-
1.发明授权公开(公告)号：US06594393B1
公开(公告)日：2003-07-15
申请号：US09569531
申请日：2000-05-12
IPC分类号： G06K968
CPC分类号： G06K9/6297 , Y10S707/99936
摘要： In a text recognition system, the computational efficiency of a text line image decoding operation is improved by utilizing the characteristic of a graph known as the cut set. The branches of the data structure that represents the image are initially labeled with estimated scores. When estimated scores are used, the decoding operation must perform iteratively on a text line before producing the best path through the data structure. After each iteration, nodes in the best path are re-scored with actual scores. The decoding operation incorporates an operating mode called skip mode. When the number of consecutive image positions for which the change value of cumulative path scores between current and prior iterations is substantially constant and exceeds a threshold, this signals the presence of a cut set, and the score change value is added to a previously computed path score until a re-scored node is encountered, thereby eliminating the expensive computation of new cumulative path scores at those image positions.
摘要翻译： 在文本识别系统中，通过利用称为切割集的图形的特征来提高文本行图像解码操作的计算效率。 表示图像的数据结构的分支最初用估计分数标记。 当使用估计分数时，在通过数据结构生成最佳路径之前，解码操作必须在文本行上迭代执行。 每次迭代后，最佳路径中的节点用实际分数重新计分。 解码操作包括称为跳过模式的操作模式。 当当前迭代和以前迭代之间的累积路径得分的变化值基本上恒定并超过阈值的连续图像位置的数量时，这表示切割集合的存在，并将得分改变值添加到先前计算的路径 得分，直到遇到重新计分的节点，从而消除了在这些图像位置处的新累积路径分数的昂贵计算。
-
2.发明授权公开(公告)号：US06738518B1
公开(公告)日：2004-05-18
申请号：US09570004
申请日：2000-05-12
IPC分类号： G06K968
CPC分类号： G06K9/72 , G06K2209/01
摘要： In a text recognition system that uses a stochastic finite state network to model a document image layout, the computational efficiency of text line decoding is improved. In a typical implementation, the dynamic programming operation that accomplishes decoding uses actual scores computed between two-dimensional (2D) bitmapped character template images and the (2D) bitmapped observed image. Scoring measures the degree of a match between a character template and the observed image. Computation of these actual scores is replaced with the simpler computation of column-based (i.e., one-dimensional) heuristic scores. Because the column-based heuristic scores can be shown to be a true upper bound on actual template-image scores, the heuristic scores are accurate enough to use in place of actual scoring during text line decoding. The heuristic scores essentially reduce the expensive two-dimensional computation of the actual template-image scores required by prior decoding methods to a simpler but accurate one-dimensional computation.
摘要翻译： 在使用随机有限状态网络对文档图像布局进行建模的文本识别系统中，文本行解码的计算效率得到提高。 在典型的实现中，完成解码的动态编程操作使用在二维（2D）位图匹配的字符模板图像和（2D）位图观察图像之间计算的实际分数。 评分测量字符模板与观察图像之间的匹配程度。 这些实际分数的计算由基于列（即，一维）启发式分数的更简单的计算代替。 因为基于列的启发式分数可以显示为实际模板图像分数的真实上限，所以启发式分数足够准确地用于代替文本行解码期间的实际评分。 启发式分数基本上将先前解码方法所需的实际模板图像分数的昂贵的二维计算减少到更简单而准确的一维计算。
-
公开(公告)号：US06678415B1
公开(公告)日：2004-01-13
申请号：US09570730
申请日：2000-05-12
IPC分类号： G06K962
CPC分类号： G06K9/72 , G06K2209/01
摘要： A text recognition system represents the decoded message of a document image as a path through an image network. A method for integrating a language model into the network selectively expands the network to accommodate the language model only for certain ones of the paths in the network, effectively managing the memory storage requirements and computational complexities of integrating the language model efficiently into the network. The language model generates probability distributions indicating the probability of a certain character occurring in a string, given one or more previous characters in the string. Selectively expanding the image network is achieved by initially using upper bounds on the language model probabilities on the branches of an unexpanded image network. A best path search operation is then performed to determine an estimated best path through the image network using these upper bound scores. After decoding, only the nodes on the estimated best path are expanded with new nodes and with branches incoming to the new nodes that accommodate new language model scores reflecting actual character histories in place of the upper bound scores. Decoding and selectively expanding the image network are repeated until the final output transcription of the text image has been produced.
摘要翻译： 文本识别系统将文档图像的解码消息表示为通过图像网络的路径。 将语言模型集成到网络中的方法选择性地扩展网络以适应网络中某些路径的语言模型，有效地管理存储器存储需求和将语言模型有效地集成到网络中的计算复杂性。 语言模型生成指定字符串中某个字符发生概率的概率分布，给定一个或多个字符串中的以前的字符。 通过开始使用未展开图像网络的分支上的语言模型概率的上限来实现选择性地扩展图像网络。 然后执行最佳路径搜索操作以通过使用这些上界得分来确定通过图像网络的估计最佳路径。 在解码之后，只有估计最佳路径上的节点才会用新节点扩展，并且分支进入新节点，以适应反映实际角色历史的新语言模型分数来代替上限分数。 重复解码并选择性地扩展图像网络，直到产生文本图像的最终输出转录。
-
公开(公告)号：US5570435A
公开(公告)日：1996-10-29
申请号：US365251
申请日：1994-12-28
CPC分类号： G06K9/00456 , G06K9/6835
摘要： A method and apparatus for differentiating and extracting handwritten annotations and machine printed text in an image. The method provides for the use of morphological operations, preferably at reduced scale, to eliminate for example, the handwritten annotations from an image. A separation mask is produced that, for example, converts all the image pixels corresponding to machine printed text, and none of the image pixels corresponding to handwritten or handprinted annotations. The separation mask is used in conjunction with the original image to produce separate handwritten annotations and machine printed text images. The invention also provides a method and apparatus for identifying the location of specialized type styles such as bold and italic is disclosed. The method erodes a binary image utilizing structuring elements which provide a relatively large number of hits in regions containing the specialized type styles. The destination image resulting from the erosion is coalesced so as to form masks which may be used to extract portions of the original image containing the specialized type styles.
-
5.发明授权Methods and apparatus for automatic modification of semantically significant portions of a document without document image decoding 失效用于自动修改文档的语义重要部分而不进行文档图像解码的方法和装置
公开(公告)号：US5384863A
公开(公告)日：1995-01-24
申请号：US795174
申请日：1991-11-19
申请人： Daniel P. Huttenlocher , Ronald M. Kaplan , M. Margaret Withgott , Todd A. Cass , Per-Kristian Halvorsen , Dan S. Bloomberg , Ramana B. Rao
发明人： Daniel P. Huttenlocher , Ronald M. Kaplan , M. Margaret Withgott , Todd A. Cass , Per-Kristian Halvorsen , Dan S. Bloomberg , Ramana B. Rao
CPC分类号： G06K9/2054 , G06K2209/01
摘要： Methods and apparatus of processing an undecoded document image in a digital computer to modify the document image so as to emphasize semantically significant portions without first converting the document image to character codes. The document image is segmented into image units, and morphological image characteristics of the image units are evaluated to identify significant image units for emphasis. In one embodiment, the significant image units are emphasized by modifying at least one shape characteristic of the significant image units using at least one uniform morphological bitmap operation applied to the entire image unit bitmaps corresponding to the significant image units.
摘要翻译： 在数字计算机中处理未解码的文档图像以修改文档图像以便在不首先将文档图像转换为字符代码的情况下强调语义上有意义的部分的方法和装置。 将文档图像分割为图像单元，并且评估图像单元的形态图像特征以识别用于强调的重要图像单元。 在一个实施例中，通过使用应用于对应于有效图像单元的整个图像单元位图的至少一个均匀形态位图操作来修改显着图像单元的至少一个形状特征来强调有意图像单元。
-
公开(公告)号：US5157726A
公开(公告)日：1992-10-20
申请号：US810644
申请日：1991-12-19
申请人： Ralph C. Merkle , Dan S. Bloomberg , John S. Brown
发明人： Ralph C. Merkle , Dan S. Bloomberg , John S. Brown
CPC分类号： G07F7/08 , G03G15/221 , G07D7/12 , G07D7/20 , H04L9/3247
摘要： A system for authenticating a hard copy of an original document. The system employs a special copying machine at the sender's end together with a special ID card (smart card) or other user identification for activating the special machine, and a special copying machine at the receiving end. At the sender's station, the original document and ID card are inserted into the machine. The latter digitizes the document text, to produce a digital signature which incorporates unique information from the sender's ID card. This machine then produces a hard copy of the document to which is added the digital signature. The sender retains the original, but forwards the copy to the recipient or receiver. The receiver then inserts the received copy into the machine at his location, which digitizes and processes the document text and signature and indicates whether the digital signature is valid. Preferably a dual key authentication system is used, with the digital signature incorporating the sender's secret signing key, and the receiver using the related public key in the validation process.
-
7.发明授权Data detection and optical focus error detection system for rotating optical media 失效用于旋转光学介质的数据检测和光学聚焦误差检测系统
公开(公告)号：US4801794A
公开(公告)日：1989-01-31
申请号：US45746
申请日：1987-04-29
IPC分类号： G11B7/09 , G11B11/105 , G01J1/20
CPC分类号： G11B11/10576 , G11B7/0912 , G11B7/0946 , G11B7/094
摘要： A magneto-optic optical disc system which uses the magneto-optic differential data detection channel, with addition only a low pass filter, to also detect focus error. The differential data detection channel includes a pair of photodetectors, the first photodetector being located a predetermined distance within the focal length of the detector lens associated with that photodetector and the second photodetector being located beyond the focal length of the detector lens associated with that photodetector. The output of a differential amplifier receiving the photodetector outputs is the data signal and the output of a low pass filter connected to the output of the differential amplifier is the focus error signal. The dual functionality of the differential data detection channel eliminates a separate optical focus channel, and relative to separate astigmatic focus and data detection channels elmininates a quadrature detector, several optical elements, several electrical elements, and the space they occupy.
摘要翻译： 磁光盘系统使用磁光差分数据检测通道，只加一个低通滤波器，也可以检测聚焦误差。 差分数据检测通道包括一对光电检测器，第一光电检测器位于与该光电检测器相关联的检测器透镜的焦距内的预定距离处，并且第二光电检测器位于与该光电检测器相关联的检测器透镜的焦距之外。 接收光电检测器输出的差分放大器的输出是数据信号，并且连接到差分放大器的输出的低通滤波器的输出是聚焦误差信号。 差分数据检测通道的双重功能消除了单独的光学聚焦通道，并且相对于单独的散光焦点和数据检测通道消除了正交检测器，几个光学元件，几个电气元件以及它们所占据的空间。
-
8.发明授权Methods for generating anti-aliased text and line graphics in compressed document images 有权在压缩文档图像中生成反锯齿文本和线图形的方法公开(公告)号：US07266250B2
公开(公告)日：2007-09-04
申请号：US11354044
申请日：2006-02-15
申请人： Dan S. Bloomberg , Luc Vincent
发明人： Dan S. Bloomberg , Luc Vincent
IPC分类号： G06K9/40
摘要： A method and system for storing and generating anti-aliased text and lineart data from compressed document images files, using a MRC model that represents the image as an ordered set of mask/image pairs at resolutions appropriate to the content of each layer. The method and system provide the ability to generate for anti-aliased text data to improve appearance at both high and low resolution, and to avoid baseline jitter of compressed tokens.
摘要翻译： 一种用于从压缩文档图像文件存储和生成抗锯齿文本和线条数据的方法和系统，其使用将所述图像表示为适合于每层内容的分辨率的掩模/图像对的有序集合的MRC模型。 该方法和系统提供生成抗锯齿文本数据以改善高分辨率和低分辨率外观的能力，并避免压缩令牌的基线抖动。
-
9.发明授权Method and apparatus for summarizing a document without document image decoding 失效用于总结文件而不进行文件图像解码的方法和装置
公开(公告)号：US5491760A
公开(公告)日：1996-02-13
申请号：US240284
申请日：1994-05-09
申请人： M. Margaret Withgott , Steven C. Bagley , Dan S. Bloomberg , Per-Kristian Halvorsen , Daniel P. Huttenlocher , Todd A. Cass , Ronald M. Kaplan , Ramana R. Rao
发明人： M. Margaret Withgott , Steven C. Bagley , Dan S. Bloomberg , Per-Kristian Halvorsen , Daniel P. Huttenlocher , Todd A. Cass , Ronald M. Kaplan , Ramana R. Rao
CPC分类号： G06K9/72 , G06K2209/01
摘要： A method and apparatus for excerpting and summarizing an undecoded document image, without first converting the document image to optical character codes such as ASCII text, identifies significant words, phrases and graphics in the document image using automatic or interactive morphological image recognition techniques, document summaries or indices are produced based on the identified significant portions of the document image. The disclosed method is particularly adept for improvement of reading machines for the blind.
摘要翻译： 在不首先将文档图像转换成诸如ASCII文本的光学字符代码的情况下，摘录和总结未解码的文档图像的方法和装置使用自动或交互式形态图像识别技术识别文档图像中的重要单词，短语和图形，文档摘要 或者基于所识别的文档图像的重要部分来生成索引。 所公开的方法特别适用于盲人阅读机的改进。
-
10.发明授权Detecting function words without converting a scanned document to character codes 失效检测功能字，而不将扫描的文档转换为字符代码
公开(公告)号：US5455871A
公开(公告)日：1995-10-03
申请号：US242990
申请日：1994-05-16
CPC分类号： G06K9/00
摘要： A method and apparatus detects function words in a first image of a scanned document without first converting the image to character codes. Function words include determiners, prepositions, articles, and other words that play a largely grammatical role, as opposed to words such as nouns and verbs that convey topic information. Non-content based morphological characteristics of image units are predetermined as well as the presence or omission of character ascenders and descenders in image units. Predetermined characteristics of function word image units are compared with the image units of an image and when a match occurs, the image unit is identified as a function word. Conversely when no matching characteristics occur, the image unit is identified as a non-function word. Additionally, image units are classified and identified as containing only upper case characters, only lower case characters, only digits, and mixed character types.
摘要翻译： 方法和装置检测扫描文件的第一图像中的功能词，而无需首先将图像转换成字符代码。 功能词包括决定者，介词，文章和其他发挥主要语法作用的单词，而不是传达主题信息的名词和动词。 图像单位的基于非内容的形态特征是预先确定的，以及图像单元中角色上升器和下降器的存在或不存在。 将功能字图像单元的预定特征与图像的图像单位进行比较，并且当匹配发生时，图像单元被识别为功能字。 相反，当没有匹配特征出现时，图像单元被识别为非功能字。 此外，图像单位被分类并标识为仅包含大写字母，仅包含小写字母，仅数字和混合字符类型。
-
-
-
-
-
-
-
-
-
搜索结果
58 条记录 (耗时 0.024 秒)
