公开(公告)号：US20030063803A1

公开(公告)日：2003-04-03

申请号：US09965880

申请日：2001-09-28

Applicant: Xerox Corporation

Inventor： Ying-Wei Lin ,  Stuart A. Schweid ,  Jeng-Nan Shiau ,  Raja Bala ,  Zhigang Fan

IPC: G06K009/00

CPC classification number: H04N1/40062 ,  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：US20020097438A1

公开(公告)日：2002-07-25

申请号：US10046687

申请日：2002-01-16

Applicant: Xerox Corporation

Inventor： Stuart A. Schweid ,  David J. Metcalfe

IPC: H04N001/405 ,  H04N001/409 ,  G06K015/02

CPC classification number: H04N1/4052

Abstract: A system and method for processing image data converts a pixel of image data having a first resolution to a plurality of subpixels, the plurality of subpixels representing a second resolution, the second resolution being higher than the first resolution. The plurality of subpixels are thresholded to generate a group of subpixel values for each pixel and a threshold error value. It is then determined if the group of subpixel values from the thresholding process produce a pattern containing an isolated subpixel. If the group of subpixel values from the thresholding process produce a pattern containing an isolated subpixel, the group of subpixel vales is modified to produce a pattern without an isolated subpixel. The modification process produces a subpixel error value which is compensated for localized error before being diffused to adjacent pixels.

公开(公告)号：US20030128895A1

公开(公告)日：2003-07-10

申请号：US10040810

申请日：2002-01-07

Applicant: XEROX CORPORATION

Inventor： Stuart A. Schweid

IPC: G06K009/36

CPC classification number: G06K9/3283

Abstract: A method of determining image skew in a scanned document includes scanning the image and determining on a pixel-by-pixel basis whether or not pixels are ON or OFF on scan lines and columns along both the fast and slow scan directions for a particular document rotation angle. Through one read of the image, image data is sampled simultaneously at a plurality of predetermined document rotation angles From the sampled data, the second order moment of the number of ON pixels is calculated as a function of document rotation angle for scan lines along both the fast and slow scan directions, yielding two independent skew angle estimates. Skew angle estimates corresponding to valid second order moment data sets are compared and combined to provide a resultant skew angle estimate for the document.

Abstract translation: 确定扫描文档中的图像偏斜的方法包括扫描图像并且在逐个像素的基础上确定对于特定文档旋转，沿着快扫描方向和慢扫描方向的扫描线和列上的像素是ON还是OFF 角度。 通过对图像的一次读取，以多个预定原稿旋转角度同时对图像数据进行采样从采样数据中计算ON像素数的二阶矩，作为沿两个扫描线的扫描线的文档旋转角度的函数 快速和慢速的扫描方向，产生两个独立的倾斜角估计。 对应于有效的二阶矩数据集的倾斜角度估计被比较并组合以提供文档的合成斜角估计。

公开(公告)号：US20030123749A1

公开(公告)日：2003-07-03

申请号：US10032464

申请日：2002-01-02

Applicant: XEROX CORPORATION

Inventor： Hui Cheng ,  Ying-wei Lin ,  Stuart A. Schweid

IPC: G06K009/40 ,  G06K009/44 ,  G06K009/00 ,  G06K009/42

CPC classification number: G06T5/30 ,  G06T5/005 ,  G06T2207/10008

Abstract: An annular window-shaped structuring element is provided for image processing to remove speckles from a scanned image. The window-shaped structuring element is composed of two differently sized squares sharing the same geometric center-point. The pixel to be analyzed with the structuring element is at the center-point. The structuring element is used in a method to remove speckles from binary, grayscale, and/or color images by first eroding the image, detecting speckles relative to other pixels in the image, and removing declared speckles. The method may additionally include a halftoning module to protect halftone images.

Abstract translation: 提供环形窗形结构元件用于图像处理以从扫描图像去除斑点。 窗形结构元件由共享相同几何中心点的两个不同大小的正方形组成。 要用结构元素分析的像素在中心点。 结构化元素用于通过首先侵蚀图像，检测相对于图像中的其他像素的斑点以及去除所宣称的斑点来从二进制，灰度和/或彩色图像中去除散斑的方法。 该方法可以另外包括用于保护半色调图像的半色调模块。