公开(公告)号：US07792324B2

公开(公告)日：2010-09-07

申请号：US11502987

申请日：2006-08-11

申请人： Zhigang Fan ,  William A. Fuss

发明人： Zhigang Fan ,  William A. Fuss

IPC分类号： G06K9/00

CPC分类号： H04N1/32309 ,  H04N1/32229

摘要： A method is provided for embedding miniature security marks within documents and images, utilizing a mark parameters database, graphical user interface, and detection simulator. The method includes predicting detection error rates for each pixel location of a host image, defined as a digital representation of at least one recipient of the miniature security marks. The detection error rates for each pixel are displayed with the host image on a graphical user interface and the desired miniature security mark locations are selected. At least one set of miniature security mark parameters is identified, with the parameters being mark parameters that enable determination of an optimized balance between detectability and visibility of the miniature security marks. The host image with the miniature security mark is displayed on the graphical user interface for review and adjustment by an operator.

摘要翻译： 提供了一种利用标记参数数据库，图形用户界面和检测模拟器在文档和图像内嵌入微型安全标记的方法。 该方法包括预测主机图像的每个像素位置的检测错误率，被定义为微型安全标记的至少一个接收者的数字表示。 每个像素的检测错误率与图像用户界面上的主机图像一起显示，并选择所需的微型安全标记位置。 识别至少一组微型安全标记参数，其中参数是可以确定微型安全标记的可检测性和可见性之间的优化平衡的标记参数。 具有微型安全标记的主机图像显示在图形用户界面上，供操作员查看和调整。

公开(公告)号：US20100128290A1

公开(公告)日：2010-05-27

申请号：US12276024

申请日：2008-11-21

申请人： Zhigang Fan ,  Francis K. Tse ,  Robert E. Nuuja

发明人： Zhigang Fan ,  Francis K. Tse ,  Robert E. Nuuja

IPC分类号： G06F15/00

CPC分类号： B42D25/29

摘要： A method for embedding coded information in a document border includes encoding information as a plurality of data carrying dot pair patterns where each dot is too small to be visually noticeable. For each page of a document to be rendered, the method includes determining whether the border area is blank. If found not blank the border area is cleared. Each of the plurality of data carrying dot patterns is embedded in the blank border area of the document page. The document page with the embedded data carrying dot patterns is then rendered, where each data carrying dot is too small to be visually noticeable.

摘要翻译： 用于将编码信息嵌入到文档边界中的方法包括编码信息作为多个数据携带点对图案，其中每个点太小而不能视觉上看得见。 对于要呈现的文档的每个页面，该方法包括确定边框区域是否为空白。 如果找不到空白，则边界区域被清除。 多个数据携带点图案中的每一个嵌入在文档页面的空白边界区域中。 然后呈现带有点图案的嵌入数据的文档页面，其中每个数据携带点都太小，不能视觉上看得见。

公开(公告)号：US20100033765A1

公开(公告)日：2010-02-11

申请号：US12185904

申请日：2008-08-05

申请人： Zhigang Fan ,  Ramesh Nagarajan

发明人： Zhigang Fan ,  Ramesh Nagarajan

IPC分类号： H04N1/40

CPC分类号： H04N1/40062

摘要： Systems and methods are described that facilitate determining an original document format for a scanned document by analyzing a bitmap thereof. Text objects are extracted from the document, binarized, and segmented to identify text. Page orientation and text size are used to distinguish between a slideshow-type document, and a word processing or spreadsheet-type document. To further distinguish between the word processing and spreadsheet types, text column structure and count is analyzed.

摘要翻译： 描述了通过分析其位图来帮助确定扫描文档的原始文档格式的系统和方法。 从文档中提取文本对象，进行二值化和分段以识别文本。 页面方向和文字大小用于区分幻灯片式文档和文字处理或电子表格类型的文档。 为了进一步区分文字处理和电子表格类型，分析文本列结构和计数。

公开(公告)号：US07660460B2

公开(公告)日：2010-02-09

申请号：US11274638

申请日：2005-11-15

申请人： Wencheng Wu ,  Edul N. Dalal ,  Zhigang Fan

发明人： Wencheng Wu ,  Edul N. Dalal ,  Zhigang Fan

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： H04N1/603 ,  G06K9/00449

摘要： In preparation for rendering respective portions of a document via a respective plurality of engines, objects within the document are identified and characterized. A determination is made as to whether gamut variations between the engines might result in objectionable variations in the appearance of rendered versions of identified objects having similar characteristics. For those objects within the document for which the determination is made that variations might be objectionable, a target gamut is selected to be an intersection gamut of the engines to be used to render the document. For those objects within the document for which the determination is made that variations would be unobjectionable, the target gamut is selected to be that of selected individual engines. A system for selecting target gamuts for objects within a document can include an object identifier, a characteristic identifier and a gamut selector.

摘要翻译： 在准备通过相应的多个引擎呈现文档的各个部分时，识别和表征文档内的对象。 确定发动机之间的色域变化是否可能导致具有相似特征的识别对象的渲染版本的外观的令人反感的变化。 对于确定变化可能令人反感的文档中的那些对象，目标色域被选择为用于呈现文档的引擎的交叉色域。 对于确定变化是无反应的文档中的那些对象，目标色域被选择为所选择的各个引擎的目标色域。 用于为文档中的对象选择目标色域的系统可以包括对象标识符，特征标识符和色域选择器。

公开(公告)号：US07515732B2

公开(公告)日：2009-04-07

申请号：US11034131

申请日：2005-01-12

申请人： Zhigang Fan ,  Shen-ge Wang ,  Hui Cheng

发明人： Zhigang Fan ,  Shen-ge Wang ,  Hui Cheng

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/40

CPC分类号： H04N1/32309 ,  G06T1/0021 ,  G06T2201/0601 ,  H04N1/32144 ,  H04N1/32341 ,  H04N1/6033 ,  H04N2201/0081 ,  H04N2201/3242 ,  H04N2201/3271 ,  H04N2201/3283

摘要： A method for enhancing color fidelity in multi-reproduction, includes scanning an image to be reproduced, wherein the image contains an invisible digital watermark including color information; decoding the color information contained in the watermark; comparing the decoded color information with the scanned image; generating a correction table from the differences between the decoded color information and the scanned image; and performing color correction on the scanned image using the correction table. This method confines the color error to one generation, even when copies go through multiple reproduction.

摘要翻译： 一种用于增强多重再现中的色彩保真度的方法，包括扫描要再现的图像，其中图像包含包含颜色信息的不可见数字水印; 对包含在水印中的颜色信息进行解码; 将解码的颜色信息与扫描图像进行比较; 从解码的颜色信息和扫描图像之间的差异产生校正表; 并使用校正表对扫描图像执行颜色校正。 这种方法将颜色误差限制在一代，即使拷贝经过多重再现。

公开(公告)号：US20080297852A1

公开(公告)日：2008-12-04

申请号：US11756375

申请日：2007-05-31

申请人： Zhigang Fan ,  Reiner Eschbach ,  Judith E. Stinehour

发明人： Zhigang Fan ,  Reiner Eschbach ,  Judith E. Stinehour

IPC分类号： G06K15/00

CPC分类号： B42D25/29

摘要： A method and system is provided for generating a variable data differential line pattern font comprising forming a periodic line pattern suitable for tessellation disposition within a printed document and selectively distorting a portion of the periodic line pattern in a predetermined manner wherein the distorting comprises generating a distinguishable font corresponding to the distorting. A plurality of different distinguishable fonts are formed by a corresponding plurality of distorted line patterns, respectively.

摘要翻译： 提供了一种用于产生可变数据差分线图案字体的方法和系统，包括形成适合于打印文档内的镶嵌布置的周期性线图案，并且以预定方式选择性地扭曲周期线图案的一部分，其中，所述失真包括生成可区分的 字体对应于扭曲。 多个不同的可区分字体分别由对应的多个失真线图案形成。

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：US07433539B2

公开(公告)日：2008-10-07

申请号：US10993852

申请日：2004-11-19

申请人： Shen-Ge Wang ,  Zhigang Fan ,  Reiner Eschbach

发明人： Shen-Ge Wang ,  Zhigang Fan ,  Reiner Eschbach

IPC分类号： G06K9/40 ,  G06K9/32

CPC分类号： H04N1/4097

摘要： A method for run-time streak removal from a scanned image includes providing a scan line of image data from the scanned image; detecting corrupted data within the scan line; evaluating image data located in a neighborhood before and after the corrupted data on the scan line; if the evaluated image data in the neighborhood is smooth, replacing the corrupted data with image data determined by a linear interpolation process; and else if the evaluated image data in the neighborhood is not smooth, replacing the corrupted data with image data determined by the linear prediction process. Various techniques can be used to evaluate the image data located in the surrounding neighborhood. For example, a filter selection step may be used based on prediction discrepancies.

摘要翻译： 从扫描图像中去除运行时间条纹的方法包括从扫描图像提供图像数据的扫描线; 检测扫描线内的损坏的数据; 评估位于扫描线上的损坏数据之前和之后的邻域中的图像数据; 如果附近的评估图像数据平滑，则用由线性内插处理确定的图像数据替换损坏的数据; 否则如果附近的评估图像数据不平滑，则用由线性预测处理确定的图像数据替换损坏的数据。 可以使用各种技术来评估位于周边地区的图像数据。 例如，可以基于预测差异来使用滤波器选择步骤。

公开(公告)号：US07382919B2

公开(公告)日：2008-06-03

申请号：US11472698

申请日：2006-06-22

申请人： Reiner Eschbach ,  Zhigang Fan ,  William Fuss

发明人： Reiner Eschbach ,  Zhigang Fan ,  William Fuss

IPC分类号： G06K9/34

CPC分类号： H04N1/3871

摘要： A method for editing image data includes segmenting input image data into a plurality of discrete objects, wherein each of the objects is defined by a plurality of input pixels that are spatially grouped and that relate to a common content type and feature of the input image data so as to define an objectized input image from the input image data. The objectized input image and a holding area image are generated and simultaneously displayed. Editing input is received from a user by user selection of an object of the objectized input image that the user desires to be moved from the objectized input image to the holding area image based upon the user's visual inspection of the objectized input image. The objectized input image and the holding area image are updated based upon the received editing input so that the selected object is deleted from an original location in the objectized input image and inserted into the holding area image as a temporary object at an insertion location that spatially corresponds to the original location of the objectized input image. The method further includes receiving replacement input data from the user that indicates a selected replacement object in a replacement object database to be inserted into the original location of the objectized input image. The objectized input image is updated to include the selected replacement object in the original location to define an objectized output image.

摘要翻译： 用于编辑图像数据的方法包括将输入图像数据分割成多个离散对象，其中每个对象由空间分组的多个输入像素定义，并且与输入图像数据的公共内容类型和特征相关 以便从输入图像数据中定义一个对象化的输入图像。 产生并同时显示被摄体输入图像和保持区域图像。 基于用户对目标化输入图像的目视检查，用户通过用户选择用户期望从对象化输入图像移动到保持区域图像的对象化输入图像的对象来接收编辑输入。 基于所接收的编辑输入来更新对象化输入图像和保持区域图像，使得所选择的对象在对象化输入图像中从原始位置被删除并且在空间上插入到插入位置中作为临时对象插入到保持区域图像中 对应于对象化输入图像的原始位置。 该方法还包括接收来自用户的替换输入数据，该替换输入数据指示替换对象数据库中的所选择的替换对象，以插入到对象化输入图像的原始位置。 更新对象化的输入图像以在原始位置包括所选择的替换对象以定义对象化的输出图像。

公开(公告)号：US07376272B2

公开(公告)日：2008-05-20

申请号：US10866850

申请日：2004-06-14

申请人： Zhigang Fan ,  Timothy W. Jacobs

发明人： Zhigang Fan ,  Timothy W. Jacobs

IPC分类号： G06K9/34

CPC分类号： G06K9/38 ,  G06K9/00456 ,  G06K2209/01 ,  H04N1/40062

摘要： The present invention is a method for image segmentation to produce a mixed raster content (MRC) image with constant foreground layers. The invention extracts uniform text and other uniform color objects that carry detail information. The method includes four primary steps. First, the objects are extracted from the image. Next, the objects are tested for color consistency and other features to decide if they should be chosen for coding to the MRC foreground layers. The objects that are chosen are then clustered in color space. The image is finally segmented such that each foreground layer codes the objects from the same color cluster.

摘要翻译： 本发明是一种用于图像分割以产生具有恒定前景层的混合光栅内容（MRC）图像的方法。 本发明提供了携带细节信息的统一文本和其他统一的彩色对象。 该方法包括四个主要步骤。 首先，从图像中提取对象。 接下来，测试对象的颜色一致性和其他特征，以决定是否应该选择它们来编码到MRC前景层。 然后将所选择的对象聚类在颜色空间中。 图像最终被分割，使得每个前景层对来自相同颜色集群的对象进行编码。