公开(公告)号：US11087126B2

公开(公告)日：2021-08-10

申请号：US16441601

申请日：2019-06-14

Applicant: Xerox Corporation

Inventor： Xing Li ,  Dhevendra Alagan Palanivel ,  Sainarayanan Gopalakrishnan ,  Rajasekar Kanagasabai

IPC: G06K9/00 ,  H04N1/407 ,  G06T7/13

Abstract: A document processing system produces a digital representation of an original image by determining a background level for white space of the original image. Using the background level, the system identifies pixels not belonging to the white space. The system generates a binary image of the original image based from the identified pixels. The system then identifies image content surrounded by the white space in the original image using the binary image. Next, the system generates a block for each image content and extracts each block from the original image. After processing each block, the system reapplies the processed blocks to a blank canvas to generate the digital representation.

公开(公告)号：US20180310011A1

公开(公告)日：2018-10-25

申请号：US15493674

申请日：2017-04-21

Applicant: Xerox Corporation

Inventor： Sainarayanan Gopalakrishnan ,  Xing Li ,  Rajasekar Kanagasabai ,  Clara Cuciurean-Zapan ,  Vignesh Doss

IPC: H04N19/426 ,  H04N19/33 ,  H04N19/187

CPC classification number: H04N19/27 ,  H04N1/642

Abstract: An image compression method includes compressing an input image with first and second compression methods to generate first and second (e.g., lossless and lossy) compressed images. First and second residual layers are generated, based on a difference between the first and second compressed images. Connected components in the residual layers are identified. Each connected component includes a group of one or more pixels that, when mapped to the second compressed image is connected, in first and second directions, to pixels in the second compressed image. A compressed image is generated, which includes, for a connected component identified in the first residual layer, removing corresponding pixels from the second compressed image, and for a connected component identified in the second residual layer, adding corresponding pixels to the second compressed image. The system and method can thus provide file size savings associated with lossy compression while avoiding character replacement.

公开(公告)号：US09736333B1

公开(公告)日：2017-08-15

申请号：US15094681

申请日：2016-04-08

Applicant: Xerox Corporation

Inventor： Xing Li ,  Dhevendra Alagan Palanivel ,  Sainarayanan Gopalakrishnan ,  Vignesh Doss

IPC: H04N1/40 ,  H04N1/409 ,  H04N1/393 ,  G06K15/02 ,  G06T15/02 ,  G06T3/40 ,  G06T5/00

CPC classification number: H04N1/409 ,  G06K15/1843 ,  G06K15/1847 ,  G06K15/1872 ,  G06T3/40 ,  G06T3/403 ,  G06T5/003 ,  G06T7/12 ,  G06T7/136 ,  G06T7/187 ,  H04N1/393 ,  H04N1/40062 ,  H04N1/40093 ,  H04N1/4092

Abstract: A method, non-transitory computer readable medium and apparatus for generating an output image are disclosed. For example, the method includes receiving an image, applying a first filter, applying a second filter, calculating a difference between the image with the second filter that was applied and the image with the first filter that was applied and transmitting the difference to a sharpening module and a segmentation module to generate the output image.

公开(公告)号：US20160098596A1

公开(公告)日：2016-04-07

申请号：US14505517

申请日：2014-10-03

Applicant: Xerox Corporation

Inventor： Sainarayanan Gopalakrishnan ,  Rajasekar Kanagasabai ,  Vignesh Doss ,  Sudhagar Subbaian ,  Xing Li

IPC: G06K9/00 ,  G06F17/21

CPC classification number: G06K9/00456 ,  G06F17/212 ,  G06K9/00422 ,  G06K9/2063

Abstract: Methods and systems for classifying a region of interest in an electronic document. A first region from the electronic document is extracted. The first region includes at least the region of interest. A first projection profile of pixels is determined in the region of interest. The first projection profile of pixels is indicative of a presence of a content in the region of interest. The region of interest is classified in at least one category based on a comparison of the first projection profile with a predetermined projection profile associated with the region of interest.

Abstract translation: 在电子文件中分类感兴趣区域的方法和系统。 提取电子文档的第一区域。 第一区域至少包括感兴趣的区域。 在感兴趣的区域中确定像素的第一投影轮廓。 像素的第一投影轮廓指示感兴趣区域中的内容的存在。 基于第一投影轮廓与与感兴趣区域相关联的预定投影轮廓的比较，感兴趣区域被分类为至少一个类别。

公开(公告)号：US20150356740A1

公开(公告)日：2015-12-10

申请号：US14296553

申请日：2014-06-05

Applicant: Xerox Corporation

Inventor： Sudhagar Subbaian ,  Sainarayanan Gopalakrishnan ,  Xing Li ,  Clara Cuciurean-Zapan

IPC: G06T7/00 ,  G06K9/62 ,  G06K9/18

CPC classification number: G06K9/6267 ,  G06K9/00456 ,  G06K9/4638

Abstract: A method and system for segmenting text from non-text portions of a digital image using the size, solidity, and run length characteristics of connected components within the image data. For a connected component comprising a rectangular group of pixels enclosing a set of connected pixels having the same binary state, the size characteristic may be based on a ratio of height to width of the connected component and the total number of pixels within the connected component, the solidity characteristic may be based on a ratio of pixels within a convex hull of the set of connected pixel to a total number of pixels within the connected component, and the run length characteristic may be based on a number of transitions within the connected component.

Abstract translation: 一种用于使用图像数据内的连接分量的大小，坚固度和游程长度特征从数字图像的非文本部分分割文本的方法和系统。 对于包括围绕具有相同二进制状态的一组连接像素的矩形像素组的连接分量，尺寸特征可以基于所连接分量的高度与宽度的比率以及连通分量内的总像素数， 固体特性可以基于所连接的像素组中的凸包内的像素与连通分量内的总像素数的比率，并且游程长度特征可以基于所连接的组件内的多个转换。

公开(公告)号：US09106864B2

公开(公告)日：2015-08-11

申请号：US14057509

申请日：2013-10-18

Applicant: XEROX CORPORATION

Inventor： Xing Li ,  Ryan Metcalfe

IPC: H04N1/52 ,  H04N1/405

CPC classification number: H04N1/4052 ,  H04N1/40087 ,  H04N1/405 ,  H04N1/409

Abstract: The present invention generally relates to systems and methods for error diffusion, e.g., for use in a halftone process. The described techniques are faster than known techniques in that they utilize fewer computations on average. Consequently, the described techniques can be more readily implemented in software, for example, though the described techniques are not limited to software.

Abstract translation: 本发明一般涉及用于误差扩散的系统和方法，例如用于半色调处理。 所描述的技术比已知技术更快，因为它们平均使用较少的计算。 因此，所描述的技术可以更容易地在软件中实现，例如，尽管所描述的技术不限于软件。

公开(公告)号：US09083912B2

公开(公告)日：2015-07-14

申请号：US13670276

申请日：2012-11-06

Applicant: Xerox Corporation

Inventor： Xing Li

IPC: G09G5/02 ,  H04N1/405 ,  G09G3/20

CPC classification number: H04N1/4052 ,  G09G3/2059

Abstract: A method, non-transitory computer readable medium, and apparatus for enabling parallel processing of pixels in an image are disclosed. For example, the method performs, via a multiple core processor, a one-dimensional error diffusion on the pixels in the image to reduce a number of bits per pixel to a value lower than an initial number of bits per pixel and greater than one, and performs a two-dimensional error diffusion on the pixels in the image that have undergone the one-dimensional error diffusion, to reduce the number of bits per pixel to one bit per pixel.

Abstract translation: 公开了一种用于使图像中的像素能够并行处理的方法，非暂时计算机可读介质和装置。 例如，该方法通过多核处理器执行图像中的像素上的一维误差扩散，以将每像素的位数减少到低于每像素的初始位数和大于1的值， 并且对已经经历一维误差扩散的图像中的像素执行二维误差扩散，以将每像素的位数减少到每像素1位。

公开(公告)号：US09007659B1

公开(公告)日：2015-04-14

申请号：US14107327

申请日：2013-12-16

Applicant: Xerox Corporation

Inventor： Chao Yu ,  Xing Li ,  David J. Metcalfe

IPC: H04N1/405 ,  H04N1/32

CPC classification number: H04N1/4052

Abstract: A method, non-transitory computer readable medium, and apparatus for performing error diffusion are disclosed. For example, the method quantizes an error for a first pixel of a plurality of pixels in a first row, diffuses the error to an adjacent pixel of the plurality of pixels in the first row, performs the quantizing and the diffusing for each remaining pixel of the plurality of pixels in the first row and applies the error that is quantized for each one of the plurality of pixels the first row in a desired number of different directions in a plurality of parallel operations that is equal to the desired number of different directions.

Abstract translation: 公开了一种用于执行误差扩散的方法，非暂时计算机可读介质和装置。 例如，该方法对第一行中的多个像素的第一像素的误差进行量化，将误差扩散到第一行中的多个像素的相邻像素，对每个剩余像素的残留像素执行量化和扩散 第一行中的多个像素，并且在等于期望数量的不同方向的多个并行操作中，将针对所述第一行中的每个像素的每一个量化的误差应用于期望数量的不同方向。

公开(公告)号：US08995021B2

公开(公告)日：2015-03-31

申请号：US13916059

申请日：2013-06-12

Applicant: Xerox Corporation

Inventor： Xing Li ,  Zhenhuan Wen

IPC: G06F3/12 ,  G06K15/02

CPC classification number: G06K15/1881 ,  H04N1/58

Abstract: Provided are black trapping methods, apparatus and systems for binary images. According to one exemplary method, black trapping color image data is performed by incorporating a set of trapping condition logical operations. Specifically, edge checking is based on estimated contone color values and density checking based on a binary bitmap.

Abstract translation: 提供了用于二进制图像的黑色捕获方法，装置和系统。 根据一个示例性方法，通过结合一组捕获条件逻辑操作来执行黑色捕获彩色图像数据。 具体来说，边缘检查基于基于二进制位图的估计连续色度颜色值和浓度检查。

公开(公告)号：US20150077808A1

公开(公告)日：2015-03-19

申请号：US14029903

申请日：2013-09-18

Applicant: XEROX CORPORATION

Inventor： Xing Li ,  David Jon Metcalfe ,  Robert Robideau

IPC: G06K15/02

CPC classification number: G06T7/408 ,  G06T5/002 ,  G06T5/20 ,  G06T7/90 ,  G06T11/001 ,  G06T2207/10024 ,  G06T2207/20192 ,  H04N1/40075 ,  H04N1/405 ,  H04N1/4051 ,  H04N1/4055 ,  H04N1/4058 ,  H04N1/6008

Abstract: A method and system for estimating continuous tone values associated with input pixels in a color image are provided. The method includes receiving binarized halftone image data representing a color image, wherein the color image has a plurality of input pixels; and estimating the continuous tone values associated with each of the input pixels by: establishing a window comprising a pixel of interest and neighboring pixels in the binarized halftone image data, wherein the window comprises a plurality of sub-windows and wherein each sub-window has a plurality of predetermined number of rows and columns of pixels; and processing the binarized halftone image data in both a process direction and a cross-process direction using the window such that the processing is performed for one of the pixels in each of the rows within the sub-window and the processing is skipped for the remaining pixels in that row of that sub-window.

Abstract translation: 提供了一种用于估计与彩色图像中的输入像素相关联的连续色调值的方法和系统。 该方法包括接收表示彩色图像的二值化半色调图像数据，其中彩色图像具有多个输入像素; 以及通过以下步骤估计与每个输入像素相关联的连续色调值：建立包括所述二值化半色调图像数据中的感兴趣像素和相邻像素的窗口，其中所述窗口包括多个子窗口，并且其中每个子窗口具有 多个预定数量的行和列的像素; 以及使用所述窗口在处理方向和交叉处理方向上处理二进制化的半色调图像数据，使得对于子窗口内的每行中的一个像素执行处理，并且跳过剩余的处理 该子窗口该行的像素。