公开(公告)号：US20040258272A1

公开(公告)日：2004-12-23

申请号：US10600139

申请日：2003-06-20

Applicant: Xerox Corporation

Inventor： Zhigang Fan

IPC: G06K009/00

CPC classification number: G06T1/0021 ,  G06T2201/0051

Abstract: A new information embedding technology is disclosed using conjugate screen concept. More specifically, two screens are applied in a halftoning process, one for the areas that corresponds to the symbol to be embedded (object), and one for the background. Both screens can be conceptually decomposed into a two-layer structure similar to supercells. The top layer determines the overall halftone texture, while the bottom layer, which is conjugate for background and object, carries embedded data. The information can be retrieved digitally or optically. In embedding, there is no restriction of the symbol sizes. The computation is relatively simple and can be implemented in real time. In retrieval, it is relatively robust to registration errors.

Abstract translation: 使用共轭屏幕概念公开了一种新的信息嵌入技术。 更具体地说，在半色调处理中应用两个屏幕，一个用于与要嵌入的符号对应的区域（对象），一个用于背景。 两个屏幕可以在概念上分解成类似于超级单元的两层结构。 顶层确定整体半色调纹理，而底层（用于背景和对象）是共轭的，它携带嵌入数据。 信息可以数字或光学检索。 在嵌入中，没有限制符号大小。 计算相对简单，可以实时实现。 在检索中，注册错误相对较强。

公开(公告)号：US20030128396A1

公开(公告)日：2003-07-10

申请号：US10040693

申请日：2002-01-07

Applicant: XEROX CORPORATION

Inventor： Zhigang Fan

IPC: H04N001/407 ,  G06K015/00 ,  H04N001/40

CPC classification number: G06K9/00456 ,  H04N1/40062

Abstract: A method and system for classifying images between natural pictures and synthetic graphics is provided. In embodiments of the invention, a picture/graphic classification method and system implements edge features for image classification of natural pictures and synthetic graphics. In another embodiment of the invention, a picture/graphic combination classification method and system using edge features, color discreteness features, and SGLD texture features is used to classify images between natural picture and synthetic graphic classes

Abstract translation: 提供了一种在自然图片和合成图形之间分类图像的方法和系统。 在本发明的实施例中，图片/图形分类方法和系统实现用于自然图片和合成图形的图像分类的边缘特征。 在本发明的另一个实施例中，使用图像/图形组合分类方法和使用边缘特征，颜色离散特征和SGLD纹理特征的系统来对自然图像和合成图形类别之间的图像进行分类

公开(公告)号：US20020031268A1

公开(公告)日：2002-03-14

申请号：US09965922

申请日：2001-09-28

Applicant: XEROX CORPORATION

Inventor： Salil Prabhakar ,  Hui Cheng ,  Zhigang Fan ,  John C. Handley ,  Ying-Wei Lin

IPC: G06K009/62

CPC classification number: G06K9/00456

Abstract: A method and system for image processing, in conjunction with classification of images between natural pictures and synthetic graphics, using SGLD texture (e.g., variance, bias, skewness, and fitness), color discreteness (e.g., R_L, R_U, and R_V normalized histograms), or edge features (e.g., pixels per detected edge, horizontal edges, and vertical edges) is provided. In another embodiment, a picture/graphics classifier using combinations of SGLD texture, color discreteness, and edge features is provided. In still another embodiment, a nullsoftnull image classifier using combinations of two (2) or more SGLD texture, color discreteness, and edge features is provided. The nullsoftnull classifier uses image features to classify areas of an input image in picture, graphics, or fuzzy classes.

Abstract translation: 一种用于图像处理的方法和系统，结合使用SGLD纹理（例如，方差，偏差，偏度和适应度）的自然图像和合成图像之间的图像分类，颜色离散性（例如，R_L，R_U和R_V归一化直方图 ）或边缘特征（例如，每个检测到的边缘的像素，水平边缘和垂直边缘）。 在另一个实施例中，提供了使用SGLD纹理，颜色离散性和边缘特征的组合的图片/图形分类器。 在另一个实施例中，提供了使用两（2）或更多SGLD纹理，颜色离散性和边缘特征的组合的“软”图像分类器。 “软”分类器使用图像特征来对图像，图形或模糊类中的输入图像的区域进行分类。

公开(公告)号：US20040114186A1

公开(公告)日：2004-06-17

申请号：US10321968

申请日：2002-12-17

Applicant: Xerox Corporation

Inventor： Zhigang Fan

IPC: H04N001/405 ,  G06K009/56

CPC classification number: H04N1/40062 ,  H04N1/405

Abstract: A method for selecting a halftoning mode to be applied to regions within an image. The method operates on received image data to identify low-level regions within the received image data. The low-level regions are defined and separated by edges. Pixels that are not separated by edges are considered to belong to the same region. After the regions have been identified, low-level image attributes for the image data within each region are compiled. A halftoning method suited for the image data within the region can be selected based upon low-level image attributes.

Abstract translation: 一种用于选择要应用于图像内的区域的半色调模式的方法。 该方法对接收到的图像数据进行操作以识别接收到的图像数据内的低级区域。 低级区域由边界定义和分隔。 不被边缘分隔的像素被认为属于同一区域。 在区域被识别之后，编译每个区域内的图像数据的低级图像属性。 可以基于低级图像属性来选择适合于该区域内的图像数据的半色调方法。

公开(公告)号：US20030081256A1

公开(公告)日：2003-05-01

申请号：US10020676

申请日：2001-10-30

Applicant: Xerox Corporation

Inventor： Shen-Ge Wang ,  Zhigang Fan

IPC: H04N001/405 ,  G06K015/00

CPC classification number: H04N1/4058

Abstract: A method of constructing a halftone screen includes selecting a frequency and screen angle of interest. A subcell having spatial vectors which satisfy the selected frequency and screen angle of interest is identified. A supercell comprising an array of the subcells is formed. An integer relationship potentially having numerous solutions exists between the supercell and the subcell. The integer relationship is solved for values of the integers and then tested against the values for the subcell spatial vectors. Although the solution may in some cases be the null set, in many cases there will be numerous solutions. Each resulting solution, if any, is then tested according to any additional constraints or tolerances specified for the particular halftone screen. If any of the resulting supercell solutions satisfies the tests, that supercell may be used to create a halftone screen.

Abstract translation: 构建半色调网屏的方法包括选择频率和屏幕感兴趣的角度。 识别具有满足所选择的频率和屏幕感兴趣角度的空间矢量的子小区。 形成包括子电池阵列的超电池。 在超级单元和子单元之间存在潜在地具有许多解决方案的整数关系。 针对整数的值求解整数关系，然后根据子单元空间向量的值进行测试。 尽管解决方案在某些情况下可能是空集，但在许多情况下，将有许多解决方案。 然后根据为特定半色调屏幕指定的任何附加约束或公差测试每个产生的解决方案（如果有的话）。 如果所得到的超细胞溶液中的任何一种满足测试，则该超级细胞可用于产生半色调筛选。

公开(公告)号：US20020110283A1

公开(公告)日：2002-08-15

申请号：US09737513

申请日：2000-12-15

Applicant: XEROX CORPORATION

Inventor： Zhigang Fan ,  Thyagarajan Balasubramanian

IPC: G06K009/00 ,  G06K009/62 ,  G06K009/40

CPC classification number: G06K9/00456 ,  G06T7/44

Abstract: A document processing system and a method for classifying an input image or region thereof as either a synthetic graphic or a natural picture, is disclosed. The system includes an image input subsystem, a processing subsystem for processing image data provided by the image input subsystem, and software/firmware means operative on the processing subsystem for a) low-pass filtering image data representative of the input image or region thereof to produce low-pass filtered pixel values; b) determining a smoothness value for each of a plurality of low-pass filtered pixel values; c) generating histogram data from the smoothness values; d) determining a texture metric for the input image or region thereof from a subset of the histogram data; and e) thresholding the texture metric to classify the input image as either a synthetic graphic or a natural picture.

Abstract translation: 公开了将输入图像或其区域分类为合成图形或自然图像的文档处理系统和方法。 该系统包括图像输入子系统，用于处理由图像输入子系统提供的图像数据的处理子系统，以及在处理子系统上操作的软件/固件装置，用于a）表示输入图像或其区域的低通滤波图像数据 产生低通滤波像素值; b）确定多个低通滤波像素值中的每一个的平滑度值; c）从平滑度值生成直方图数据; d）从直方图数据的子集确定输入图像或其区域的纹理度量; 以及e）阈值纹理度量以将输入图像分类为合成图形或自然图像。

公开(公告)号：US20020093686A1

公开(公告)日：2002-07-18

申请号：US09731131

申请日：2000-12-06

Applicant: XEROX CORPORATION

Inventor： Zhigang Fan ,  Ying-Wei Lin ,  Hong Li

IPC: H04N001/405 ,  G06K015/00 ,  G06T005/00

CPC classification number: H04N1/40075

Abstract: An adaptive filtering method and apparatus for descreening a scanned halftoned image representation is disclosed. The apparatus includes an image input subsystem; a processing subsystem for processing halftoned image data provided by the image input subsystem; and software/firmware means operative on the processing subsystem for a) low-pass filtering a halftoned input pixel value provided by the image input subsystem to produce a low-pass filtered pixel value; b) notch-filtering the halftoned input pixel value to produce a notch-filtered pixel value; c) determining a local contrast value for the halftoned input pixel value; and d) producing a descreened output pixel value based on the low-pass filtered pixel value, the notch-filtered pixel value, or a combination of the low-pass filtered pixel value and the notch-filtered pixel value depending on the local contrast value.

Abstract translation: 公开了一种用于对已扫描的半色调图像表示进行去网的自适应滤波方法和装置。 该装置包括图像输入子系统; 用于处理由图像输入子系统提供的半色调图像数据的处理子系统; 以及在所述处理子系统上操作的软件/固件，用于a）对由所述图像输入子系统提供的半色调输入像素值进行低通滤波以产生低通滤波像素值; b）对所述半色调输入像素值进行陷波滤波以产生陷波经滤波的像素值; c）确定半色调输入像素值的局部对比度值; 以及d）基于所述低通滤波像素值，所述陷波经滤波的像素值或者根据所述局部对比度值的所述低通滤波像素值和所述陷波经滤波的像素值的组合来产生去网输出像素值 。

公开(公告)号：US20040013317A1

公开(公告)日：2004-01-22

申请号：US10200238

申请日：2002-07-22

Applicant: XEROX CORPORATION

Inventor： Reiner Eschbach ,  Zhigang Fan

IPC: G06K009/68

CPC classification number: G06K9/6202 ,  Y10S707/99931

Abstract: An image finder method and apparatus are provided for identifying a source image data file in a database based upon a printed image actually generated from a source image data file in the database. Input image data that represent a printed input image are received from a scanner. Source image data are received from the database that is defined by a plurality of different source image data files stored on a CD-ROM or other storage medium. Correlation operations are carried out to identify any source image data files that are highly correlated with the input image data. The results of the correlation operations are used to identify the source image data file from which the input printed image was actually generated or, if this is not possible, to identify more than one source image data file that could be the source image data file from which the printed input image was actually generated. Both the input image data and source image data are severely subsampled to obtain no more than about 1000 (and most preferably no more than 200) data values from each set of data for use in the correlation operation to provide for extremely fast processing without loss of accuracy.

Abstract translation: 提供了一种图像取景器方法和装置，用于基于从数据库中的源图像数据文件实际生成的打印图像来识别数据库中的源图像数据文件。 从扫描仪接收输入表示打印输入图像的图像数据。 从数据库接收源图像数据，其由存储在CD-ROM或其他存储介质上的多个不同的源图像数据文件定义。 执行相关操作以识别与输入图像数据高度相关的任何源图像数据文件。 相关操作的结果用于识别实际生成输入打印图像的源图像数据文件，或者如果不可能，则识别可以是源图像数据文件的多于一个源图像数据文件， 打印的输入图像实际上被生成。 输入图像数据和源图像数据都被严重二次采样，以从相关运算中使用的每组数据获得不超过约1000个（最优选不超过200个）的数据值，以提供非常快速的处理，而不会损失 准确性。

公开(公告)号：US20030223099A1

公开(公告)日：2003-12-04

申请号：US10158027

申请日：2002-05-29

Applicant: Xerox Corporation

Inventor： Zhigang Fan ,  Hui Cheng ,  Robert J. Rolleston

IPC: G06K009/00 ,  H04N001/46

CPC classification number: G06T1/0071 ,  G06T2201/0051 ,  G06T2201/0061 ,  G11B20/00086 ,  H04N1/00005 ,  H04N1/00037 ,  H04N1/32144 ,  H04N1/32213 ,  H04N1/32251 ,  H04N1/32267 ,  H04N1/32288 ,  H04N1/32299 ,  H04N1/32304 ,  H04N1/32309 ,  H04N2201/3242 ,  H04N2201/328

Abstract: A method of editing a digital image having associated embedded data, such as printing hints, includes embedding a first watermark in the original image before the image is edited. The first watermarking scheme associates first watermark information with each pixel and is used to detect which pixels have been edited. A second watermark may be embedded in the original image according to a second watermarking scheme which associates second watermark information with non-overlapping groups of pixels in the original image. The second watermark information may be used to synchronize the first watermark information and to detect editing information which does not change pixel values. After editing, only those edited portions of the image need have their embedded data reapplied.

Abstract translation: 编辑具有相关联的嵌入数据（诸如打印提示）的数字图像的方法包括在图像编辑之前在原始图像中嵌入第一水印。 第一水印方案将第一水印信息与每个像素相关联，并用于检测哪些像素已被编辑。 第二水印可以根据将第二水印信息与原始图像中的非重叠像素组相关联的第二水印方案嵌入到原始图像中。 第二水印信息可以用于同步第一水印信息并且检测不改变像素值的编辑信息。 编辑后，只有图像的编辑部分需要重新应用其嵌入的数据。

公开(公告)号：US20030133160A1

公开(公告)日：2003-07-17

申请号：US10044468

申请日：2002-01-11

Applicant: XEROX CORPORATION

Inventor： Gaurav Sharma ,  Shen-Ge Wang ,  Zhigang Fan

IPC: H04N001/405 ,  G06K015/00

CPC classification number: G06K15/107 ,  H04N1/4053

Abstract: A system and method for halftoning for multi-pass rendering of an image in which different pixel locations are rendered in each pass which reduces the effects of inter-pass mis-registration errors. The method of halftoning includes restricting a substantial majority of the pixels turned on to render a tone to the minimum number of passes required to produce the tone. The halftoning method can include generating a stochastic halftone turn-on sequence and re-ordering the turn-on sequence. The halftoning method can also use error diffusion, adding a zero mean bias signal to either the image input pixels or the threshold values. The halftoning method is applicable to color or black and white rendering.

Abstract translation: 用于半色调的系统和方法，用于在每次通过中渲染不同像素位置的图像的多遍渲染，其减少了通过间错误注册错误的影响。 半色调的方法包括将打开的大部分像素限制为产生音调所需的最小通过次数。 半色调方法可以包括产生随机半色调开启序列并重新排序开启序列。 半色调方法还可以使用误差扩散，向图像输入像素或阈值添加零平均偏置信号。 半色调方法适用于彩色或黑白渲染。