-
1.发明授权Method for image segmentation from proved detection of background and text image portions 失效经过验证的背景和文字图像部分的图像分割方法公开(公告)号：US07379593B2
公开(公告)日：2008-05-27
申请号：US11313980
申请日：2005-12-21
IPC分类号： G06K9/34
CPC分类号： G06K9/38 , G06K9/00456 , G06K2209/01
摘要： A method is provided for segmenting scanned image data in accordance with mixed raster content processing, further including windowing for purposes of extracting particularly classifiable objects, i.e., text, graphics or pictures. Application of predetermined parameter sets selected for more precise identification of the extracted objects are applied to the data for object extraction, object selection, color uniformity, and clustering for coloring similarity. A page background detection feature uses dual thresholding for segregating text (darker) areas from non-text (brighter) areas. Two histograms are created for the respective areas. Thresholds are generated from the two histograms and applied to the respective areas separately.
摘要翻译： 提供了一种根据混合光栅内容处理来分割扫描图像数据的方法，还包括为了提取特别可分类的对象，即文本，图形或图片的窗口。 将用于更精确地识别提取的对象的预定参数集的应用应用于用于对象提取，对象选择，颜色均匀性和聚类的数据用于着色相似性。 页面背景检测功能使用双阈值来隔离非文本（较亮）区域的文本（较暗）区域。 为各个区域创建两个直方图。 从两个直方图生成阈值并分别应用于各个区域。
-
2.发明授权公开(公告)号：US06529291B1
公开(公告)日：2003-03-04
申请号：US09401378
申请日：1999-09-22
申请人： Stuart A. Schweid , Jeng-nan Shiau , Zhigang Fan
发明人： Stuart A. Schweid , Jeng-nan Shiau , Zhigang Fan
IPC分类号： G06F1500
CPC分类号： H04N1/6025
摘要： A color conversion table designed to produce 0% under-color removal and a 100% under-color removal TRC are configured as a matched pair and are used to render an image from fuzzy detected color signals, including providing variable under-color removal to obtain fuzzy black conversion. The output of the color conversion table and the TRC are multiplied by a weighted value which depends on a value of a received neutral tag. The weighted outputs of the color conversion table and TRC are added such that a varying weighted output is generated. The generated output is used in image rendering to produce a smooth transition from a full color to monochrome, where variable amounts of under-color removal are obtained using the color correction table and TRC.
摘要翻译： 被设计为产生0％的底色去除和100％底色去除TRC的颜色转换表被配置为匹配对，并且用于从模糊检测到的颜色信号渲染图像，包括提供可变的底色去除以获得 模糊黑转换。 颜色转换表和TRC的输出乘以取决于所接收的中立标签的值的加权值。 添加颜色转换表和TRC的加权输出，使得生成变化的加权输出。 生成的输出用于图像渲染，以产生从全色到单色的平滑过渡，其中使用颜色校正表和TRC获得可变量的底色去除。
-
公开(公告)号：US06947597B2
公开(公告)日：2005-09-20
申请号：US09965880
申请日：2001-09-28
申请人： Ying-wei Lin , Stuart A. Schweid , Jeng-nan Shiau , Raja Bala , Zhigang Fan
发明人： Ying-wei Lin , Stuart A. Schweid , Jeng-nan Shiau , Raja Bala , Zhigang Fan
CPC分类号： H04N1/40062 , G06K9/00456
摘要： 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 “soft” image classifier using combinations of two (2) or more SGLD texture, color discreteness, and edge features is provided. The “soft” classifier uses image features to classify areas of an input image in picture, graphics, or fuzzy classes.
摘要翻译： 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：US09798712B2
公开(公告)日：2017-10-24
申请号：US13609541
申请日：2012-09-11
申请人： Beilei Xu , Stuart A. Schweid , Raja Bala , Rinku Gajera
发明人： Beilei Xu , Stuart A. Schweid , Raja Bala , Rinku Gajera
CPC分类号： G06F17/248 , G06F17/289
摘要： The present disclosure provides a method of producing a personalized medical record, comprising: sensing capabilities of a receiving device; retrieving stock information; retrieving personalized information; combining at least a portion of the stock information and at least a portion of the personalized information into the personalized record; formatting the personalized record based on a combination of the capabilities of the receiving device and a user's preference; and, transmitting the formatted personalized record to the device.
-
公开(公告)号：US20130097099A1
公开(公告)日：2013-04-18
申请号：US13275934
申请日：2011-10-18
IPC分类号： G06Q30/02
CPC分类号： G06Q30/04 , G06Q30/0283
摘要： Disclosed is a processor-implemented method for processing images. The processor receives image data of a color space defined by input provided to a system by a user, determines at least one color attribute of the pixels in the received image correlating to at least perceptual image characteristics, determines statistics using the attribute(s), and analyzes the statistics to classify the image into a category. Based on at least the category, a billing structure for the image is determined. For example, chroma and/or hue of pixels can be used to create histograms, whose data is used to determine a degree of color and/or content of an image, which is categorized. Color space components of received pixels can also be statistically analyzed. Such determinations consider billing based on human perception of use of color. Billing for color images in this manner satisfies the user and increases use of color output (e.g., printing).
摘要翻译： 公开了一种用于处理图像的处理器实现的方法。 处理器接收由用户提供给系统的输入定义的颜色空间的图像数据，确定与至少感知图像特征相关的接收图像中的像素的至少一个颜色属性，使用属性确定统计， 并分析统计信息，将图像分类为一个类别。 基于至少该类别，确定图像的记帐结构。 例如，可以使用像素的色度和/或色调来创建直方图，其数据用于确定被分类的图像的颜色和/或内容的程度。 也可以统计分析接收像素的颜色空间分量。 这种确定考虑了基于人类对颜色使用的看法的计费。 以这种方式对彩色图像进行计费满足用户并增加使用颜色输出（例如打印）。
-
公开(公告)号：US20090257674A1
公开(公告)日：2009-10-15
申请号：US12101944
申请日：2008-04-11
申请人： Stuart A. Schweid
发明人： Stuart A. Schweid
IPC分类号： G06K9/40
CPC分类号： G06K9/40 , G06T5/002 , G06T5/20 , G06T2207/20016 , G06T2207/20192
摘要： A system determines the noise level of image data by high pass filtering image data. Absolutes values of the high pass filtered image data are determined. Thereafter, multiple mean values for absolute values less than a predetermined number of threshold values are determined. Based upon the determined mean values, a plurality of estimated mean values is calculated, each estimated mean value being calculated from a combination of two determined mean values. The noise of the image is determined from a combination of the minimum estimated mean value and the maximum estimated mean value. This noise can be optionally used by a sigma filter, at Step S740, to sigma filter the image data.
-
7.发明授权Systems and methods for streak detection in image array scanning using overdetermined scanners and column filtering 失效使用超定义扫描仪和列过滤的图像阵列扫描中条纹检测的系统和方法公开(公告)号：US07359093B2
公开(公告)日：2008-04-15
申请号：US10845164
申请日：2004-05-14
申请人： Stuart A. Schweid , Shen-ge Wang , Paul A. Hosier
发明人： Stuart A. Schweid , Shen-ge Wang , Paul A. Hosier
IPC分类号： H04N1/409
CPC分类号： H04N1/4097 , H04N1/00092 , H04N1/1215 , H04N1/193
摘要： A streak detection method and system in a fixed imaging array digital scanning system obtains image data from each of the plurality of rows in the at least one full color spectrum channel set of rows of positionally discrete sensors and integrates this data to produce an estimate of image data recorded by at least one clear channel row of positionally discrete sensors. A clear channel error signal is generated by the comparison to alert the operator to the presence of non-image data. The clear channel error signal may be refined to through a low pass column filtering process in order to filter out potentially erroneous clear channel error resulting from thermal, mechanical or other noise sources unrelated to image scanning. Stationary obstructions in the field of view of the imaging array, or defects in one or more sensors in the imaging array, are detected through this comparison which would otherwise appear repeatedly reproduced as streaks or lines in the reproduced output image.
摘要翻译： 固定成像阵列数字扫描系统中的条纹检测方法和系统从至少一个位置离散传感器行的全色谱通道组中的多行中的每一行获得图像数据，并对该数据进行积分以产生图像估计 通过位置离散传感器的至少一个清晰通道行记录的数据。 通过比较产生清晰的通道错误信号，以向操作员警告非图像数据的存在。 可以通过低通列滤波处理来将清除信道误差信号细化为过滤掉与图像扫描无关的热，机械或其它噪声源引起的潜在错误的清除信道误差。 通过该比较来检测成像阵列的视场中的固定障碍物或成像阵列中的一个或多个传感器中的缺陷，否则该比较将被再现为再现的输出图像中的条纹或线条。
-
8.发明授权Method and apparatus for implementing integrated cavity effect correction in scanners 有权在扫描仪中实现集成腔效应校正的方法和装置公开(公告)号：US06631215B1
公开(公告)日：2003-10-07
申请号：US09448009
申请日：1999-11-23
IPC分类号： G06K940
CPC分类号： G06T5/20
摘要： A method and apparatus are provided for determining a weighted average measured reflectance parameter Rm for pixels in an image for use in integrated cavity effect correction of the image. For each pixel of interest Pi,j in the image, an approximate spatial dependent average Ai,j, Bi,j of video values in a region of W pixels by H scan lines surrounding the pixel of interest Pi,j is computed by convolving video values Vi,j of the image in the region with a uniform filter. For each pixel of interest Pi,j a result of the convolving step is used as the reflectance parameter Rm. The apparatus includes a video buffer for storing the pixels of the original scanned image, and first and second stage average buffers for storing the computed approximate spatial dependent averages Ai,j, Bi,j. First and second stage processing circuits respectively generate the first and second stage average values Ai,j, Bi,j by convolving the video values of the image in a preselected region with a uniform filter.
摘要翻译： 提供一种方法和装置，用于确定用于图像的集成腔效应校正的图像中的像素的加权平均测量反射率参数Rm。 对于图像中的每个感兴趣像素P i，j，通过卷积视频来计算在围绕像素p，j的W像素的H像素的区域中的视频值的近似空间依赖平均值Ai，j，Bi，j 在具有均匀滤波器的区域中的图像的值Vi，j。 对于感兴趣的每个像素Pi，j，使用卷积步骤的结果作为反射参数Rm。 该装置包括用于存储原始扫描图像的像素的视频缓冲器，以及用于存储所计算的近似空间相关平均值Ai，j，Bi，j的第一和第二平均缓冲器。 第一和第二级处理电路通过使用均匀的滤波器卷积预选区域中的图像的视频值，分别产生第一和第二平均值Ai，j，Bi，j。
-
9.发明授权Method and apparatus for reducing excess developer material at the edges of print sheets of full bleed images via digital image processing 有权用于通过数字图像处理减少在全放像图像的打印片的边缘处的多余显影剂材料的方法和装置公开(公告)号：US06469806B1
公开(公告)日：2002-10-22
申请号：US09216528
申请日：1998-12-18
IPC分类号： G06F1900
CPC分类号： G06K15/12 , H04N1/4092
摘要： A digital image processing apparatus is disclosed. The apparatus increases input pixel intensity values in an edge region of input image data to form output pixel intensity values. The input pixel intensity values are varyingly increased depending on a location of the input pixel values within the edge region. The output values are printed on an edge region of a print sheet. A printer prints the output intensity pixel values on a print sheet. The invention allows printing of digital images to the edge of a print sheet without accumulating a great deal of toner at the edge of the sheet or overburdening a toner cleaning device.
摘要翻译： 公开了一种数字图像处理装置。 该装置增加输入图像数据的边缘区域中的输入像素强度值以形成输出像素强度值。 输入像素强度值根据边缘区域内的输入像素值的位置而不同地增加。 输出值打印在打印纸的边缘区域上。 打印机打印打印纸上的输出强度像素值。 本发明允许将数字图像打印到打印纸的边缘，而不在纸张的边缘处积聚大量的调色剂或使调色剂清洁装置过载。
-
10.发明授权Method and apparatus for distinguishing between noisy continuous tone document types and other document types to maintain reliable image segmentation 有权用于区分嘈杂的连续色调文档类型和其他文档类型以保持可靠的图像分割的方法和装置公开(公告)号：US06411735B1
公开(公告)日：2002-06-25
申请号：US09158868
申请日：1998-09-23
IPC分类号： G06K962
CPC分类号： G06K9/00456 , H04N1/40062
摘要： A method and apparatus are disclosed for distinguishing noisy continuous tone document types from other document types such as halftone or text, in order to maintain reliable image segmentation. In both cases a Range of Video microclassifier is added to the other microclassifiers (Sij, estimated halftone frequency, etc.) to disqualify noisy continuous tone images from being incorrectly classified as other document types such as halftone or text document types.
摘要翻译： 公开了一种用于区分噪声连续色调文档类型和其他文档类型（例如半色调或文本）的方法和装置，以便保持可靠的图像分割。 在这两种情况下，将视频微分类器的范围添加到其他微分类器（Sij，估计的半色调频率等），以使噪声连续色调图像被不正确地分类为诸如半色调或文本文档类型的其他文档类型。
-
-
-
-
-
-
-
-
-
搜索结果
79 条记录 (耗时 0.028 秒)
