公开(公告)号：US20050281459A1

公开(公告)日：2005-12-22

申请号：US10871114

申请日：2004-06-18

申请人： Raja Bala ,  Judith Stinehour ,  Gaurav Sharma

发明人： Raja Bala ,  Judith Stinehour ,  Gaurav Sharma

IPC分类号： G06F15/00 ,  G06K9/00 ,  H04N1/407 ,  H04N1/60

CPC分类号： H04N1/4078 ,  H04N1/6022

摘要： The present invention is directed to a method and apparatus for the improved characterization of an image scanner or similar image input terminal so as to enable the device to be employed in the measurement and analysis of color images. The invention uses a family of input device characterization targets, each varying in primary colorants and at a fixed level of black (K) colorant. A corresponding family of input device characterizations is derived, one for each level of K, and the final transformation is prepared such that the characterization includes K as an additional input—thereby improving the characterization and accuracy of the input device.

摘要翻译： 本发明涉及一种用于改进图像扫描仪或类似图像输入端子的表征的方法和装置，以便能够将该装置用于彩色图像的测量和分析。 本发明使用一系列输入设备表征目标，每个变色原色和在黑（K）着色剂的固定水平。 导出相应的输入设备特性系列，每个级别为K一个，并且准备最终变换，使得表征包括K作为附加输入，从而改善输入设备的表征和精度。

公开(公告)号：US20050036171A1

公开(公告)日：2005-02-17

申请号：US10641205

申请日：2003-08-14

申请人： Raja Bala ,  Gaurav Sharma ,  Robert Rolleston

发明人： Raja Bala ,  Gaurav Sharma ,  Robert Rolleston

IPC分类号： H04N1/50 ,  H04N1/56 ,  H04N1/60

CPC分类号： H04N1/603 ,  H04N1/6058

摘要： The system for selecting a best device for rendering a color document involves first determining the types of color data included in the color document to be printed. Once the type of color data has been determined, the color characteristics are matched against the strengths of the available output devices to obtain a list of devices best suited for this particular color print job. At least one device from the list of best devices is selected and the color document is rendered onto the selected device. Preferably, the types of color data involved are determined by the mix of defined colorimetry and undefined colorimetry in the color document. Alternatively, the types of color data are determined by analyzing the colorspaces in the document (i.e., RGB, CMYK, LAB, XYZ, etc.), and the embedded profiles, if any, in the document (e.g., sRGB, SWOPCMYK, Euroscale). In the instance wherein a number of devices match the criteria for selection, only those devices which honor embedded color profiles are selected for documents containing embedded profiles. Alternatively, only those devices are selected that produce a consistent rendering across multiple color spaces and profiles for documents with a mix of color spaces and profiles. Selecting the best device may also depend on whether the type of print job is considered to be Job-Balancing or Job-Splitting. With Job-Balancing, at least one of the metrics is used: (i) Intersection Gamut Volume, (ii) Gamut Similarity, or (iii) Mismatch Between Document Colors and Intersection Gamut for device selection. With Job-Splitting, at least one of these metrics are used: (i) Individual Gamut Volume, or (ii) Mismatch Between Document Colors and Device Gamut. Colorimetric definition of the selected colors can be retrieved from either an embedded source profile or by default and mapping the colors to the output gamut.

公开(公告)号：US07355752B2

公开(公告)日：2008-04-08

申请号：US10465408

申请日：2003-06-18

申请人： Gaurav Sharma ,  Raja Bala ,  Jean-Pierre R. N. Van de Capelle ,  Martin S. Maltz ,  Lalit K. Mestha

发明人： Gaurav Sharma ,  Raja Bala ,  Jean-Pierre R. N. Van de Capelle ,  Martin S. Maltz ,  Lalit K. Mestha

IPC分类号： H04N1/50 ,  H04N1/56

CPC分类号： H04N1/50 ,  G09G5/04 ,  G09G2320/0276 ,  G09G2320/0693 ,  H04N1/603

摘要： A color output device is generally driven by at least three independent control signals for control of its response. A desired response in device independent color space is normally obtained by employing a cascade consisting of a characterization transform and calibration transform. The calibration transform transforms input control variables into output control variables that are directly used to drive the device. Input control variables can be transformed into intermediate control variables, which can be then mapped to output control variables utilizing a two-dimensional transformation. The two-dimensional calibration architecture provides improved control functionality and flexibility.

摘要翻译： 颜色输出装置通常由至少三个独立的控制信号驱动，以控制其响应。 通常通过使用由特征变换和校准变换组成的级联来获得器件独立色彩空间中的期望响应。 校准变换将输入控制变量转换为直接用于驱动器件的输出控制变量。 输入控制变量可以转换为中间控制变量，然后可以使用二维变换将其映射到输出控制变量。 二维校准架构提供了改进的控制功能和灵活性。

公开(公告)号：US20060110031A1

公开(公告)日：2006-05-25

申请号：US10997528

申请日：2004-11-24

申请人： Raja Bala ,  Gaurav Sharma

发明人： Raja Bala ,  Gaurav Sharma

IPC分类号： G06K9/00

CPC分类号： H04N1/603

摘要： A system and method for generating an adjusted profile for a device in response to a specified aim, where the aim may include parameters established in response to a user's specifications, for device emulation, etc.

摘要翻译： 一种用于响应于指定目的产生用于设备的经调整的简档的系统和方法，其中目的可以包括响应于用户的规范而建立的参数，用于设备仿真等。

公开(公告)号：US09798712B2

公开(公告)日：2017-10-24

申请号：US13609541

申请日：2012-09-11

申请人： Beilei Xu ,  Stuart A. Schweid ,  Raja Bala ,  Rinku Gajera

发明人： Beilei Xu ,  Stuart A. Schweid ,  Raja Bala ,  Rinku Gajera

IPC分类号： G06F5/16 ,  G06F17/24 ,  G06F17/28

CPC分类号： G06F17/248 ,  G06F17/289

摘要： The present disclosure provides a method of producing a personalized medical record, comprising: sensing capabilities of a receiving device; retrieving stock information; retrieving personalized information; combining at least a portion of the stock information and at least a portion of the personalized information into the personalized record; formatting the personalized record based on a combination of the capabilities of the receiving device and a user's preference; and, transmitting the formatted personalized record to the device.

公开(公告)号：US09213701B2

公开(公告)日：2015-12-15

申请号：US13094573

申请日：2011-04-26

申请人： Raja Bala ,  Francis K. Tse ,  George Cunha Cardoso ,  Tonya L. Love ,  Fritz F. Ebner ,  Michael R. Furst

发明人： Raja Bala ,  Francis K. Tse ,  George Cunha Cardoso ,  Tonya L. Love ,  Fritz F. Ebner ,  Michael R. Furst

IPC分类号： G06K15/02 ,  G06F17/30

CPC分类号： G06F17/30011

摘要： An embodiment generally relates to systems and methods for electronically auto-filing and retrieving erasable paper document documents configured for ultraviolet (UV) imaging. A device can automatically generate an electronic version of the erasable paper document and store the electronic version in a database. A user can search the database for the electronic version with identification information associated with the erasable paper document, upon which the systems and methods can retrieve the electronic version of the erasable paper document for the user. The electronic version of the erasable paper document can be re-rendered either as a new erasable paper document, for display to the user, or other renderings.

摘要翻译： 一个实施方案通常涉及用于电子自动归档和检索配置用于紫外线（UV）成像的可擦除纸质文件的系统和方法。 设备可以自动生成电子版本的可擦除纸质文档，并将电子版本存储在数据库中。 用户可以在数据库中搜索具有与可擦除纸质文档相关联的识别信息的电子版本，系统和方法可以在其上检索用户的可擦除纸质文档的电子版本。 可擦除纸质文档的电子版可以作为新的可擦除纸张文档重新呈现，以供显示给用户或其他渲染。

公开(公告)号：US09075803B2

公开(公告)日：2015-07-07

申请号：US13094516

申请日：2011-04-26

申请人： George Cunha Cardoso ,  Raja Bala ,  Tonya L. Love ,  Francis K. Tse ,  Fritz F. Ebner ,  Michael R. Furst

发明人： George Cunha Cardoso ,  Raja Bala ,  Tonya L. Love ,  Francis K. Tse ,  Fritz F. Ebner ,  Michael R. Furst

IPC分类号： G06F3/12 ,  G06F17/30 ,  B41J3/407 ,  G03C11/02

CPC分类号： G06F17/30011 ,  B41J3/4076 ,  B41M2205/18 ,  G03C11/02 ,  G06F17/30725

摘要： An embodiment generally relates to systems and methods for electronically auto-filing and retrieving erasable paper document documents configured for ultraviolet (UV) imaging. A device can embed a machine readable code on an erasable paper document, or can detect a machine readable code preprinted on the document. An electronic version of the erasable paper document along with the machine readable code can be stored in a database. When the machine readable code is later detected on a rendered document, the electronic version corresponding to the machine readable code can be retrieved from storage. The erasable paper document can be re-rendered using the retrieved electronic version either as a new erasable paper document, for display to the user, or other renderings.

摘要翻译： 一个实施方案通常涉及用于电子自动归档和检索配置用于紫外线（UV）成像的可擦除纸质文件的系统和方法。 设备可以将机器可读代码嵌入到可擦除的纸质文档上，或者可以检测预先印在文档上的机器可读代码。 可擦写纸文件的电子版本与机器可读代码可以存储在数据库中。 当随后在呈现的文档上检测到机器可读代码时，可以从存储器检索对应于机器可读代码的电子版本。 可以使用检索到的电子版本作为新的可擦除纸质文档来重新呈现可擦除的纸质文档，以供显示给用户或其他渲染。

公开(公告)号：US09042640B2

公开(公告)日：2015-05-26

申请号：US13349751

申请日：2012-01-13

申请人： Raja Bala ,  Zhigang Fan ,  Hengzhou Ding ,  Jan P. Allebach ,  Charles A. Bouman ,  Reuven J. Sherwin

发明人： Raja Bala ,  Zhigang Fan ,  Hengzhou Ding ,  Jan P. Allebach ,  Charles A. Bouman ,  Reuven J. Sherwin

IPC分类号： G06K9/62 ,  G06K9/00 ,  G06K9/32

CPC分类号： G06K9/00671 ,  G06K9/3258

摘要： As set forth herein, a computer-implemented method facilitates pre-analyzing an image and automatically suggesting to the user the most suitable regions within an image for text-based personalization. Image regions that are spatially smooth and regions with existing text (e.g. signage, banners, etc.) are primary candidates for personalization. This gives rise to two sets of corresponding algorithms: one for identifying smooth areas, and one for locating text regions. Smooth regions are found by dividing the image into blocks and applying an iterative combining strategy, and those regions satisfying certain spatial properties (e.g. size, position, shape of the boundary) are retained as promising candidates. In one embodiment, connected component analysis is performed on the image for locating text regions. Finally, based on the smooth and text regions found in the image, several alternative approaches are described herein to derive an overall metric for “suitability for personalization.”

摘要翻译： 如本文所述，计算机实现的方法有助于预分析图像并且自动地向用户建议图像内的最合适的区域用于基于文本的个性化。 具有空间平滑的图像区域和具有现有文本的区域（例如标牌，横幅等）是用于个性化的主要候选者。 这产生了两组相应的算法：一种用于识别平滑区域，一种用于定位文本区域。 通过将图像划分成块并应用迭代组合策略来找到平滑区域，并且满足某些空间属性（例如，边界的大小，位置，形状）的那些区域被保留为有希望的候选者。 在一个实施例中，对用于定位文本区域的图像执行连接分量分析。 最后，基于图像中发现的平滑和文本区域，本文描述了几种替代方法，以得出“适合个性化”的总体度量。

公开(公告)号：US20130330004A1

公开(公告)日：2013-12-12

申请号：US13494173

申请日：2012-06-12

申请人： Raja Bala ,  Zhigang Fan ,  Hengzhou Ding ,  Jan P. Allebach ,  Charles A. Bouman

发明人： Raja Bala ,  Zhigang Fan ,  Hengzhou Ding ,  Jan P. Allebach ,  Charles A. Bouman

IPC分类号： G06K9/18 ,  G06K9/34

CPC分类号： G06K9/4604 ,  G06K9/3258 ,  G06K9/4638 ,  G06K2209/01 ,  G06T7/13 ,  G06T7/181 ,  G06T2207/10004

摘要： As set forth herein, systems and methods facilitate providing an efficient edge-detection and closed-contour based approach for finding text in natural scenes such as photographic images, digital, and/or electronic images, and the like. Edge information (e.g., edges of structures or objects in the images) is obtained via an edge detection technique. Edges from text characters form closed contours even in the presence of reasonable levels of noise. Closed contour linking and candidate text line formation are two additional features of the described approach. A candidate text line classifier is applied to further screen out false-positive text identifications. Candidate text regions for placement of text in the natural scene of the electronic image are highlighted and presented to a user.

摘要翻译： 如本文所述，系统和方法有助于提供有效的边缘检测和基于闭合轮廓的方法，用于在诸如照相图像，数字和/或电子图像等的自然场景中查找文本。 通过边缘检测技术获得边缘信息（例如，图像中的结构或对象的边缘）。 即使存在合理的噪声水平，文本字符的边缘也会形成封闭的轮廓。 闭合轮廓链接和候选文本线形成是所述方法的两个附加特征。 应用候选文本行分类器进一步筛选出假阳性文本标识。 用于在电子图像的自然场景中放置文本的候选文本区域被突出显示并呈现给用户。

公开(公告)号：US20130286208A1

公开(公告)日：2013-10-31

申请号：US13476239

申请日：2012-05-21

申请人： Raja Bala ,  Zhigang Fan ,  Aaron Burry ,  Vishal Monga ,  Xuan Mo

发明人： Raja Bala ,  Zhigang Fan ,  Aaron Burry ,  Vishal Monga ,  Xuan Mo

IPC分类号： H04N7/18

CPC分类号： G06K9/00771 ,  G06K9/6249 ,  G08G1/0129 ,  H04N7/181

摘要： Methods and systems for automatically detecting multi-object anomalies at a traffic intersection utilizing a joint sparse reconstruction model. A first input video sequence at a first traffic location can be received and at least one normal event involving P moving objects (where P is greater than or equal to 1) can be identified in an offline training phase. The normal event in the first input video sequence can be assigned to at least one normal event class and a training dictionary suitable for joint sparse reconstruction can be built in the offline training phase. A second input video sequence captured at a second traffic location similar to the first traffic location can be received and at least one event involving P moving objects can be identified in an online detection phase.

摘要翻译： 利用联合稀疏重建模型自动检测交通路口多物体异常的方法和系统。 可以在离线训练阶段中识别在第一交通位置处的第一输入视频序列，并且可以在离线训练阶段识别涉及P个运动对象（其中P大于或等于1）的至少一个正常事件。 可以将第一输入视频序列中的正常事件分配给至少一个正常事件类，并且可以在离线训练阶段中构建适合关联稀疏重建的训练字典。 可以接收在类似于第一业务位置的第二业务位置处捕获的第二输入视频序列，并且可以在在线检测阶段中识别涉及P个移动对象的至少一个事件。