公开(公告)号：US06941014B2

公开(公告)日：2005-09-06

申请号：US09737515

申请日：2000-12-15

Applicant: Ying-wei Lin ,  Martin E. Banton ,  William A. Fuss

Inventor： Ying-wei Lin ,  Martin E. Banton ,  William A. Fuss

IPC: G06K9/20 ,  G06T5/00 ,  H04N1/40 ,  H04N1/41 ,  G06K9/34

CPC classification number: G06K9/00456 ,  G06T7/11 ,  G06T7/174 ,  G06T2207/10008 ,  G06T2207/30176 ,  H04N1/40062 ,  H04N1/41

Abstract: This invention relates to a method and apparatus for segmenting an image using a combination of image segmentation techniques. More particularly, the invention is directed to an improved image segmentation technique for use in an image processing system that performs at least two distinct image segmentation processes on an image and combines the results to obtain a combined multi-layer representation of the image that can be suitably processed. In a specific example, a block based segmentation technique is performed on an image to generate a MRC (mixed raster content) representation—having foreground, background and selector layers. A pixel based segmentation technique is also performed on the image to generate rendering hints. The MRC representation and the rendering hints are then combined to obtain a four (4) layer representation of the image. The four layer representation is subsequently processed as required by the image processing system, e.g. compressed and stored.

Abstract translation: 本发明涉及使用图像分割技术的组合分割图像的方法和装置。 更具体地，本发明涉及一种用于在图像处理系统中使用的改进的图像分割技术，该图像处理系统对图像执行至少两个不同的图像分割处理，并且将结果组合以获得图像的组合多层表示，其可以是 适当加工。 在具体示例中，对图像执行基于块的分割技术以生成具有前景，背景和选择器层的MRC（混合光栅内容）表示。 还对图像执行基于像素的分割技术以产生渲染提示。 然后组合MRC表示和渲染提示以获得图像的四（4）层表示。 随后根据图像处理系统的要求对四层表示进行处理。 压缩并存储。

公开(公告)号：US06728004B2

公开(公告)日：2004-04-27

申请号：US09870304

申请日：2001-05-30

Applicant: Robert P. Loce ,  Michael Branciforte ,  Ying-wei Lin

Inventor： Robert P. Loce ,  Michael Branciforte ,  Ying-wei Lin

IPC: B41B944

CPC classification number: G06T5/20 ,  H04N1/58

Abstract: A method for processing digital images to be displayed, stored, or printed, to eliminate blooming and other artifacts. The system utilizes morphological processes to isolate and modify image structures susceptible to marking process artifacts and then combines the modified image structures with the input image to produce a printable image that may be rendered on a given printer.

Abstract translation: 一种用于处理要显示，存储或打印的数字图像的方法，以消除起霜和其他伪像。 该系统利用形态学过程来分离和修改易受标记过程伪像影响的图像结构，然后将修改的图像结构与输入图像组合，以产生可在给定打印机上呈现的可打印图像。

公开(公告)号：US06717700B1

公开(公告)日：2004-04-06

申请号：US09345740

申请日：1999-07-01

Applicant: Thomas A. Sanderson ,  Ying-wei Lin

Inventor： Thomas A. Sanderson ,  Ying-wei Lin

IPC: G06K936

CPC classification number: H04N1/407 ,  H04N1/40075

Abstract: A method and system which converts an electronic binary image to another electronic binary image by compensating for the differences between printer responses so that a target printer can print the image to emulate how the image would appear if printed by an originally-intended printer or another printer. A print-ready binary image is inputted into a print and scan simulation circuit which electronically simulates the printing and scanning of the image data. The print and scan simulation circuit converts the binary image data to gray scale image data. The gray scale image data is then processed by a tone response correction circuit. The tone response correction circuit alters the gray scale image data based on the difference between the tone reproduction curves of two printers, such as an originally-intended printer and a target printer. This changes the value of each pixel so that it ultimately yields the same density on the target printer when it is converted to binary form and printed as it would if the original binary image were printed on the originally-intended printer. This altered gray scale image data is then sent to a binarization circuit which converts the gray scale image data to a binary image. This binary image may then be sent to a printer, such as the target printer, so that the quality of the printed binary image simulates how it would have been printed on the originally intended printer.

Abstract translation: 通过补偿打印机响应之间的差异将电子二进制图像转换为另一电子二进制图像的方法和系统，使得目标打印机可以打印图像以模拟如果由原始打印机或另一打印机打印的图像将如何出现 。 打印准备的二进制图像被输入到电子模拟图像数据的打印和扫描的打印和扫描模拟电路中。 打印和扫描模拟电路将二进制图像数据转换为灰度图像数据。 然后灰度图像数据由色调响应校正电路处理。 色调响应校正电路基于原始打印机和目标打印机等两台打印机的色调再现曲线之间的差异来改变灰度图像数据。 这将改变每个像素的值，以便当目标打印机转换为二进制形式并打印时，它将最终产生相同的浓度，如果原始二进制图像打印在原始打印机上。 然后将该改变的灰度图像数据发送到将灰度图像数据转换为二进制图像的二值化电路。 然后可以将该二进制图像发送到诸如目标打印机的打印机，使得打印的二进制图像的质量模拟如何将其打印在原始打印机上。

公开(公告)号：US06549656B1

公开(公告)日：2003-04-15

申请号：US08626433

申请日：1996-04-02

Applicant: Ying-wei Lin

Inventor： Ying-wei Lin

IPC: G06K962

CPC classification number: G06K9/00456

Abstract: A digital image processing system for automatically segmenting a set of input image signals into a combination of predetermined classes of imagery, the set of input image signals forming part of a video image generated by an image input terminal. The system includes a classification circuit that receives the set of input image signals and classifies them as a ratio of the predetermined classes of imagery. A plurality of image processing circuits also receives the set of input image signals, each of which is adapted to process a unique class of imagery selected from the predetermined classes of imagery to generate a set of output image signals for that predetermined class of imagery. Finally, a mixing circuit combines each of the sets of output image signals determined by the plurality of image processing circuits in accordance with the ratio determined by the classification circuit to form a single set of output image signals, the mixing circuit minimizing the generation of artifacts formed in the single set of output image signals by providing a gradual transition between each of the predetermined class of imagery.

Abstract translation: 一种数字图像处理系统，用于将一组输入图像信号自动分割成预定类别的图像的组合，所述一组输入图像信号形成由图像输入端产生的视频图像的一部分。 该系统包括分类电路，其接收该组输入图像信号并将其分类为预定类别的图像的比率。 多个图像处理电路还接收一组输入图像信号，每个输入图像信号适于处理从预定类别的图像中选择的独特类别的图像，以生成用于该预定类别的图像的一组输出图像信号。 最后，混合电路根据由分类电路确定的比例组合由多个图像处理电路确定的输出图像信号组，以形成单组输出图像信号，混合电路最小化伪像的产生 通过在每个预定类别的图像之间提供逐渐的过渡而形成在单组输出图像信号中。

公开(公告)号：US06426802B1

公开(公告)日：2002-07-30

申请号：US09232637

申请日：1999-01-19

Applicant: Ying-wei Lin

Inventor： Ying-wei Lin

IPC: H04N152

CPC classification number: H04N1/52 ,  H04N1/6058

Abstract: A method and apparatus for generating highlight color tints for DND printing from full color image information uses complementary halftone screens. Image information that is out of a printing gamut is mapped into the printing gamut and the complementary halftone screens are applied to generate tint information while preserving gradation.

Abstract translation: 用于从全色图像信息产生用于DND打印的高亮色调的方法和装置使用互补的半色调屏幕。 不在打印色域中的图像信息被映射到打印色域中，并且应用互补半色调屏幕以生成色调信息同时保持灰度。

公开(公告)号：US5659399A

公开(公告)日：1997-08-19

申请号：US565138

申请日：1995-11-30

Applicant: Ying-wei Lin ,  Martin E. Banton

Inventor： Ying-wei Lin ,  Martin E. Banton

IPC: B41J2/44 ,  B41J5/30 ,  G06K15/12 ,  G06T3/40 ,  H03M7/30 ,  H04N1/405 ,  G06K15/00 ,  G06K1/00

CPC classification number: G06K15/128 ,  G06K2215/0071

Abstract: The present invention is a method and apparatus for detecting the presence of image regions requiring compact dot growth control and controlling the dot growth of such regions when rendered on a printing system. The invention operates to recognize those pixels within a bitmap image that are appropriate for alteration, using a template-based approach, and then alters the exposure pulse of identified pixels during imaging so as to assure a more stable output by a xerographic development system.

Abstract translation: 本发明是一种用于检测需要紧密点生长控制的图像区域的存在并且当在打印系统上呈现时控制这些区域的点生长的方法和装置。 本发明利用基于模板的方法来识别位图图像中适合于改变的那些像素，然后在成像期间改变识别的像素的曝光脉冲，以确保静电印刷制图系统的更稳定的输出。

公开(公告)号：US08368964B2

公开(公告)日：2013-02-05

申请号：US12536967

申请日：2009-08-06

Applicant: Beilei Xu ,  Robert Paul Loce ,  Chu-Heng Liu ,  Ying-wei Lin

Inventor： Beilei Xu ,  Robert Paul Loce ,  Chu-Heng Liu ,  Ying-wei Lin

IPC: H04N1/40

CPC classification number: H04N1/387 ,  G06T5/003 ,  G06T5/50 ,  G06T2207/10008 ,  G06T2207/10148 ,  G06T2207/30176

Abstract: A method for determining local defocus distance in a scanned image of a non-planar original object is provided comprising scanning at least a portion of the non-planar original object to produce first scanned image data at a first focal plane and scanning same the at least a portion of the non-planar original object to produce at least second scanned image data at a second focal plane. The first scanned image data is different from the second scanned image data wherein a distance between the first focal plane and the second focal plane is a predetermined quantity. The method further comprises estimating an out-of-focus distance of the object from the first and the second scanned image data.

Abstract translation: 提供了一种用于确定非平面原始对象的扫描图像中的局部散焦距离的方法，包括扫描非平面原始对象的至少一部分以在第一焦平面处产生第一扫描图像数据，并至少扫描至少 所述非平面原始对象的一部分在第二焦平面处产生至少第二扫描图像数据。 第一扫描图像数据与第二扫描图像数据不同，其中第一焦平面和第二焦平面之间的距离是预定量。 该方法还包括估计物体与第一和第二扫描图像数据的离焦距离。

公开(公告)号：US07706594B2

公开(公告)日：2010-04-27

申请号：US12123188

申请日：2008-05-19

Applicant: Ying-wei Lin ,  Raphael F. Bov, Jr. ,  Zhigang Fan ,  John C. Handley

Inventor： Ying-wei Lin ,  Raphael F. Bov, Jr. ,  Zhigang Fan ,  John C. Handley

IPC: G06K9/00 ,  H04N7/167

CPC classification number: G06K9/186 ,  G06K9/18

Abstract: The present disclosure is directed to a method and apparatus for applying magnetic ink character recognition (MICR) technology to enable the embedding of coded information within text characters of a document.

Abstract translation: 本公开涉及一种用于应用磁墨水字符识别（MICR）技术以使得能够在文档的文本字符内嵌入编码信息的方法和装置。

公开(公告)号：US07218332B2

公开(公告)日：2007-05-15

申请号：US10135139

申请日：2002-04-30

Applicant: Hui Cheng ,  Ying-wei Lin

Inventor： Hui Cheng ,  Ying-wei Lin

IPC: G06T15/00

CPC classification number: H04N1/00 ,  G06T11/00 ,  H04N1/00798

Abstract: Systems and methods are presented for processing and rendering image data during a single pass through the image data. A method includes loading scanlines of image data into a rolling band buffer, performing a windowing technique on the image data, and determining if a class change was experienced by any window having a portion in an output scanline of the buffer. The method further includes processing image data in the output scanline for a window portion that experienced a class change, using a blended rendering algorithm. If no class change is detected, the method includes processing image data in the output scanline for the window portion using a class-based rendering algorithm. The method optionally includes rendering processed image data for the output scanline to a rendering device. According to other features, an apparatus includes a rolling band buffer, a windowing processor, class-based rendering algorithms, and a blended rendering algorithm.

Abstract translation: 呈现系统和方法，用于在单次传递图像数据期间处理和渲染图像数据。 一种方法包括将图像数据的扫描线加载到滚动带缓冲器中，对图像数据执行加窗技术，以及确定是否由具有缓冲器的输出扫描线中的一部分的任何窗口经历了类别改变。 该方法还包括使用混合渲染算法来处理经历类别改变的窗口部分的输出扫描线中的图像数据。 如果没有检测到类更改，则该方法包括使用基于类的呈现算法来处理窗口部分的输出扫描线中的图像数据。 该方法可选地包括将处理的输出扫描线的图像数据渲染到呈现设备。 根据其他特征，一种装置包括滚动带缓冲器，加窗处理器，基于类的渲染算法和混合渲染算法。

公开(公告)号：US07116443B2

公开(公告)日：2006-10-03

申请号：US10137677

申请日：2002-05-02

Applicant: John C. Handley ,  Ying-wei Lin

Inventor： John C. Handley ,  Ying-wei Lin

IPC: H04N1/60 ,  G03F3/08 ,  G06K9/00

CPC classification number: H04N1/56 ,  G01J3/462

Abstract: A method for neutral pixel detection using color space feature vectors wherein one color space coordinate represents lightness is provided. The method includes the following steps: a) receiving an input image represented in a first color space; b) converting the input image to a second color space wherein one coordinate represents lightness; c) selecting a pixel in the second color space representation to be classified; d) computing second color space feature vectors associated with the selected pixel; and e) classifying the selected pixel between neutral and color classes based on the values computed for the second color space feature vectors. Typically, the input image is processed using a smoothing filter to create a smoothed input image prior to the conversion to the second color space. The method can be adapted to page processing or strip processing schemes with respect to the input image.