公开(公告)号：US20130045751A1

公开(公告)日：2013-02-21

申请号：US13486359

申请日：2012-06-01

申请人： Hui Chao ,  Nan Hu ,  Saumitra Mohan Das ,  Rajarshi Gupta

发明人： Hui Chao ,  Nan Hu ,  Saumitra Mohan Das ,  Rajarshi Gupta

IPC分类号： H04W4/02

CPC分类号： G06F17/30528 ,  G01C21/206 ,  G01C21/3602 ,  G01S5/16

摘要： Example methods, apparatuses, or articles of manufacture are disclosed herein that may be utilized, in whole or in part, to facilitate or support one or more operations or techniques for logo detection for indoor positioning for use in or with a mobile device. Briefly, in accordance with one implementation, a method may include extracting, at a mobile device, visual features from one or more images captured via a camera sensor of the mobile device; and estimating a location of the mobile device based, at least in part, on a match between extracted visual features and one or more brand-specific visual signatures associated with one or more points of interest of one or more known locations. In some instances, an estimated location of a mobile device may be refined based, at least in part, on at least one additional POI of one or more POIs of one or more known locations.

摘要翻译： 本文公开的可以全部或部分地用于促进或支持一种或多种用于在移动设备中或与移动设备一起使用的室内定位的标志检测的操作或技术的示例性方法，设备或制品。 简而言之，根据一个实现方式，一种方法可以包括在移动设备处从经由移动设备的相机传感器捕获的一个或多个图像中提取视觉特征; 以及至少部分地基于提取的可视特征与与一个或多个已知位置的一个或多个兴趣点相关联的一个或多个品牌特定视觉签名之间的匹配来估计移动设备的位置。 在一些情况下，移动设备的估计位置可以至少部分地基于一个或多个已知位置的一个或多个POI的至少一个附加POI进行改进。

公开(公告)号：US08056001B2

公开(公告)日：2011-11-08

申请号：US10410999

申请日：2003-04-10

申请人： Hui Chao

发明人： Hui Chao

IPC分类号： G06F17/00

CPC分类号： G06F3/1208 ,  G06F3/1242 ,  G06F3/1275 ,  G06F3/1284

摘要： A method of classifying elements of a document includes receiving a file defining a document having at least one page and a plurality of elements. Each selected element is classified into one of a plurality of categories based on at least one of the element type, location, size (area, height, or width), or recurrence throughout the document.

摘要翻译： 对文档的元素进行分类的方法包括接收定义具有至少一个页面和多个元素的文档的文件。 基于元素类型，位置，大小（面积，高度或宽度）中的至少一个或整个文档中的重复，将每个所选择的元素分类为多个类别中的一个。

公开(公告)号：US08000529B2

公开(公告)日：2011-08-16

申请号：US11827526

申请日：2007-07-11

申请人： Hui Chao ,  Jian Fan ,  Steven J. Simske

发明人： Hui Chao ,  Jian Fan ,  Steven J. Simske

IPC分类号： G06K9/34 ,  G06K9/62 ,  G06K9/00

CPC分类号： G06K9/00442 ,  G06F17/248

摘要： Embodiments of the present invention recite a system and method for creating an editable template from a document image. In one embodiment of the present invention, the spatial characteristics and the color characteristics of at least one region of a document are identified. A set of characteristics of a graphic representation within the region are then determined without the necessity of recognizing a character comprising the graphic representation. An editable template is then created comprising a second region having the same spatial characteristics and the same color characteristics of the at least one region of the document and comprising a second graphic representation which is defined by the set of characteristics of the first graphic representation.

摘要翻译： 本发明的实施例背诵用于从文档图像创建可编辑模板的系统和方法。 在本发明的一个实施例中，识别文档的至少一个区域的空间特性和颜色特性。 然后确定区域内的图形表示的一组特征，而不需要识别包括图形表示的字符。 然后创建可编辑的模板，其包括具有与文档的至少一个区域相同的空间特征和相同颜色特征的第二区域，并且包括由第一图形表示的特征集合定义的第二图形表示。

公开(公告)号：US07555711B2

公开(公告)日：2009-06-30

申请号：US11166931

申请日：2005-06-24

申请人： Hui Chao ,  Xiaofan Lin ,  Charles G. Nelson

发明人： Hui Chao ,  Xiaofan Lin ,  Charles G. Nelson

IPC分类号： G06F17/00

CPC分类号： G06F17/211

摘要： Methods, systems and machine-readable instructions for processing an electronic document are described. In one aspect, logical blocks that were extracted from the electronic document, including a text block comprising text lines each encompassed by a respective bounding rectangle, are received. Edges of ones of the bounding rectangles are extended to at least one boundary without changing layout relationships among the logical blocks in the electronic document. A text layout boundary is generated from extended and unextended edges of the bounding rectangles. A description of the text layout boundary is stored in a machine-readable medium.

摘要翻译： 描述了用于处理电子文档的方法，系统和机器可读指令。 在一个方面，从电子文档中提取的逻辑块，包括由各自的边界矩形包含的文本行的文本块。 边界矩形的边缘扩展到至少一个边界，而不改变电子文档中的逻辑块之间的布局关系。 文本布局边界由边界矩形的扩展和未延伸边缘生成。 文本布局边界的描述存储在机器可读介质中。

公开(公告)号：US07421116B2

公开(公告)日：2008-09-02

申请号：US10809234

申请日：2004-03-25

申请人： Jian Fan ,  Hui Chao

发明人： Jian Fan ,  Hui Chao

IPC分类号： G06K9/00

CPC分类号： G06T11/60

摘要： Systems and methods according to the present invention provide techniques to automatically insert an object from one image into a region of another image. The systems and methods require little or no user interaction to allow efficient re-use and updating of existing images, presentations, documents and the like. An object and a container region are identified. Feasible placement location(s) within the container region for the object, as well as an associated scale factor, are determined. If multiple feasible placement locations are identified for a particular scale factor, then one is selected based upon predetermined criteria. The object can then be inserted into the container region and the resulting composite image stored or, alternatively, parameters can be stored which enable object insertion at a subsequent processing step.

摘要翻译： 根据本发明的系统和方法提供了将对象从一个图像自动插入到另一个图像的区域中的技术。 系统和方法需要很少或没有用户交互以允许有效地重新使用和更新现有图像，演示文稿，文档等。 识别对象和容器区域。 确定对象的容器区域内的可行放置位置以及相关的比例因子。 如果针对特定的比例因子识别出多个可行的放置位置，则基于预定标准来选择一个。 然后可以将对象插入到容器区域中，并且可以存储所生成的合成图像，或者可以存储参数，以在随后的处理步骤中使对象插入。

公开(公告)号：US20080095470A1

公开(公告)日：2008-04-24

申请号：US11551733

申请日：2006-10-23

申请人： Hui Chao ,  Prassd Gabbur

发明人： Hui Chao ,  Prassd Gabbur

IPC分类号： G06K9/34 ,  G06K9/32

CPC分类号： G06K9/38 ,  G06T3/0012

摘要： A method for auto-resizing an original digital image from an original image to a resized image. The method comprises separating the foreground elements from the background elements, determining an original aspect ratio of the foreground elements and creating resized foreground elements by scaling the foreground elements while maintaining the original aspect ratio. The method further comprises creating resized background elements by stretching or shrinking the background elements to fit the dimensions of the resized image and repositioning the resized foreground and background elements on the resized image while maintaining the design intention of the original image.

摘要翻译： 一种用于将原始数字图像从原始图像自动调整到调整大小的图像的方法。 该方法包括从背景元素分离前景元素，通过在保持原始宽高比的同时缩放前景元素来确定前景元素的原始宽高比并创建调整大小的前景元素。 该方法还包括通过拉伸或收缩背景元素以适应调整大小的图像的尺寸并且在维持原始图像的设计意图的同时将调整大小的前景和背景元素重新定位在经调整大小的图像上来创建调整大小的背景元素。

公开(公告)号：US20070022003A1

公开(公告)日：2007-01-25

申请号：US11184098

申请日：2005-07-19

申请人： Hui Chao ,  Menaka Indrani ,  Gary Vondran ,  Xiaofan Lin ,  Parag Joshi ,  Dirk Beyer ,  C. Atkins ,  Pere Obrador ,  Alex Zhang

发明人： Hui Chao ,  Menaka Indrani ,  Gary Vondran ,  Xiaofan Lin ,  Parag Joshi ,  Dirk Beyer ,  C. Atkins ,  Pere Obrador ,  Alex Zhang

IPC分类号： G06Q30/00

CPC分类号： G06Q30/02 ,  G06Q30/0201 ,  G06Q30/0247 ,  G06Q30/0249 ,  G06Q30/0254 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q30/0273

摘要： Methods, machines, systems and machine-readable instructions for producing marketing items are described. In one aspect, a user is prompted to specify campaign parameters, including one or more campaign topics, defining a scope of the campaign. The user is prompted to specify for each of the one or more campaign topics a corresponding set of one or more attributes of intended recipients of the marketing campaign. The one or more specified campaign topics are associated to respective sets of targeted recipients selected from a database of records of potential recipients based on mappings of the respective sets of recipient attributes to the campaign topics and the specified campaign parameters defining the scope of the marketing campaign. For each of the targeted recipients, a respective marketing item containing a respective set of one or more contents matched to the campaign topic associated to the targeted recipient is composed.

摘要翻译： 描述了用于生产营销项目的方法，机器，系统和机器可读指令。 在一个方面，提示用户指定广告系列参数，包括一个或多个活动主题，定义广告系列的范围。 提示用户为一个或多个活动主题中的每一个指定营销活动的预期接收者的一个或多个属性的对应集合。 一个或多个指定的活动主题与从潜在接收者的记录的数据库中选择的各组目标接收者相关联，所述目标接收者基于针对该活动主题的各个接收方属性集合的映射以及指定的营销活动范围的活动参数 。 对于每个目标收件人，组成包含与与目标接收者相关联的活动主题匹配的一个或多个内容的相应集合的相应营销项目。

公开(公告)号：US20060062454A1

公开(公告)日：2006-03-23

申请号：US10948822

申请日：2004-09-23

申请人： Jian Fan ,  Hui Chao ,  Luca Chiarabini

发明人： Jian Fan ,  Hui Chao ,  Luca Chiarabini

IPC分类号： G06K9/34 ,  G06K9/00

CPC分类号： G06K9/38 ,  G06K9/342 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/20012 ,  G06T2207/20101

摘要： Methods, machines, and computer-readable media storing machine-readable instructions for segmenting pixels in an image are described. In one aspect, a region of background pixels is identified in the image. At least some of the background pixels in the region are located on a boundary spatially delimiting the region. One or more orientation-dependent adaptive thresholds are determined for one or more respective candidate growth directions from a given background pixel located on the region boundary. Color distances between the given background pixel and candidate pixels in a neighborhood of the given background pixel are determined. The region is grown based on application of the one or more orientation-dependent adaptive thresholds to the determined color distances.

公开(公告)号：US06983084B2

公开(公告)日：2006-01-03

申请号：US10231415

申请日：2002-08-28

申请人： Hui Chao ,  Dan S. Bloomberg

发明人： Hui Chao ,  Dan S. Bloomberg

IPC分类号： G06K9/32

CPC分类号： G06K9/3283

摘要： A method of aligning a first page image and a second page image is disclosed. The first page image and the second page image are deskewed. Then, the first page image and the second page image are vertically aligned. In particular, a first vertical data set comprising a plurality of first values each first value based on a horizontal scanline of the first page image is generated. Moreover, a second vertical data set comprising a plurality of second values each second value based on a horizontal scanline of the second page image is generated. One of the first and second vertical data sets is dilated. Then, the first and second vertical data sets are cross-correlated to generate cross-correlation data. A maximum value of the cross-correlation data is determined, whereas the maximum value indicates vertical alignment between the first and second page images. Finally, the first and second page images are horizontally aligned.

公开(公告)号：US20050213848A1

公开(公告)日：2005-09-29

申请号：US10809234

申请日：2004-03-25

申请人： Jian Fan ,  Hui Chao

发明人： Jian Fan ,  Hui Chao

IPC分类号： G06T11/60 ,  G06K9/00 ,  G06K1/00

CPC分类号： G06T11/60

摘要： Systems and methods according to the present invention provide techniques to automatically insert an object from one image into a region of another image. The systems and methods require little or no user interaction to allow efficient re-use and updating of existing images, presentations, documents and the like. An object and a container region are identified. Feasible placement location(s) within the container region for the object, as well as an associated scale factor, are determined. If multiple feasible placement locations are identified for a particular scale factor, then one is selected based upon predetermined criteria. The object can then be inserted into the container region and the resulting composite image stored or, alternatively, parameters can be stored which enable object insertion at a subsequent processing step.

摘要翻译： 根据本发明的系统和方法提供了将对象从一个图像自动插入到另一个图像的区域中的技术。 系统和方法需要很少或没有用户交互以允许有效地重新使用和更新现有图像，演示文稿，文档等。 识别对象和容器区域。 确定对象的容器区域内的可行放置位置以及相关的比例因子。 如果针对特定的比例因子识别出多个可行的放置位置，则基于预定标准来选择一个。 然后可以将对象插入到容器区域中，并且可以存储所生成的合成图像，或者可以存储参数，以在随后的处理步骤中使对象插入。