-
公开(公告)号：US09589185B2
公开(公告)日：2017-03-07
申请号：US14880583
申请日：2015-10-12
CPC分类号： G06K9/00456 , G06K9/00429 , G06K9/6282 , G06K2209/011
摘要： The current document is directed to methods and systems for identifying symbols corresponding to symbol images in a scanned-document image or other text-containing image, with the symbols corresponding to Chinese or Japanese characters, to Korean morpho-syllabic blocks, or to symbols of other languages that use a large number of symbols for writing and printing. In one implementation, the methods and systems to which the current document is directed carry out an initial processing step on one or more scanned images to identify a set of graphemes that most likely correspond to each symbol image that occurs in the scanned document image. The graphemes are selected for a symbol image based on accumulated votes generated from symbol patterns identified as likely related to the symbol image using one or more decision forests.
摘要翻译： 本文件涉及用于识别对应于扫描文档图像或其他含文本图像中的符号图像的符号的方法和系统，其中包含与中文或日文字符对应的符号，韩文形式音节块或符号 使用大量符号进行写入和打印的其他语言。 在一个实现中，当前文档所针对的方法和系统在一个或多个扫描图像上执行初始处理步骤，以识别最可能对应于在扫描的文档图像中出现的每个符号图像的一组图形。 基于从使用一个或多个决策树识别为可能与符号图像相关的符号模式生成的累积投票，为符号图像选择图形。
-
32.发明授权Scanning device having a bed cover including a pattern of repeated design elements 有权具有包括重复设计元件的图案的床罩的扫描装置公开(公告)号：US09413912B2
公开(公告)日：2016-08-09
申请号：US13712950
申请日：2012-12-12
申请人： ABBYY Software Ltd.
发明人： Andrey Isaev
CPC分类号： H04N1/00681 , G06K9/3275 , H04N1/00018 , H04N1/00045 , H04N1/00702 , H04N1/00748 , H04N1/00758 , H04N1/00774 , H04N1/00809 , H04N1/00816 , H04N1/00819 , H04N1/0402 , H04N1/047 , H04N1/10 , H04N1/3872 , H04N1/3878 , H04N1/409 , H04N2201/0006 , H04N2201/0422
摘要： Methods and devices are described for detecting boundaries of documents on flatbed and multi-function scanners on a first pass of a carriage assembly, and then performing a high resolution scan on a second pass. High resolution images of documents can then be obtained with little or no interaction normally necessary to identify areas of interest on the scanner bed. Patterns on the scanner cover or lid facilitate not only edge determination, but orientation of text and other objects, and straightening of images in preparation for OCR and related functions. Electronic images and files derived from paper documents may be automatically cropped, deskewed, subjected to OCR, and named consistent with content or other information derived from them.
摘要翻译： 描述了用于在托架组件的第一次通过中检测平板和多功能扫描仪上的文档的边界，然后在第二遍上进行高分辨率扫描的方法和装置。 那么文件的高分辨率图像然后可以很少或根本不需要进行交互来获得，以识别扫描仪床上的感兴趣区域。 扫描仪盖子或盖子上的图案不仅可以方便边缘确定，还可以方便文本和其他物体，以及校正图像以准备OCR和相关功能。 从纸质文档衍生的电子图像和文件可能会自动裁剪，进行偏斜校正，受到OCR的影响，并与来自它们的内容或其他信息命名一致。
-
公开(公告)号：US09411801B2
公开(公告)日：2016-08-09
申请号：US13725095
申请日：2012-12-21
申请人： Maria Osipova
发明人： Maria Osipova
CPC分类号： G06F17/276 , G06F17/289 , G06K9/00671 , G06K9/6842
摘要： Disclosed are implementations of methods and systems for displaying definitions and translations of words by searching for a translation simultaneously in various languages according to a query in a general language dictionary. The invention removes the need to specify a source language for the word or word combination when translated into a target language. The target language may be preset. Translation is possible for word combinations in multiple sources languages. Source words may be entered manually or captured by an imaging component of an electronic device. When captured, a word combination is selected, and subjected to optical character recognition (OCR) and translation. Source language and OCR language may be suggested via geolocation of the electronic device.
摘要翻译： 公开了用于通过根据通用语言字典中的查询以各种语言同时搜索翻译来显示词语的定义和翻译的方法和系统的实现。 本发明不需要在翻译成目标语言时为单词或单词组合指定源语言。 可以预设目标语言。 可以用多种语言的单词组合进行翻译。 源字可以手动输入或由电子设备的成像部件捕获。 当被捕获时，选择一个单词组合，并进行光学字符识别（OCR）和翻译。 可以通过电子设备的地理定位来建议源语言和OCR语言。
-
公开(公告)号：US09378061B2
公开(公告)日：2016-06-28
申请号：US14571832
申请日：2014-12-16
IPC分类号： G06F9/46 , G06F9/50 , H04L12/911 , G06F9/48
CPC分类号： G06F9/5038 , G06F9/4881 , G06F2209/5021 , H04L47/821
摘要： An algorithm for assigning priorities to tasks queued for processing by users based on how heavily each task's user used the system resources in the past, including the number of tasks queued by the user in the past, the volume of these tasks, and the amount of processor time used. In the OCR context, the tasks are graphic files placed on servers and chosen for processing in accordance with the assigned priorities.
摘要翻译： 一种算法，用于根据过去每个任务的用户使用系统资源的重要程度，为用户排队等待处理的任务优先级，包括过去用户排队的任务数量，这些任务的数量以及 使用处理器时间。 在OCR上下文中，任务是放置在服务器上的图形文件，并根据分配的优先级选择进行处理。
-
35.发明授权Insertion of translation in displayed text consisting of grammatical variations pertaining to gender, number and tense 有权在与性别，数量和时态有关的语法变化的显示文本中插入翻译公开(公告)号：US09053098B2
公开(公告)日：2015-06-09
申请号：US13481644
申请日：2012-05-25
申请人： Elvira Kozlova , Dmitry Levchenko
发明人： Elvira Kozlova , Dmitry Levchenko
IPC分类号： G06F17/28 , G09G5/00 , G06K9/18 , G06F3/0485 , G06F3/01
CPC分类号： G06F17/289 , G06F3/018 , G06F3/0485
摘要： A computer method and an electronic device enable a user to lookup words and insert new words in a text based on the results of the look up. The method executed by the device includes: providing a user with a capability to select at least one word in a text displayed on the screen of the device; performing a dictionary lookup of the identified word so as to determine translation alternatives of the identified word; displaying at least some of the translation alternatives; selecting one of the displayed alternatives; determining its word forms, wherein the word forms consist of gender, number, grammatical tense and grammatical variations of the same word; selecting one of the word forms; and inserting the selected word from in the text.
摘要翻译： 计算机方法和电子设备使得用户能够基于查询的结果来查找单词并在文本中插入新单词。 由该设备执行的方法包括：向用户提供在设备的屏幕上显示的文本中选择至少一个单词的能力; 执行所识别的词的字典查找，以便确定所识别的词的翻译替代; 显示至少一些翻译替代品; 选择显示的替代品之一; 确定其单词形式，其中单词形式由同一单词的性别，数字，语法时态和语法变化组成; 选择一种单词形式; 并从文本中插入所选择的单词。
-
36.发明授权Method and system for looking up words on a display screen by OCR comprising a set of base forms of recognized inflected words 有权用于通过OCR在显示屏幕上查找单词的方法和系统包括一组识别的变形词的基本形式公开(公告)号：US09031831B1
公开(公告)日：2015-05-12
申请号：US13006813
申请日：2011-01-14
申请人： Dmitry Levchenko
发明人： Dmitry Levchenko
CPC分类号： G06F17/2785 , G06F17/2735 , G06F17/2755 , G10L15/265
摘要： Embodiments of the present invention disclose a dictionary lookup method and an electronic device that implements the dictionary lookup method. The dictionary lookup method allows a user to quickly obtain meanings and translations of words from electronic dictionaries while reading a text on a display screen of the electronic device, wherein reading text is utilized by performing an optical character recognition comprising of determining a set of base forms of each inflected recognized word. Advantageously, in one embodiment the meanings (e.g., the base forms) and translations may be displayed in a balloon, in a pop-up window, as subscript, as superscript, or in any other suitable manner when the user touches a word on the display screen, in one embodiment.
摘要翻译： 本发明的实施例公开了一种字典查找方法和实现字典查找方法的电子设备。 字典查找方法允许用户在电子设备的显示屏幕上读取文本的同时，从电子词典中快速获得词语的意义和翻译，其中通过执行光学字符识别来利用阅读文本，所述光学字符识别包括确定一组基本形式 每个变形识别词。 有利的是，在一个实施例中，当用户触摸一个字时，可以在气球，弹出窗口中以下标，上标或任何其他合适的方式显示意义（例如，基本形式）和翻译 显示屏幕，在一个实施例中。
-
公开(公告)号：US08989485B2
公开(公告)日：2015-03-24
申请号：US14053208
申请日：2013-10-14
发明人： Yuri Chulinin , Oleg Senkevich
CPC分类号： G06K9/4642 , G06K9/00 , G06K9/00375 , G06K9/34 , G06K9/342 , G06K9/4647 , G06K9/469 , G06K2209/01 , G06K2209/013
摘要： A method for detecting a junction in a received image of the line of text to update a junction list with descriptive data is provided. The method includes creating a color histogram based on a number of color pixels in the received image of the line of text and detecting, based at least in part on the received image of the line of text, a rung within the received image of the line of text. The method also includes identifying a horizontal position of the detected rung in the received image of the line of text and identifying a gateway on the color histogram, wherein the identified gateway is associated with the detected rung. The junction list is updated with data including a description of the identified gateway.
摘要翻译： 提供了一种用于检测文本行的接收图像中的结以更新具有描述性数据的连接列表的方法。 该方法包括基于文本行的接收图像中的彩色像素的数量创建颜色直方图，并且至少部分地基于所接收的文本行的图像来检测所接收到的图像线内的梯级 的文字。 该方法还包括识别所接收的文本行图像中所检测到的梯级的水平位置，并且识别颜色直方图上的网关，其中所识别的网关与检测到的梯级相关联。 连接列表用包括所识别的网关的描述的数据更新。
-
公开(公告)号：US08928763B2
公开(公告)日：2015-01-06
申请号：US13305768
申请日：2011-11-29
申请人： Mikhail Kostyukov , Sergey Fedorov
发明人： Mikhail Kostyukov , Sergey Fedorov
CPC分类号： G06K9/40 , G06F2207/025 , G06K2209/01 , G06T5/003 , G06T2207/20021 , G06T2207/20056 , G06T2207/20201
摘要： Detecting blur and defocusing in images is described. After detection, correction algorithms are applied. Detection provides an image processing system with parameters related to a blur (e.g., direction, strength) and noise levels, or may trigger a message to a user to re-take a photograph. Detection involves finding and analyzing edges of objects instead of an entire image. Disclosed detector may be used for OCR purposes, blur and defocusing detection in photographic and scanning devices, video cameras, print quality control systems, computer vision. Detection of blur and defocusing of an image involve second derivatives of image brightness. Object edges are detected. For points on edges, profiles of second derivative are obtained in the direction of the gradient. Statistics are gathered about parameters of profiles in various directions. By analyzing statistics, image distortions and their type (e.g., blur, defocusing), the strength of distortion, the direction of the blur are detected.
摘要翻译： 描述了检测图像中的模糊和散焦。 检测后，应用校正算法。 检测提供具有与模糊（例如，方向，强度）和噪声水平相关的参数的图像处理系统，或者可以触发用户重新拍摄照片的消息。 检测涉及查找和分析对象的边缘，而不是整个图像。 公开的检测器可以用于OCR目的，在摄影和扫描设备，摄像机，打印质量控制系统，计算机视觉中的模糊和散焦检测。 图像的模糊和散焦的检测涉及图像亮度的二阶导数。 检测到物体边缘。 对于边缘上的点，在梯度的方向上获得二阶导数的轮廓。 收集有关各方面参数参数的统计数据。 通过分析统计，图像失真及其类型（例如，模糊，散焦），检测失真的强度，模糊的方向。
-
公开(公告)号：US08724930B2
公开(公告)日：2014-05-13
申请号：US12476131
申请日：2009-06-01
申请人： Ding-Yuan Tang
发明人： Ding-Yuan Tang
CPC分类号： G06K9/03 , G06F17/30011
摘要： Embodiments of the present invention disclose a copying method that combines optical character recognition (OCR) technology and a search in order to improve the quality of a copy despite the presence of degrading factors. In one embodiment, the search comprises an Internet search and is used to reconstruct/enhance the copy digitally before outputting the copy to print or some other digital medium. Advantageously, a copy produced using the techniques of the present invention may be at least equal to if not better than the original document copied.
摘要翻译： 本发明的实施例公开了一种组合光学字符识别（OCR）技术和搜索的复制方法，以便尽管存在降级因素来提高拷贝的质量。 在一个实施例中，搜索包括因特网搜索，并且用于在将副本输出到打印机或其他数字媒体之前以数字方式重建/增强副本。 有利地，使用本发明的技术产生的副本可以至少等于如果不是比所复制的原始文档更好。
-
公开(公告)号：US20140126812A1
公开(公告)日：2014-05-08
申请号：US14053208
申请日：2013-10-14
发明人： Yuri CHULININ , Oleg Senkevich
IPC分类号： G06K9/46
CPC分类号： G06K9/4642 , G06K9/00 , G06K9/00375 , G06K9/34 , G06K9/342 , G06K9/4647 , G06K9/469 , G06K2209/01 , G06K2209/013
摘要： A method for detecting a junction in a received image of the line of text to update a junction list with descriptive data is provided. The method includes creating a color histogram based on a number of color pixels in the received image of the line of text and detecting, based at least in part on the received image of the line of text, a rung within the received image of the line of text. The method also includes identifying a horizontal position of the detected rung in the received image of the line of text and identifying a gateway on the color histogram, wherein the identified gateway is associated with the detected rung. The junction list is updated with data including a description of the identified gateway.
摘要翻译： 提供了一种用于检测文本行的接收图像中的结以更新具有描述性数据的连接列表的方法。 该方法包括基于文本行的接收图像中的彩色像素的数量创建颜色直方图，并且至少部分地基于所接收的文本行的图像来检测所接收到的图像线内的梯级 的文字。 该方法还包括识别所接收的文本行图像中所检测到的梯级的水平位置，并且识别颜色直方图上的网关，其中所识别的网关与检测到的梯级相关联。 连接列表用包括所识别的网关的描述的数据更新。
-
-
-
-
-
-
-
-
-
搜索结果
96 条记录 (耗时 0.026 秒)
