
COPYRIGHT: (C)2004,JPO
摘要翻译：要解决的问题：提供一种在形式登记时广泛地减少用户的劳动的文件格式登记方法，并且甚至允许没有经验的用户容易地执行表单注册。
解决方案：在预注册文件的形式和基于注册表格识别文档上的字符时，通过使用图像输入装置，位置，厚度，行来捕获没有写入的空白文档的图像从捕获的图像中提取出划线的类型等，并将所提取的划线的信息登记为形式信息。版权所有（C）2004，JPO

9. 发明专利

JP2014109464A Object measuring device and object measuring method 有权
标题翻译：对象测量装置和对象测量方法
公开(公告)号：JP2014109464A
公开(公告)日：2014-06-12
申请号：JP2012263076
申请日：2012-11-30
申请人： Toshiba Corp , 株式会社東芝
发明人： KONO YUKA , MAEDA MASAYA , HAMAMURA TOMOYUKI , IRIE BUMPEI
IPC分类号： G01B11/24 , G01B11/00
摘要： PROBLEM TO BE SOLVED: To provide an object measuring device and an object measuring method capable of precisely measuring an object.SOLUTION: An object measuring device 100 includes: plural image acquisition units 101 which are disposed at both sides of a conveyance path 103 on which objects 106 are conveyed to acquire distance images from the objects 106 being conveyed by the conveyance path 103; a configuration data generation unit that generates configuration data on the basis of the distance images acquired by the plural image acquisition units 101; a measurement target detection unit that detects a measurement target on an object 106 from the configuration data; and a measurement unit that measures the measurement target 106.
摘要翻译：要解决的问题：提供一种能够精确测量物体的物体测量装置和物体测量方法。解决方案：物体测量装置100包括：多个图像获取单元101，其设置在输送路径103的两侧，传送物体106以从被传送路径103传送的物体106获取距离图像; 配置数据生成单元，其基于由多个图像获取单元101获取的距离图像生成配置数据; 测量对象检测单元，从配置数据检测对象106上的测量对象; 以及测量测量对象106的测量单元。

10. 发明专利

JP2013054600A Word recognition device, word recognition method and paper sheet processing device provided with word recognition device 有权
标题翻译：字识别装置，字识别方法和纸字处理装置，用字识别装置提供
公开(公告)号：JP2013054600A
公开(公告)日：2013-03-21
申请号：JP2011193282
申请日：2011-09-05
申请人： Toshiba Corp , 株式会社東芝
发明人： MAEDA MASAYA , HAMAMURA TOMOYUKI , IRIE BUMPEI , BOKU HIDE
IPC分类号： G06K9/72 , G06K9/00
摘要： PROBLEM TO BE SOLVED: To provide a word recognition device capable of recognizing a word with higher accuracy, and further to provide a word recognition method and a paper sheet processing device provided with the word recognition device.SOLUTION: A word recognition device comprises: a word dictionary for storing a plurality of words; image receiving means for receiving an image containing words; word image extracting means for extracting a word image for each word from the image; character candidate extracting means for extracting a character candidate from the word image; analytical matching means that performs recognition with respect to the character candidate, and calculates a first evaluation value for each word stored in the word dictionary; overall matching means for calculating a second evaluation value on the basis of the word image and a word model for each word stored in the word dictionary; integrated evaluation value calculating means that integrates the first evaluation value and the second evaluation value to calculate a third evaluation value; and outputting means for outputting the third evaluation value calculated by the integrated evaluation value calculating means.
摘要翻译：要解决的问题：提供一种能够更高精度地识别单词的字识别装置，并且还提供一种字识别方法和具有该单词识别装置的纸张处理装置。一种词识别装置，包括：用于存储多个词的词典; 图像接收装置，用于接收包含单词的图像; 用于从图像中提取每个单词的单词图像的单词图像提取装置; 字符候选提取装置，用于从字图像提取字符候选; 分析匹配装置，对所述字符候选进行识别，并且计算出存储在所述单词字典中的每个单词的第一评估值; 整体匹配装置，用于基于单词图像计算第二评估值，以及用于在单词字典中存储的每个单词的单词模型; 综合评估值计算装置，其将所述第一评估值和所述第二评估值进行积分，以计算第三评估值; 以及输出装置，用于输出由综合评估值计算装置计算出的第三评估值。版权所有（C）2013，JPO＆INPIT

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