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
    • 31. 发明授权
    • Image processing method and apparatus and storage medium
    • 图像处理方法及装置及存储介质
    • US06885778B2
    • 2005-04-26
    • US09899283
    • 2001-07-06
    • Kitahiro Kaneda
    • Kitahiro Kaneda
    • G06K9/20G06K9/32G06T1/00G06T3/20G06T7/60
    • G06K9/00469G06K9/32G06K2209/01
    • The positional offset of an image is corrected without performing any processing for the setting of a reference position with respect to a document image, e.g., the setting of markings. Pieces of information about a reference image, including a reference position, are stored in a predetermined storage unit. Information about the input image is extracted from the input image, and a target position on the input image is calculated on the basis of the extracted information. In addition, a reference image with respect to the input image is specified on the basis of the information about the input image from the predetermined storage unit. The positional offset of the target position with respect to the reference position of the specified reference image is calculated. The positional offset of the input image with respect to the reference image is corrected on the basis of the calculated positional offset amount.
    • 校正图像的位置偏移,而不执行关于文档图像的基准位置的设置的任何处理,例如标记的设置。 关于包括参考位置的参考图像的信息的数据被存储在预定的存储单元中。 从输入图像提取关于输入图像的信息,并且基于所提取的信息来计算输入图像上的目标位置。 此外,基于来自预定存储单元的关于输入图像的信息来指定关于输入图像的参考图像。 计算目标位置相对于指定参考图像的参考位置的位置偏移。 基于计算出的位置偏移量来校正输入图像相对于参考图像的位置偏移。
    • 34. 发明授权
    • Image processing apparatus, image processing method, and computer program
    • 图像处理装置,图像处理方法和计算机程序
    • US08532388B2
    • 2013-09-10
    • US13299283
    • 2011-11-17
    • Makoto EnomotoTomotoshi KanatsuKitahiro Kaneda
    • Makoto EnomotoTomotoshi KanatsuKitahiro Kaneda
    • G06K9/00
    • G06F17/2205G06K9/00442
    • This invention generates a digital document by applying character recognition to character images in a document image, and rendering the character recognition result on the document image in a transparent color. This digital document allows to specify a part corresponding to a search keyword on the document image upon conducting a search. When this digital document is generated, it includes a description required to use glyph data (font data) of a simple character shape commonly to a plurality of character types as font data used upon rendering the character recognition result. Therefore, even when the digital document needs to save font data, an increase in file size can be minimized. Also, by rendering using a simple character shape, the data size of the font data itself can be reduced.
    • 本发明通过对文档图像中的字符图像应用字符识别并以文字图像将文字识别结果呈现为透明颜色来生成数字文档。 该数字文档允许在进行搜索时在文档图像上指定与搜索关键词对应的部分。 当生成该数字文档时,它包括将字符数据(字体数据)简单字符形状通常用作多个字符类型所需的描述,作为在呈现字符识别结果时使用的字体数据。 因此,即使数字文档需要保存字体数据,文件大小也可以最小化。 此外,通过使用简单的字符形状进行渲染,可以减少字体数据本身的数据大小。
    • 37. 发明授权
    • Image processing apparatus and image processing method
    • 图像处理装置和图像处理方法
    • US07317833B2
    • 2008-01-08
    • US10990458
    • 2004-11-18
    • Kitahiro Kaneda
    • Kitahiro Kaneda
    • G06K9/00G06K9/34G06T11/20
    • G06K9/4647G06K2209/01
    • There are provided an image processing apparatus and image processing method which can increase the processing efficiency upon obtaining data which allows re-use and re-editing of a document such as a paper document. While image data is input, and pieces of character information included in the input image data are sequentially recognized, the pieces of character information included in the input image data are subjected to outline conversion using vector data. At this time, the character type of the pieces of recognized character information and the vector data having undergone outline conversion are managed while being associated with each other. Upon recognizing the pieces of character information, it is determined whether the character type of the pieces of character information has undergone previous outline conversion. If it is determined that the character type has undergone the previous outline conversion, the management is controlled so as to use vector data used in the previous outline conversion.
    • 提供了一种图像处理装置和图像处理方法,其可以在获得允许重复使用和重新编辑诸如纸质文档的文档的数据时提高处理效率。 当输入图像数据并且顺序地识别包括在输入图像数据中的文字信息时,使用向量数据对包含在输入图像数据中的文字信息进行轮廓转换。 此时,识别的字符信息的字符类型和已经历轮廓转换的矢量数据彼此相关联地被管理。 在识别出这些字符信息时,确定字符信息的字符类型是否经历了之前的轮廓转换。 如果确定字符类型已经进行了前一轮廓转换,则控制管理以便使用在前轮廓转换中使用的矢量数据。
    • 38. 发明授权
    • Image processing method, device and storage medium therefor
    • 图像处理方法,装置和存储介质
    • US07305619B2
    • 2007-12-04
    • US10748208
    • 2003-12-31
    • Kitahiro KanedaTomotoshi Kanatsu
    • Kitahiro KanedaTomotoshi Kanatsu
    • G06F15/00G06K9/32G06K9/36
    • G06K9/3283H04N1/3877
    • The invention significantly improves operability by automatically discriminating a plurality of image orientations, which are not assured of always being fed in common orientations, and reduces possible burdens to operators by eliminating efforts required to arrange the images in a common orientation before feeding or to correct each orientations into a common orientation after feeding. The invention improves the operability also by enabling modes in which orientation discrimination as well as tilt corrections can be performed before operator's instructions, if the Auto mode has been specified for the orientation recognition function. The invention also improves accuracy of processing by determining whether orientations or tilt recognition is proper and providing the result to the operators.
    • 本发明通过自动区分多个图像取向,通过自动识别不能始终以共同定向馈送的方式显着地提高了可操作性,并且通过消除在馈送之前将图像排列成共同的方向所需的努力或减少每个 喂养后方向成共同的方向。 本发明还通过启用能够在操作人员指示之前进行方向判别以及倾斜校正的模式,如果已经为方位识别功能指定了自动模式,则可以改善操作性。 本发明还通过确定方向或倾斜识别是否正确以及向操作者提供结果来提高处理的准确性。
    • 39. 发明申请
    • Communication system and control method, and computer-readable memory
    • 通信系统和控制方法,以及计算机可读存储器
    • US20050163376A1
    • 2005-07-28
    • US11081504
    • 2005-03-17
    • Kitahiro Kaneda
    • Kitahiro Kaneda
    • G06K9/03G06K9/00
    • G06K9/03
    • A mobile terminal reads a read manuscript as image data. A character recognition block performs character recognition from the image data, which is read, on the basis of a threshold for judgement of unrecognizableness. A character recognition result is transmitted to a central control unit, or the threshold for judgement of unrecognizableness is received from the central control unit in a threshold receiver. On the other hand, the central control unit receives the result of character recognition from the mobile terminal, or transmits the threshold for judgement of unrecognizableness from a threshold transmitter to the mobile terminal. Furthermore, the central control unit controls the threshold for judgement of unrecognizableness with a threshold controller.
    • 移动终端将读取的原稿读取为图像数据。 字符识别块基于用于判断不可识别的阈值,从读取的图像数据中执行字符识别。 字符识别结果被发送到中央控制单元,或者在阈值接收器中从中央控制单元接收到用于判断不可识别的阈值。 另一方面,中央控制单元从移动终端接收字符识别的结果,或者从门限发送器向移动终端发送用于判断不可识别的阈值。 此外,中央控制单元通过阈值控制器控制用于判断不可识别的阈值。