公开(公告)号：US20140232862A1

公开(公告)日：2014-08-21

申请号：US13773097

申请日：2013-02-21

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

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

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/00771 ,  G06K9/6249

摘要： A method and system for detecting anomalies in video footage. A training dictionary can be configured to include a number of event classes, wherein events among the event classes can be defined with respect to n-diminensional feature vectors. One or more nonlinear kernel function can be defined, which transform the n-dimensional feature vectors into a higher dimensional feature space. One or more test events can then be received within an input video sequence of the video footage. Thereafter, a determination can be made if the test event(s) is anomalous by applying a sparse reconstruction with respect to the training dictionary in the higher dimensional feature space induced by the nonlinear kernel function.

摘要翻译： 一种用于检测视频画面异常的方法和系统。 训练词典可以被配置为包括多个事件类，其中事件类中的事件可以相对于n维特征向量来定义。 可以定义一个或多个非线性内核函数，其将n维特征向量变换成更高维度的特征空间。 然后可以在视频录像的输入视频序列内接收一个或多个测试事件。 此后，如果通过对由非线性内核函数引起的较高维特征空间中的训练词典应用稀疏重建来测试事件是异常的，则可以进行确定。

公开(公告)号：US08792682B2

公开(公告)日：2014-07-29

申请号：US13091371

申请日：2011-04-21

申请人： Zhigang Fan ,  Vladimir Kozitsky ,  Aaron M. Burry

发明人： Zhigang Fan ,  Vladimir Kozitsky ,  Aaron M. Burry

IPC分类号： G06K9/00

CPC分类号： G06K9/3258 ,  G06K9/50 ,  G06K2209/01 ,  G06K2209/15

摘要： A license plate localization method and system based on a combination of a top-down texture analysis and a bottom-up connected component. An image with respect to a vehicle captured by an image capturing unit can be processed in order to locate and binarize a busy area. A black run with respect to the binarized image can be analyzed and classified and one or more objects (connected components) can be generated based on the black run classification. The objects can be further classified in accordance with their size utilizing a run-length based filter to filter out a non-text object. The leftover objects can then be spatially clustered and the uniformity and linearity of the clustered objects can be examined based on a linearity test. The clustered objects can be rejected if they fail the linearity test and the detected objects can further be matched with a plate edge characteristic in order to locate a license plate.

摘要翻译： 基于自顶向下纹理分析和自下而上连接的组件的组合的牌照定位方法和系统。 可以处理由图像捕获单元捕获的相对于车辆的图像，以便定位和二值化繁忙区域。 可以分析和分类关于二值化图像的黑色运行，并且可以基于黑色运行分类来生成一个或多个对象（连接的组件）。 可以使用基于跑步长度的过滤器根据其大小进一步分类对象以过滤非文本对象。 然后剩下的对象可以在空间上聚集，并且可以基于线性测试来检查聚类对象的均匀性和线性。 如果聚集的对象如果线性度测试失败，并且检测到的对象可以进一步与板边缘特性相匹配，以便定位车牌。

公开(公告)号：US08744132B2

公开(公告)日：2014-06-03

申请号：US13461266

申请日：2012-05-01

申请人： Orhan Bulan ,  Edgar A. Bernal ,  Robert P. Loce ,  Yao Rong Wang ,  Zhigang Fan

发明人： Orhan Bulan ,  Edgar A. Bernal ,  Robert P. Loce ,  Yao Rong Wang ,  Zhigang Fan

IPC分类号： G06K9/00 ,  G08G1/16

CPC分类号： G06K9/00771

摘要： A method and a system for determining a parking boundary violation includes receiving video data from a sequence of frames taken from an image capture device monitoring a parking area including at least a single parking space. A boundary is determined for defining at least one parking space in the parking area. A vehicle is detected in the parking area. A determination is made whether the detected vehicle is violating a parking regulation based on a position and size of the vehicle within the boundary.

摘要翻译： 用于确定停车边界违规的方法和系统包括从监视包括至少一个停车位的停车区域的图像捕获设备接收的帧序列中接收视频数据。 确定用于在停车区域中定义至少一个停车位的边界。 在停车区域内检测到车辆。 基于边界内的车辆的位置和大小来确定检测到的车辆是否违反停车规则。

公开(公告)号：US08699103B2

公开(公告)日：2014-04-15

申请号：US11170946

申请日：2005-06-30

申请人： Lalit K. Mestha ,  Yao Rong Wang ,  Zhigang Fan

发明人： Lalit K. Mestha ,  Yao Rong Wang ,  Zhigang Fan

IPC分类号： H04N1/60

CPC分类号： H04N1/6022 ,  H04N1/6041 ,  H04N1/62 ,  H04N1/628

摘要： The present disclosure is directed to a system and method to render spatially uniform memory colors when images printed with CMYK primaries are not rendered uniformly due to output device quality errors. The disclosed method uses an array of sensors to scan a test image. Colors of interest are printed at the desired location first and then adjusted (iterated) to achieve a desired output quality. Iterations are carried out on the image on desired memory colors at the spatial resolution available in the measurement system. Colors of pixels are modified based on position where the pixels will be rendered, thereby compensating for any position/process related differences. Also disclosed is a process for incorporating modified memory colors before rendering, and the extension of memory color concepts to adjust colors for the uniform blocks (not edges), with uniformity defined by user definable thresholds.

摘要翻译： 本公开涉及一种用于在由CMYK原色打印的图像由于输出设备质量错误而不均匀地呈现空间均匀的存储器颜色的系统和方法。 所公开的方法使用传感器阵列来扫描测试图像。 感兴趣的颜色首先打印在所需位置，然后进行调整（迭代）以获得所需的输出质量。 在测量系统中可用的空间分辨率下，对所需存储器颜色的图像进行迭代。 基于像素将被渲染的位置修改像素的颜色，从而补偿任何位置/过程相关差异。 还公开了一种用于在渲染之前并入改进的存储器颜色的过程，以及扩展存储器颜色概念以调整用于统一块（而不是边缘）的颜色，具有由用户可定义阈值定义的均匀性。

公开(公告)号：US08681387B2

公开(公告)日：2014-03-25

申请号：US12958819

申请日：2010-12-02

申请人： Martin S. Maltz ,  Zhigang Fan ,  Reiner Eschbach ,  Judith Stinehour

发明人： Martin S. Maltz ,  Zhigang Fan ,  Reiner Eschbach ,  Judith Stinehour

IPC分类号： H04N1/32

CPC分类号： H04N1/0044 ,  H04N1/00883

摘要： A method and system for creating guilloché base pattern with two-dimensional periodicity in a plurality of replicate patterns is shown wherein the creating can be assessed in real-time for pattern acceptability by a user. A base pattern is set on an imaging device in vector space relative to a set of predetermined pattern nodes. The base pattern is modulated via a user interface by adjusting positions of the pattern known for selectively controlling curve shapes of the pattern. A guilloché mark is illustrated by display on the imaging device of the adjusted base pattern and a compilation of associated replicate patterns for user assessment of the mark.

摘要翻译： 示出了用于在多个重复图案中创建具有二维周期性的illo形基底图案的方法和系统，其中可以实时地评估创建以便用户的图案可接受性。 在相对于一组预定图案节点的向量空间中的成像装置上设置基本图案。 通过调整已知的用于选择性地控制图案的曲线形状的图案的位置，经由用户界面调制基本图案。 通过在成像装置上显示调整后的基本图案和用于用户评估标记的相关联的重复图案的汇编来说明illo迹标记。

公开(公告)号：US20140022603A1

公开(公告)日：2014-01-23

申请号：US13553338

申请日：2012-07-19

申请人： Reiner Eschbach ,  Zhigang Fan ,  Martin E. Hoover

发明人： Reiner Eschbach ,  Zhigang Fan ,  Martin E. Hoover

IPC分类号： G06K15/02

CPC分类号： G06T1/0028 ,  G06T2201/0051 ,  H04N1/32261 ,  H04N1/32309 ,  H04N1/32331 ,  H04N1/32352 ,  H04N2201/327

摘要： An image watermarking method includes a color transform on RGB image data to derive CMYK image data that define a constant K image. Variable infrared (IR) mark data defining an IR mark are received and a sparse two-dimensional pattern of black pixels is defined that corresponds to the variable IR data, e.g., using Gold codes or pseudorandom binary sequences. A watermarked black separation K″ is defined by embedding the sparse two-dimensional pattern into the constant K black separation K′ while maintaining local average levels. A watermarked image includes the watermarked black separation K″ in combination with the CMY separations of the constant K image. A decoding process includes using an IR microscope fitted with IR LEDs and an IR pass filter to capture an IR image, which is subjected to exposure correction, thresholding, and dilation operations to extract the two-dimensional pattern for subsequent correlation processing.

摘要翻译： 图像水印方法包括对RGB图像数据进行颜色变换以导出定义常数K图像的CMYK图像数据。 接收定义IR标记的可变红外（IR）标记数据，并且例如使用Gold码或伪随机二进制序列来定义对应于可变IR数据的稀疏二维图案的黑色像素。 通过将稀疏二维图案嵌入到常数K黑色分离K'中同时保持局部平均水平来定义水印黑色分离K“。 水印图像包括与常数K图像的CMY分离相结合的水印黑色分离K“。 解码过程包括使用装有IR LED的IR显微镜和IR通过滤光片来捕获经过曝光校正，阈值和扩张操作的IR图像，以提取二维图案用于随后的相关处理。

公开(公告)号：US08619340B2

公开(公告)日：2013-12-31

申请号：US12915249

申请日：2010-10-29

申请人： Zhigang Fan ,  Michael R. Campanelli

发明人： Zhigang Fan ,  Michael R. Campanelli

IPC分类号： H04N1/40

CPC分类号： G06K9/3208 ,  G06K2209/01

摘要： What is disclosed is a novel system and method for augmenting present methods used for determining the orientation direction automatically being detected of digital pages of a plurality of scanned documents in a digital document processing environment. The present method takes advantage of the observation that pages scanned in data processing centers are often highly correlated. The present method contains five primary steps. 1) Page orientation (i.e., up/down) is detected using a traditional method. 2) Each page is classified as either directional or non-directional. 3) The pages classified as directional are clustered into groups. 4) The direction for each group is determined. 5) The directional group's direction is used to revise the orientation for pages contained in the group. Through the implementation of the teachings hereof, performance, in terms of both speed and accuracy, are very high relative to current methods and detection error rates can be reduced significantly.

摘要翻译： 所公开的是一种新颖的系统和方法，用于增加用于确定在数字文档处理环境中自动检测到多个扫描文档的数字页面的取向方向的现有方法。 本方法利用观察结果，数据处理中心扫描的页面通常是高度相关的。 本方法包含五个主要步骤。 1）使用传统方法检测页面方向（即，上/下）。 2）每个页面被分类为定向或非定向。 3）分类为定向的页面被分组。 4）确定每组的方向。 5）定向组的方向用于修改组中包含的页面的方向。 通过实施本文的教导，相对于当前的方法，速度和精度方面的性能都非常高，检测错误率可以显着降低。

公开(公告)号：US08619074B2

公开(公告)日：2013-12-31

申请号：US12964820

申请日：2010-12-10

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

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

IPC分类号： G06T15/00

CPC分类号： G06T11/60 ,  G06T15/04 ,  G06T19/00

摘要： As set forth herein, a computer-implemented method facilitates replacing text on cylindrical or curved surfaces in images. For instance, the user is first asked to perform a multi-click selection of a polygon to bound the text. A triangulation scheme is carried out to identify the pixels. Segmentation and erasing algorithms are then applied. The ellipses are estimated accurately through constrained least squares fitting. A 3D framework for rendering the text, including the central projection pinhole camera model and specification of the cylindrical object, is generated. These parameters are jointly estimated from the fitted ellipses as well as the two vertical edges of the cylinder. The personalized text is wrapped around the cylinder and subsequently rendered.

摘要翻译： 如本文所述，计算机实现的方法有助于在图像中的圆柱形或弯曲表面上替换文本。 例如，首先要求用户执行多边形的多点选择以绑定文本。 进行三角测量方案来识别像素。 然后应用分割和擦除算法。 通过约束最小二乘拟合精确估计椭圆。 生成用于呈现文本的3D框架，包括中心投影针孔相机模型和圆柱形对象的规格。 这些参数是从安装的椭圆以及气缸的两个垂直边缘共同估计的。 个性化文字包裹在圆柱体上并随后呈现。

公开(公告)号：US20130294652A1

公开(公告)日：2013-11-07

申请号：US13464357

申请日：2012-05-04

申请人： Zhigang Fan ,  Yonghui Zhao ,  Aaron Michael Burry ,  Vladimir Kozitsky

发明人： Zhigang Fan ,  Yonghui Zhao ,  Aaron Michael Burry ,  Vladimir Kozitsky

IPC分类号： G06K9/62

CPC分类号： G06K9/3258 ,  G06K2209/15

摘要： A method determines a license plate layout configuration. The method includes generating at least one model representing a license plate layout configuration. The generating includes segmenting training images each defining a license plate to extract characters and logos from the training images. The segmenting includes calculating values corresponding to parameters of the license plate and features of the characters and logos. The segmenting includes estimating a likelihood function specified by the features using the values. The likelihood function measures deviations between an observed plate and the model. The method includes storing a layout structure and the distributions for each of the at least one model. The method includes receiving as input an observed image including a plate region. The method includes segmenting the plate region and determining a license plate layout configuration of the observed plate by comparing the segmented plate region to the at least one model.

公开(公告)号：US20130228630A1

公开(公告)日：2013-09-05

申请号：US13552177

申请日：2012-07-18

申请人： Zhigang Fan ,  Yonghui Zhao ,  Hengzhou Ding

发明人： Zhigang Fan ,  Yonghui Zhao ,  Hengzhou Ding

IPC分类号： G06K19/06

CPC分类号： G06K19/06103

摘要： A method and apparatus are disclosed for embedding a two-dimensional machine-readable code into the background of a document in an aesthetically pleasing manner. The objects (picture, graphics, text, etc.) in a document image are first segmented from the background. A location for embedding the barcode is determined. A texture image is created by replicating the barcode to a size that covers the entire image. A modulation index map is generated from the segmentation results. The original image is modulated to produce the output image based on the texture image and the modulation index map.

摘要翻译： 公开了一种用于以美观的方式将二维机器可读代码嵌入到文档的背景中的方法和装置。 文档图像中的对象（图片，图形，文本等）首先从背景分割。 确定嵌入条形码的位置。 通过将条形码复制到覆盖整个图像的大小来创建纹理图像。 从分割结果生成调制索引图。 原始图像被调制以基于纹理图像和调制索引图生成输出图像。