公开(公告)号：US08494304B2

公开(公告)日：2013-07-23

申请号：US11801958

申请日：2007-05-11

申请人： Dennis L. Venable ,  Zhigang Fan ,  Lee C. Moore

发明人： Dennis L. Venable ,  Zhigang Fan ,  Lee C. Moore

IPC分类号： G06K9/00 ,  G06K9/40

CPC分类号： G06T7/0004 ,  G06T5/005 ,  G06T2207/10008 ,  G06T2207/30144 ,  H04N1/38

摘要： A method for removal of punched hole artifacts in digital images includes, for a scanned document page, deriving an original digital image that defines the page in terms of a plurality of input pixels. A reduced resolution bitonal image is generated from the original image. The method further includes providing for identifying of candidate punched hole artifacts in the reduced resolution bitonal image and providing for testing the candidate punched hole artifacts for at least one of shape, size, and location. Where a candidate punched hole artifact meets the at least one test, the method includes generating a modified image. This includes erasing the candidate punched hole artifact from the original digital image.

摘要翻译： 用于去除数字图像中的穿孔伪影的方法包括对于扫描的文档页，导出根据多个输入像素定义页面的原始数字图像。 从原始图像生成缩小分辨率的双色图像。 该方法还包括提供在缩小分辨率双色图像中识别候选冲孔缺陷伪像，并提供用于测试形状，尺寸和位置中的至少一个的候选穿孔伪影。 在候选者穿孔孔伪影符合至少一个测试的情况下，该方法包括生成修改的图像。 这包括从原始数字图像中删除候选的穿孔伪影。

公开(公告)号：US07965891B2

公开(公告)日：2011-06-21

申请号：US12710573

申请日：2010-02-23

申请人： John C. Handley ,  M. Armon Rahgozar ,  Dennis L. Venable ,  Pamela B. Spiteri ,  Anoop M. Namboodiri ,  Richard Zanibbi

发明人： John C. Handley ,  M. Armon Rahgozar ,  Dennis L. Venable ,  Pamela B. Spiteri ,  Anoop M. Namboodiri ,  Richard Zanibbi

IPC分类号： G06K9/34

CPC分类号： G06K9/00469

摘要： A system for electronically distilling information from a business document uses a network scanner to electronically scan a platen area, having a business document thereon, to create a bitmap. A network server carries out a segmentation process to segment the scan generated bitmap into a bitmap object, the bitmap object corresponding to the scanned business document; a bitmap to text conversion process to convert the bitmap object into a block of text; a semantic recognition process to generate a structured representation of semantic entities corresponding to the scanned business document; and a document generation process to convert the structured representation into a structure text file. The semantic recognition process includes the processes of generating, for each line of text having a keyword therein, a terminal symbol corresponding to the keyword therein; generating, for each line of text not having a keyword therein and absent of numeric characters, an alphabetic terminal symbol; generating, for each line of text not having a keyword therein and having a numeric character therein, an alphanumeric terminal symbol; generating a string of terminal symbols from the generated terminal symbols; determining a probable parsing of the generated string of terminal symbols; labeling each text line, according to a determined function, with non-terminal symbols; and parsing the business document information text into fields of business document information text based upon the non-terminal symbol of each text line and the determined probable parsing of the generated string of terminal symbols.

摘要翻译： 用于从商业文档电子地蒸馏信息的系统使用网络扫描器来电子扫描其上具有业务文档的压板区域以创建位图。 网络服务器执行分割过程，将扫描生成的位图分割成位图对象，对应于扫描的业务文档的位图对象; 将位图对象转换为文本块的文本转换过程的位图; 语义识别过程，用于生成对应于扫描的业务单据的语义实体的结构化表示; 以及将结构化表示转换成结构文本文件的文档生成处理。 语义识别处理包括对于其中具有关键词的每行文本生成与其中的关键词对应的终端符号的处理; 生成对于其中没有关键字的每行文本和不存在数字字符的字母的终端符号; 为每个不具有关键字的文本行和其中具有数字字符的每行文本生成字母数字终端符号; 从所生成的终端符号生成一串终端符号; 确定所生成的终端符号串的可能解析; 根据确定的功能标记每个文本行，具有非终端符号; 以及基于每个文本行的非终端符号以及确定的所生成的终端符号串的可能解析，将业务文档信息文本解析为商业文档信息文本的字段。

公开(公告)号：US20100149606A1

公开(公告)日：2010-06-17

申请号：US12710573

申请日：2010-02-23

申请人： John C. Handley ,  M. Armon Rahgozar ,  Dennis L. Venable ,  Pamela B. Spiteri ,  Anoop M. Namboodiri ,  Richard Zanibbi

发明人： John C. Handley ,  M. Armon Rahgozar ,  Dennis L. Venable ,  Pamela B. Spiteri ,  Anoop M. Namboodiri ,  Richard Zanibbi

IPC分类号： G06F17/00 ,  G06K9/34 ,  H04N1/04

CPC分类号： G06K9/00469

摘要： A system for electronically distilling information from a business document uses a network scanner to electronically scan a platen area, having a business document thereon, to create a bitmap. A network server carries out a segmentation process to segment the scan generated bitmap into a bitmap object, the bitmap object corresponding to the scanned business document; a bitmap to text conversion process to convert the bitmap object into a block of text; a semantic recognition process to generate a structured representation of semantic entities corresponding to the scanned business document; and a document generation process to convert the structured representation into a structure text file. The semantic recognition process includes the processes of generating, for each line of text having a keyword therein, a terminal symbol corresponding to the keyword therein; generating, for each line of text not having a keyword therein and absent of numeric characters, an alphabetic terminal symbol; generating, for each line of text not having a keyword therein and having a numeric character therein, an alphanumeric terminal symbol; generating a string of terminal symbols from the generated terminal symbols; determining a probable parsing of the generated string of terminal symbols; labeling each text line, according to a determined function, with non-terminal symbols; and parsing the business document information text into fields of business document information text based upon the non-terminal symbol of each text line and the determined probable parsing of the generated string of terminal symbols.

摘要翻译： 用于从商业文档电子地蒸馏信息的系统使用网络扫描器来电子扫描其上具有业务文档的压板区域以创建位图。 网络服务器执行分割过程，将扫描生成的位图分割成位图对象，对应于扫描的业务文档的位图对象; 将位图对象转换为文本块的文本转换过程的位图; 语义识别过程，用于生成对应于扫描的业务单据的语义实体的结构化表示; 以及将结构化表示转换成结构文本文件的文档生成处理。 语义识别处理包括对于其中具有关键词的每行文本生成与其中的关键词对应的终端符号的处理; 生成对于其中没有关键字的每行文本和不存在数字字符的字母的终端符号; 为每个不具有关键字的文本行和其中具有数字字符的每行文本生成字母数字终端符号; 从所生成的终端符号生成一串终端符号; 确定所生成的终端符号串的可能解析; 根据确定的功能标记每个文本行，具有非终端符号; 以及基于每个文本行的非终端符号以及确定的所生成的终端符号串的可能解析，将业务文档信息文本解析为商业文档信息文本的字段。

公开(公告)号：US20080279474A1

公开(公告)日：2008-11-13

申请号：US11801958

申请日：2007-05-11

申请人： Dennis L. Venable ,  Zhigang Fan ,  Lee C. Moore

发明人： Dennis L. Venable ,  Zhigang Fan ,  Lee C. Moore

IPC分类号： G06K9/40

CPC分类号： G06T7/0004 ,  G06T5/005 ,  G06T2207/10008 ,  G06T2207/30144 ,  H04N1/38

摘要： A method for removal of punched hole artifacts in digital images includes, for a scanned document page, deriving an original digital image that defines the page in terms of a plurality of input pixels. A reduced resolution bitonal image is generated from the original image. The method further includes providing for identifying of candidate punched hole artifacts in the reduced resolution bitonal image and providing for testing the candidate punched hole artifacts for at least one of shape, size, and location. Where a candidate punched hole artifact meets the at least one test, the method includes generating a modified image. This includes erasing the candidate punched hole artifact from the original digital image.

摘要翻译： 用于去除数字图像中的穿孔伪影的方法包括对于扫描的文档页，导出根据多个输入像素定义页面的原始数字图像。 从原始图像生成缩小分辨率的双色图像。 该方法还包括提供在缩小分辨率双色图像中识别候选冲孔缺陷伪像，并提供用于测试形状，尺寸和位置中的至少一个的候选穿孔伪影。 在候选者穿孔孔伪影符合至少一个测试的情况下，该方法包括生成修改的图像。 这包括从原始数字图像中删除候选的穿孔伪影。

公开(公告)号：US5289297A

公开(公告)日：1994-02-22

申请号：US769683

申请日：1991-10-02

申请人： James E. Bollman ,  Dennis L. Venable

发明人： James E. Bollman ,  Dennis L. Venable

IPC分类号： G06T1/00 ,  G06T11/60 ,  H04N1/62 ,  H04N1/46

CPC分类号： H04N1/622

摘要： A method for varying the color of an image including lines and background. Where the image includes the colors black and white and a plurality of gray pixels, where gray refers to the presence of pixel values between the maximum and minimum pixel values, inclusive, the image is first converted to a color space, such as for example, r, g, b (red-green-blue). Pixel values are thresholded for differentiation between lines and background. When pixels have a value indicating that the pixel is background, that pixel is set to a background color that has been previously selected. Otherwise, that pixel is set to a foreground color. The result is that background is set to a single color, and lines are set to a second color. Alternatively, where intermediate values are present, the foreground color value may be added to the intermediate level color value to produce a gradually varying colored line.

摘要翻译： 用于改变包括线条和背景的图像的颜色的方法。 在图像包括黑色和白色的颜色和多个灰色像素的情况下，其中，灰色指的是最大和最小像素值之间的像素值的存在，包括首先，图像首先被转换为颜色空间，例如， r，g，b（红 - 绿 - 蓝）。 将像素值用于线和背景之间的区分。 当像素具有指示像素为背景的值时，该像素被设置为先前已选择的背景颜色。 否则，将该像素设置为前景色。 结果是将背景设置为单一颜色，并将线条设置为第二种颜色。 或者，当存在中间值时，前景色值可以被添加到中间级颜色值以产生逐渐变化的彩色线。

公开(公告)号：US09081609B2

公开(公告)日：2015-07-14

申请号：US11613483

申请日：2006-12-20

申请人： Phillip J. Emmett ,  Terry C. Wells ,  Dennis L. Venable ,  James E. Bollman ,  Thomas C. Rich ,  David E. Rumph

发明人： Phillip J. Emmett ,  Terry C. Wells ,  Dennis L. Venable ,  James E. Bollman ,  Thomas C. Rich ,  David E. Rumph

IPC分类号： G06T1/20 ,  G06F9/48

CPC分类号： G06F9/485 ,  G06F9/4881 ,  G06T1/20

摘要： A system and method are disclosed for an image processing system including a threaded scheduler providing compact and efficient dataflow as a pipeline management and data flow layer.

摘要翻译： 公开了一种用于图像处理系统的系统和方法，所述图像处理系统包括作为流水线管理和数据流层提供紧凑而有效的数据流的线程调度器。

公开(公告)号：US20140093858A1

公开(公告)日：2014-04-03

申请号：US13632363

申请日：2012-10-01

申请人： Edward B. Caruthers, JR. ,  Roger A. Newell ,  Robert M. Lofthus ,  Kristine A. German ,  Dennis L. Venable

发明人： Edward B. Caruthers, JR. ,  Roger A. Newell ,  Robert M. Lofthus ,  Kristine A. German ,  Dennis L. Venable

IPC分类号： G09B7/00

CPC分类号： G09B7/02

摘要： The disclosed embodiment relates to methods and systems for evaluating an electronic document. The computer implemented method includes receiving the electronic document containing a first set of answers corresponding to one or more pre-stored questions. The first set of answers are compared with a pre-stored second set of answers based on an answer descriptor syntax dataset. The answer descriptor syntax dataset comprises one or more rules. One or more answer descriptors for each of the first set of answers are determined based on the comparing. The one or more answer descriptors correspond to one or more observations for each of the first set of answers. Finally, the electronic document is evaluated based on determining.

摘要翻译： 所公开的实施例涉及用于评估电子文档的方法和系统。 计算机实现的方法包括接收包含与一个或多个预先存储的问题相对应的第一组答案的电子文档。 将第一组答案与基于答案描述符语法数据集的预先存储的第二组答案进行比较。 答案描述符语法数据集包括一个或多个规则。 基于比较确定第一组答案中的每一个的一个或多个答案描述符。 一个或多个答案描述符对应于第一组答案中的每一个的一个或多个观察值。 最后，电子文档是根据确定进行评估的。

公开(公告)号：US20120188612A1

公开(公告)日：2012-07-26

申请号：US13013890

申请日：2011-01-26

申请人： Michael Robert Campanelli ,  John C. Handley ,  Dennis L. Venable

发明人： Michael Robert Campanelli ,  John C. Handley ,  Dennis L. Venable

IPC分类号： H04N1/40

CPC分类号： H04N1/403 ,  G06K9/03 ,  G06K9/228 ,  G06T5/20 ,  G06T7/194 ,  G06T2207/30144

摘要： An image file representing at least a portion of a printed document is processed to highlight the differences between foreground material (e.g., text or other characters) from background. The method includes selecting a neighborhood of pixels, determining a weighted average of an attribute values (e.g., luminance) for each pixel, and modifying each pixel's value based on the weighted average. Graylevel scaling, error diffusion, and a bit level conversion are also performed each pixel ends up with either a first attribute value level (e.g., luminance of 0) or a second attribute value level (e.g., luminance of 255).

摘要翻译： 处理表示打印文档的至少一部分的图像文件以突出显示来自背景的前景材料（例如，文本或其他字符）之间的差异。 该方法包括选择像素的邻域，确定每个像素的属性值（例如，亮度）的加权平均值，以及基于加权平均值修改每个像素的值。 还执行灰度缩放，误差扩散和位电平转换，每个像素以第一属性值级别（例如，亮度为0）或第二属性值级别（例如，亮度为255）结束。

公开(公告)号：US20110151423A1

公开(公告)日：2011-06-23

申请号：US12640426

申请日：2009-12-17

申请人： Dennis L. Venable

发明人： Dennis L. Venable

IPC分类号： G09B7/00

CPC分类号： G09B7/00

摘要： A method and system for processing a digital assessment template are provided. The system includes at least one tangible processor and a memory with instructions to be executed by the at least one tangible processor for processing a digital assessment template. The template which includes a description of a plurality of data structures that are configured for interpreting an assessment associated with the template. The assessment was marked with strokes by an assessment-taker who was administered the assessment and responded to at least one problem provided by the assessment. The template describes a location of the marked assessment in which to find each stroke that corresponds to a response by the assessment-taker and how to interpret the strokes. Each of the locations and how to interpret the strokes are selectable.

摘要翻译： 提供了一种处理数字评估模板的方法和系统。 该系统包括至少一个有形处理器和具有由至少一个有形处理器执行的用于处理数字评估模板的指令的存储器。 该模板包括被配置用于解释与模板相关联的评估的多个数据结构的描述。 该评估由评估员标记，并由评估员进行了评估，并对评估提供的至少一个问题进行了回应。 该模板描述了标记评估的位置，其中查找与评估者的回答相对应的每个笔画以及如何解释笔画。 每个位置和如何解释笔画是可选择的。

公开(公告)号：US20100150397A1

公开(公告)日：2010-06-17

申请号：US12710568

申请日：2010-02-23

申请人： John C. Handley ,  M. Armon Rahgozar ,  Dennis L. Venable ,  Pamela B. Spiteri ,  Anoop M. Namboodiri ,  Richard Zanibbi

发明人： John C. Handley ,  M. Armon Rahgozar ,  Dennis L. Venable ,  Pamela B. Spiteri ,  Anoop M. Namboodiri ,  Richard Zanibbi

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： G06K9/00469

摘要： A system for electronically distilling information from a business document uses a network scanner to electronically scan a platen area, having a business document thereon, to create a bitmap. A network server carries out a segmentation process to segment the scan generated bitmap into a bitmap object, the bitmap object corresponding to the scanned business document; a bitmap to text conversion process to convert the bitmap object into a block of text; a semantic recognition process to generate a structured representation of semantic entities corresponding to the scanned business document; and a document generation process to convert the structured representation into a structure text file. The semantic recognition process includes the processes of generating, for each line of text having a keyword therein, a terminal symbol corresponding to the keyword therein; generating, for each line of text not having a keyword therein and absent of numeric characters, an alphabetic terminal symbol; generating, for each line of text not having a keyword therein and having a numeric character therein, an alphanumeric terminal symbol; generating a string of terminal symbols from the generated terminal symbols; determining a probable parsing of the generated string of terminal symbols; labeling each text line, according to a determined function, with non-terminal symbols; and parsing the business document information text into fields of business document information text based upon the non-terminal symbol of each text line and the determined probable parsing of the generated string of terminal symbols.