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. 发明公开

EP2521071A3 Method and system for text segmentation 无效
标题翻译：方法和系统文本分割
公开(公告)号：EP2521071A3
公开(公告)日：2015-06-03
申请号：EP11004865.9
申请日：2011-06-15
申请人： King Abdulaziz City for Science & Technology (KACST)
发明人： Abdulkader, Ahmad , Al-Omari, Hussein, Khalid , Khorsheed, Mohammad, Sulaiman
IPC分类号： G06K9/34
CPC分类号： G06K9/34 , G06K9/6814 , G06K2209/01 , G06K2209/013
摘要： A method and system for segmenting a text into a plurality of sections is provided. The text may be received in the form of an image. The method involves receiving one or more input labels from a user corresponding to one or more segmentation points of a plurality of segmentation points of the text. The plurality of segmentation points of the text are obtained by applying one or more segmentation heuristics over the text. The one or more input labels provided by the user are utilized to label the plurality of segmentation points of the text. In response to labeling, validation is performed to identify whether a segmentation point of the plurality of segmentation points is a valid segmentation point. Thereafter, based on the validation, a set of valid segmentation points is updated with one or more segmentation points of the plurality of segmentation points. The set of valid segmentation points facilitates segmentation of the text for recognizing the plurality of sections.

2. 发明公开

EP2804131A3 System and methods for arabic text recognition and arabic corpus building 审中-公开
标题翻译：系统和方法检测阿拉伯文文本和阿拉伯语料库重建
公开(公告)号：EP2804131A3
公开(公告)日：2016-09-07
申请号：EP13184319.5
申请日：2013-09-13
申请人： King Abdulaziz City for Science and Technology
发明人： Khorsheed, Mohammad S. , Al-Omari, Hussein K. , Osfoor, Majed Ibrahim Bin , Alobaid, Abdulaziz Obaid , Alfaleh, Hussam Abdulrahman , Asfour, Arwa Ibrahem Bin
IPC分类号： G06K9/68 , G06K9/62
CPC分类号： G06K9/6297 , G06K2209/013
摘要： A method for automatically recognizing Arabic text includes building an Arabic dataset comprising Arabic text files written in different writing styles and actual meanings of the Arabic text corresponding to each of the Arabic text files (100), storing writing-style indices in association with the Arabic text files (105), digitizing a line of Arabic characters to form an array of pixels (321-323) (130), dividing the line of the Arabic characters into line images, (311-313) (120), forming a text feature vector from the line images (311-313) (140), training a Hidden Markov Model using the Arabic text files and ground truths in the Arabic dataset in accordance with the writing-style indices (160), and feeding the text feature vector into a Hidden Markov Model to recognize the line of Arabic characters (170).

3. 发明公开

EP2735999A2 Systems and methods for arabic text recognition based on effective arabic text feature extraction 无效
标题翻译：系统和基于有效阿拉伯文文本特征提取的阿拉伯文字识别方法
公开(公告)号：EP2735999A2
公开(公告)日：2014-05-28
申请号：EP13162898.4
申请日：2013-04-09
申请人： King Abdulaziz City for Science & Technology (KACST)
发明人： Khorsheed, Mohammad Sulaiman , Al-Omari, Hussein Khalid
IPC分类号： G06K9/34
CPC分类号： G06K9/6297 , G06K2209/013
摘要： A method for automatically recognizing Arabic text includes digitizing a line of Arabic characters to form a two-dimensional array of pixels each associated with a pixel value, wherein the pixel value is expressed in a binary number, dividing the line of the Arabic characters into a plurality of line images, defining a plurality of cells in one of the plurality of line images, wherein each of the plurality of cells comprises a group of adjacent pixels, serializing pixel values of pixels in each of the plurality of cells in one of the plurality of line images to form a binary cell number, forming a text feature vector according to binary cell numbers obtained from the plurality of cells in one of the plurality of line images, and feeding the text feature vector into a Hidden Markov Model to recognize the line of Arabic characters.
摘要翻译：一种用于自动识别阿拉伯语文本方法包括数字化的线的阿拉伯字符，以形成像素的二维阵列中的每个具有像素值，worin像素值被二进制数过表达相关联，将所述阿拉伯字符的行成一线图像的多个，定义单元的多个在线图像的多个中的一个，worin每个细胞的多个包括一组相邻像素的，在各单元的多个串行化像素的像素值在所述多个中的一个线图像以形成二元细胞数，在线条图象的多个一形成文本特征向量雅丁从细胞获得的多个二进制细胞数，和文本特征向量馈送到隐马尔可夫模型来识别线的阿拉伯字符。

4. 发明公开

EP2662802A1 Method and system for preprocessing an image for optical character recognition 无效
标题翻译： Verfahren und System zur Vorverabeitung eines Bildes zur optischen Zeichenerkennung
公开(公告)号：EP2662802A1
公开(公告)日：2013-11-13
申请号：EP13162939.6
申请日：2013-04-09
申请人： King Abdulaziz City for Science & Technology (KACST)
发明人： Al-Omari, Hussein Khalid , Khorsheed, Mohammad Sulaiman
IPC分类号： G06K9/00
CPC分类号： G06K9/00463 , G06K2209/013
摘要： A method and system for preprocessing an image, wherein the image includes a plurality of columns, or regions, of text is disclosed. A plurality of components associated with the text is determined. On determining the plurality of components, a line height and a column spacing is determined for the components. The components are then associated with a column based on the line height and the column spacing. A set of characteristic parameters are calculated for each column and the plurality of components of each column are merged based on the characteristic parameters to form sub-words and words. A first plurality of words and/or subwords is merged and processed as a first region and a second plurality of words and/or subwords is merged and processed as a second region wherein at least a portion of the second region vertically overlaps at least a portion of the first region.
摘要翻译：一种用于预处理图像的方法和系统，其中所述图像包括文本的多个列或区域。确定与文本相关联的多个组件。在确定多个组件时，确定组件的行高和列间距。然后根据线高度和列间距将组件与列相关联。针对每列计算一组特征参数，并且基于特征参数合并每列的多个分量以形成子词和词。第一多个单词和/或子词被合并和处理为第一区域，并且第二多个单词和/或子词被合并和处理为第二区域，其中第二区域的至少一部分垂直重叠至少一部分的第一个地区。

5. 发明公开

EP2395453A2 Method and system for preprocessing an image for optical character recognition 审中-公开
标题翻译： Verfahren und System zur Vorverabeitung eines Bildes zur optischen Zeichenerkennung
公开(公告)号：EP2395453A2
公开(公告)日：2011-12-14
申请号：EP10197110.9
申请日：2010-12-28
申请人： King Abdulaziz City for Science and Technology
发明人： Al-Omari, Hussein Khalid , Khorsheed, Mohammad Sulaiman
IPC分类号： G06K9/20
CPC分类号： G06K9/00463 , G06K2209/013
摘要： A method and system for preprocessing an image for Optical Character Recognition (OCR), wherein the image includes a plurality of columns is disclosed. Each column includes one or more of Arabic text and non-text items. The method includes determining a plurality of components associated with one or more of the Arabic text and the non-text items, wherein a component includes a set of connected pixels. On determining the plurality of components, a line height and a column spacing is determined for the plurality of components. The plurality of components are then associated with a column of the plurality of columns based on the line height and the column spacing. Subsequently, a set of characteristic parameters are calculated for each column and the plurality of components of each column are merged based on the set of characteristic parameters to form sub-words and words.
摘要翻译：一种用于预处理光学字符识别（OCR）的图像的方法和系统，其中所述图像包括多个列。每列包括一个或多个阿拉伯语文本和非文本项。该方法包括确定与阿拉伯语文本和非文本项目中的一个或多个相关联的多个组件，其中组件包括一组连接的像素。在确定多个分量时，确定多个分量的行高和列间距。然后，多个部件基于线高度和列间距与多列的列相关联。随后，针对每列计算一组特征参数，并且基于该特征参数集合将每列的多个分量合并以形成子词和单词。

6. 发明公开

EP3131036A1 A HMI SYSTEM BASED ON A 3D TOTO WORD CARD 审中-公开
标题翻译： HMI系统AUF BASIS EINER 3D TOTO WORTKARTE
公开(公告)号：EP3131036A1
公开(公告)日：2017-02-15
申请号：EP16163985.1
申请日：2016-04-06
申请人： Shandong Douxiang Internet Media Co., Ltd
发明人： ZHOU, Xiaodong
IPC分类号： G06K9/20 , G06K9/62
CPC分类号： G06K9/6202 , G06K9/2063 , G06K9/4609 , G06K9/4652 , G06K9/6204 , G06K2209/011 , G06K2209/013 , G09B19/06
摘要： The present invention relates to a HMI system based on a 3D TOTO word card, comprising a verification activation module, a scanning module, a identification module, a matching module, a display module, a camera module, a help module, a interaction module, a storage module, a sharing module and a CPU. The scanning module comprises a single-card scanning module, a combined scanning module and an experience scanning module. The verification activation module, scanning module, identification module, matching module, display module, camera module, help module, interaction module, storage module and share module are connected with CPU, respectively. The present invention increases children's practical ability in the cognitive process of Chinese characters and improves Children's participation in the cognitive process of Chinese characters, thus improving Children's efficiency and fun of cognition of Chinese characters; in addition, when entering the system, the customers need to get a verification code from the merchant, and activate the system by verification activation module, to facilitate the merchant to provide customers with other follow-up services, such as notification sending or password extracting.
摘要翻译：本发明涉及一种基于3D TOTO字卡的HMI系统，包括验证激活模块，扫描模块，识别模块，匹配模块，显示模块，相机模块，帮助模块，交互模块，存储模块，共享模块和CPU。扫描模块包括单卡扫描模块，组合扫描模块和体验扫描模块。验证激活模块，扫描模块，识别模块，匹配模块，显示模块，摄像头模块，帮助模块，交互模块，存储模块和共享模块分别与CPU相连。本发明增加了儿童在汉字认知过程中的实践能力，提高了儿童对汉字认知过程的参与度，提高了儿童的汉字认知效率和乐趣; 另外，当进入系统时，客户需要从商家获取验证码，并通过验证激活模块激活系统，以便商家为客户提供其他后续服务，如通知发送或密码提取。

7. 发明公开

EP2804131A2 System and methods for arabic text recognition and arabic corpus building 审中-公开
标题翻译：系统和方法检测阿拉伯文文本和阿拉伯语料库重建
公开(公告)号：EP2804131A2
公开(公告)日：2014-11-19
申请号：EP13184319.5
申请日：2013-09-13
申请人： King Abdulaziz City for Science and Technology
发明人： Khorsheed, Mohammad S. , Al-Omari, Hussein K. , Osfoor, Majed Ibrahim Bin , Alobaid, Abdulaziz Obaid , Alfaleh, Hussam Abdulrahman , Asfour, Arwa Ibrahem Bin
IPC分类号： G06K9/68
CPC分类号： G06K9/6297 , G06K2209/013
摘要： A method for automatically recognizing Arabic text includes building an Arabic dataset comprising Arabic text files written in different writing styles and actual meanings of the Arabic text corresponding to each of the Arabic text files (100), storing writing-style indices in association with the Arabic text files (105), digitizing a line of Arabic characters to form an array of pixels (321-323) (130), dividing the line of the Arabic characters into line images, (311-313) (120), forming a text feature vector from the line images (311-313) (140), training a Hidden Markov Model using the Arabic text files and ground truths in the Arabic dataset in accordance with the writing-style indices (160), and feeding the text feature vector into a Hidden Markov Model to recognize the line of Arabic characters (170).
摘要翻译：一种自动识别阿拉伯文字方法包括阿拉伯语数据集的建筑，与阿拉伯协会包括阿拉伯语文本文件写在不同的写作风格和阿拉伯文字对应于每个阿拉伯文文本文件中的实际含义（100）存储的写作风格指数文本文件（105）数字化的线的阿拉伯字符，以在像素阵列（321-323）（130）将所述阿拉伯语的字符形成一文本行成线图像（311-313）（120）从线图像的特征向量（311-313）（140）使用阿拉伯语的文本文件和地面的真理在雅舞蹈阿拉伯语数据集的写作风格指数（160）训练隐马尔可夫模型，和喂养文本特征向量成隐马尔可夫模型来识别的阿拉伯字符（170）的线。

8. 发明公开

EP2395453A3 Method and system for preprocessing an image for optical character recognition 审中-公开
标题翻译：的方法和系统Vorverabeitung用于光学字符识别的图像
公开(公告)号：EP2395453A3
公开(公告)日：2013-08-28
申请号：EP10197110.9
申请日：2010-12-28
申请人： King Abdulaziz City for Science and Technology
发明人： Al-Omari, Hussein Khalid , Khorsheed, Mohammad Sulaiman
IPC分类号： G06K9/20
CPC分类号： G06K9/00463 , G06K2209/013
摘要： A method and system for preprocessing an image for Optical Character Recognition (OCR), wherein the image includes a plurality of columns is disclosed. Each column includes one or more of Arabic text and non-text items. The method includes determining a plurality of components associated with one or more of the Arabic text and the non-text items, wherein a component includes a set of connected pixels. On determining the plurality of components, a line height and a column spacing is determined for the plurality of components. The plurality of components are then associated with a column of the plurality of columns based on the line height and the column spacing. Subsequently, a set of characteristic parameters are calculated for each column and the plurality of components of each column are merged based on the set of characteristic parameters to form sub-words and words.

9. 发明公开

EP2521071A2 Method and system for text segmentation 无效
标题翻译： Verfahren und System zur Textsegmentierung
公开(公告)号：EP2521071A2
公开(公告)日：2012-11-07
申请号：EP11004865.9
申请日：2011-06-15
申请人： King Abdulaziz City for Science & Technology (KACST)
发明人： Abdulkader, Ahmad , Al-Omari, Hussein, Khalid , Khorsheed, Mohammad, Sulaiman
IPC分类号： G06K9/34
CPC分类号： G06K9/34 , G06K9/6814 , G06K2209/01 , G06K2209/013
摘要： A method and system for segmenting a text into a plurality of sections is provided. The text may be received in the form of an image. The method involves receiving one or more input labels from a user corresponding to one or more segmentation points of a plurality of segmentation points of the text. The plurality of segmentation points of the text are obtained by applying one or more segmentation heuristics over the text. The one or more input labels provided by the user are utilized to label the plurality of segmentation points of the text. In response to labeling, validation is performed to identify whether a segmentation point of the plurality of segmentation points is a valid segmentation point. Thereafter, based on the validation, a set of valid segmentation points is updated with one or more segmentation points of the plurality of segmentation points. The set of valid segmentation points facilitates segmentation of the text for recognizing the plurality of sections.
摘要翻译：提供了一种用于将文本分割成多个部分的方法和系统。可以以图像的形式接收文本。该方法涉及从对应于文本的多个分割点中的一个或多个分割点的用户接收一个或多个输入标签。通过在文本上应用一个或多个分割启发式算法来获得文本的多个分割点。使用由用户提供的一个或多个输入标签来标记文本的多个分割点。响应于标签，执行验证以识别多个分割点的分割点是否是有效的分割点。此后，基于验证，利用多个分割点中的一个或多个分割点更新一组有效分割点。有效分段点的集合有助于文本的分割以识别多个部分。

10. 发明公开

EP0120481A3 Method and device for selecting a character shape for each character of a text, e.g. of Arabic, according to four classes 失效
标题翻译：用于选择文本的每个字符的字符形状的方法和装置，E.G. 阿拉伯语根据四个类别
公开(公告)号：EP0120481A3
公开(公告)日：1988-02-10
申请号：EP84103192
申请日：1984-03-22
申请人： NEC CORPORATION
发明人： Hamaguchi, Yoshio
IPC分类号： G06K09/62 , B41J03/00 , G09G01/00
CPC分类号： G09G5/246 , B41J3/01 , G06K2209/013
摘要： In a character shape selecting device, one of character shapes is selected to provide a character shape sequential expression for each character (in 21) of a character sequential expression from a character shape table (18) at a predetermined timing in each cycle by a combination of the character (code) in question and a backward linking characteristic (in 22) and a forward linking characteristic (in 23) of next forwardly and backwardly adjacent independent characters. The character shapes are selected in effect by classifying the independent characters of a character set into three classes in which event, the dependent characters are regarded to be in a fourth class. The independent characters are distinguished from the dependent characters with reference to a dependability stored in a character attribute table (17) together with the backward and the forward linking characteristics for each character of the set.

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