专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08180164B2 OCR-guided text tokenization of digital images 有权
标题翻译：数字图像的OCR指导文本标记化
公开(公告)号：US08180164B2
公开(公告)日：2012-05-15
申请号：US12335624
申请日：2008-12-16
申请人： Zhigang Fan , Francis Tse , Michael R. Campanelli , Yingjun Bai
发明人： Zhigang Fan , Francis Tse , Michael R. Campanelli , Yingjun Bai
IPC分类号： G06K9/36 , G06K9/20 , G06K9/46
CPC分类号： G06K9/72 , G06K2209/01
摘要： An image processing method in which OCR is used to guide the text tokenization. More particularly, OCR is first performed on each symbol in the scanned image. For example, a symbol may be a number, letter, or other character. During the tokenization process, the OCR results are used to select appropriate matching criteria for each symbol. The symbols that are recognized as different characters are not allowed to be clustered into the same group. The symbols with the same OCR results are clustered according to the recognition confidence levels.
摘要翻译：一种使用OCR来指导文本标记化的图像处理方法。更具体地，首先对扫描图像中的每个符号执行OCR。例如，符号可以是数字，字母或其他字符。在标记化过程中，OCR结果用于为每个符号选择合适的匹配标准。识别为不同字符的符号不允许聚集到同一组中。具有相同OCR结果的符号根据识别置信水平进行聚类。

2. 发明申请

US20100150460A1 OCR-GUIDED TEXT TOKENIZATION OF DIGITAL IMAGES 有权
标题翻译： OCR指导数字图像的文本识别
公开(公告)号：US20100150460A1
公开(公告)日：2010-06-17
申请号：US12335624
申请日：2008-12-16
申请人： Zhigang Fan , Francis Tse , Michael R. Campanelli , Yingjun Bai
发明人： Zhigang Fan , Francis Tse , Michael R. Campanelli , Yingjun Bai
IPC分类号： G06K9/36 , G06K9/20
CPC分类号： G06K9/72 , G06K2209/01
摘要： An image processing method in which OCR is used to guide the text tokenization. More particularly, OCR is first performed on each symbol in the scanned image. For example, a symbol may be a number, letter, or other character. During the tokenization process, the OCR results are used to select appropriate matching criteria for each symbol. The symbols that are recognized as different characters are not allowed to be clustered into the same group. The symbols with the same OCR results are clustered according to the recognition confidence levels.
摘要翻译：一种使用OCR来指导文本标记化的图像处理方法。更具体地，首先对扫描图像中的每个符号执行OCR。例如，符号可以是数字，字母或其他字符。在标记化过程中，OCR结果用于为每个符号选择合适的匹配标准。识别为不同字符的符号不允许聚集到同一组中。具有相同OCR结果的符号根据识别置信水平进行聚类。

3. 发明申请

US20050286776A1 Using graphic objects in MFD scan-to-export function 失效
标题翻译：在MFD扫描到导出功能中使用图形对象
公开(公告)号：US20050286776A1
公开(公告)日：2005-12-29
申请号：US10877302
申请日：2004-06-25
申请人： Yingjun Bai , Zhigang Fan , Timothy Jacobs
发明人： Yingjun Bai , Zhigang Fan , Timothy Jacobs
IPC分类号： G06K9/36 , H04N1/32
CPC分类号： H04N1/642
摘要： A method of compressing a document includes: acquiring an image of the document, the image represented by pixels; segmenting the image into Mixed Raster Content (MRC) planes including a foreground plane (12) that receives a first portion of the pixels, a background plane (14) that receives a second portion of the pixels, and a selector plane (16) that identifies which of the foreground and background planes the pixels belong to; identifying a geometric shape in at least one of the MRC planes; determining if the identified geometric shape has a substantially uniform color; and, replacing the identified shape when it is determined to have a substantially uniform color with a vector graphic representation of the geometric shape.
摘要翻译：压缩文档的方法包括：获取文档的图像，由像素表示的图像; 将图像分割成包含接收像素的第一部分的前景平面（12）的混合光栅内容（MRC）平面，接收像素的第二部分的背景平面（14）以及选择器平面（16），其中，识别像素属于哪个前景和背景平面; 识别所述MRC平面中的至少一个中的几何形状; 确定所识别的几何形状是否具有基本均匀的颜色; 并且当确定具有几何形状的矢量图形表示的基本均匀的颜色时，替换所识别的形状。

4. 发明授权

US07283674B2 Using graphic objects in MFD scan-to-export function 失效
标题翻译：在MFD扫描到导出功能中使用图形对象
公开(公告)号：US07283674B2
公开(公告)日：2007-10-16
申请号：US10877302
申请日：2004-06-25
申请人： Yingjun Bai , Zhigang Fan , Timothy W. Jacobs
发明人： Yingjun Bai , Zhigang Fan , Timothy W. Jacobs
IPC分类号： G06K9/36 , G06K9/00
CPC分类号： H04N1/642
摘要： A method of compressing a document includes: acquiring an image of the document, the image represented by pixels; segmenting the image into Mixed Raster Content (MRC) planes including a foreground plane (12) that receives a first portion of the pixels, a background plane (14) that receives a second portion of the pixels, and a selector plane (16) that identifies which of the foreground and background planes the pixels belong to; identifying a geometric shape in at least one of the MRC planes; determining if the identified geometric shape has a substantially uniform color; and, replacing the identified shape when it is determined to have a substantially uniform color with a vector graphic representation of the geometric shape.
摘要翻译：压缩文档的方法包括：获取文档的图像，由像素表示的图像; 将图像分割成包含接收像素的第一部分的前景平面（12）的混合光栅内容（MRC）平面，接收像素的第二部分的背景平面（14）以及选择器平面（16），其中，识别像素属于哪个前景和背景平面; 识别所述MRC平面中的至少一个中的几何形状; 确定所识别的几何形状是否具有基本均匀的颜色; 并且当确定具有几何形状的矢量图形表示的基本均匀的颜色时，替换所识别的形状。

5. 发明申请

US20050190981A1 System for recording image data from a set of sheets having similar graphic elements 有权
标题翻译：用于从具有相似图形元素的一组纸张记录图像数据的系统
公开(公告)号：US20050190981A1
公开(公告)日：2005-09-01
申请号：US10788944
申请日：2004-02-26
申请人： Zhigang Fan , Ramesh Nagarajan , Yingjun Bai
发明人： Zhigang Fan , Ramesh Nagarajan , Yingjun Bai
IPC分类号： G06K9/20 , G06K9/36 , H04N7/26
CPC分类号： H04N19/90 , G06K9/00449
摘要： In an input scanning system, as would be present in a digital copier, a “template” of similar visual elements or objects, such as logos and other designs, is detected among a series of scanned images. The common objects form a reference image against which subsequently-recorded input images are compared. If bounding boxes around objects in the input images match those in the reference image, the objects in the bounding boxes are attempted to be matched to those in the reference image. If objects in the input image and reference image match, then the image data from the input image is coded using a pointer to the corresponding object in the reference image.
摘要翻译：在输入扫描系统中，如在数字复印机中所存在的那样，在一系列扫描图像中检测到类似的视觉元素或物体（诸如徽标和其他设计）的“模板”。公共对象形成参考图像，随后记录的输入图像被比较。如果输入图像中的对象周围的边框与参考图像中的边框相匹配，则尝试将边界框中的对象与参考图像中的对象进行匹配。如果输入图像和参考图像中的对象匹配，则使用指向参考图像中的相应对象的指针对来自输入图像的图像数据进行编码。

6. 发明授权

US07292710B2 System for recording image data from a set of sheets having similar graphic elements 有权
标题翻译：用于从具有相似图形元素的一组纸张记录图像数据的系统
公开(公告)号：US07292710B2
公开(公告)日：2007-11-06
申请号：US10788944
申请日：2004-02-26
申请人： Zhigang Fan , Ramesh Nagarajan , Yingjun Bai
发明人： Zhigang Fan , Ramesh Nagarajan , Yingjun Bai
IPC分类号： G06K9/00
CPC分类号： H04N19/90 , G06K9/00449
摘要： In an input scanning system, as would be present in a digital copier, a “template” of similar visual elements or objects, such as logos and other designs, is detected among a series of scanned images. The common objects form a reference image against which subsequently-recorded input images are compared. If bounding boxes around objects in the input images match those in the reference image, the objects in the bounding boxes are attempted to be matched to those in the reference image. If objects in the input image and reference image match, then the image data from the input image is coded using a pointer to the corresponding object in the reference image.
摘要翻译：在输入扫描系统中，如在数字复印机中所存在的那样，在一系列扫描图像中检测到类似的视觉元素或物体（诸如徽标和其他设计）的“模板”。公共对象形成参考图像，随后记录的输入图像被比较。如果输入图像中的对象周围的边框与参考图像中的边框相匹配，则尝试将边界框中的对象与参考图像中的对象进行匹配。如果输入图像和参考图像中的对象匹配，则使用指向参考图像中的相应对象的指针对来自输入图像的图像数据进行编码。

7. 发明授权

US08200043B2 Page orientation detection based on selective character recognition 失效
标题翻译：基于选择性字符识别的页面方位检测
公开(公告)号：US08200043B2
公开(公告)日：2012-06-12
申请号：US12113264
申请日：2008-05-01
申请人： Zhigang Fan , Michael R. Campanelli , Dennis Venable
发明人： Zhigang Fan , Michael R. Campanelli , Dennis Venable
IPC分类号： G06K9/20 , G06K9/32 , G06K9/36 , G06K15/00 , H04N1/40 , G09G5/00
CPC分类号： G06K9/3208 , G06K2209/01
摘要： A system and method for character recognition with document orientation determination is shown. The method is a detection of simple page orientation based on a limited version of character recognition. The method includes binairizing an input image which has a plurality of alphanumeric characters with a first orientation. The method continues with extracting the connected components and determining a second orientation where the second orientation is based on a 90° turn clockwise or counterclockwise or, in the alternative, no turn from the first orientation. The second orientation will result in a 180° variance from the proper orientation or it will be the proper orientation. The method continues with implementing a limited version of optical character recognition for an analysis of a character and determining if that second orientation is upside down, based at least in part on the analysis. This method generally uses the character “i” for analysis. However, for documents that have a limited number of “i”s, e.g. such as Russian documents or documents with all capital letters, the “T” may also be used.
摘要翻译：示出了用于文档取向确定的字符识别的系统和方法。该方法是基于有限版本的字符识别来检测简单的页面定向。该方法包括使具有第一取向的多个字母数字字符的输入图像。该方法继续提取连接的部件并且确定第二方向，其中第二方位是基于顺时针或逆时针方向的90°转弯，或者替代地，不与第一方向相反。第二个方向将导致与正确方向的180°偏差，否则将是正确的方向。该方法至少部分地基于分析，继续实施用于角色分析的有限版本的光学字符识别和确定该第二取向是否颠倒。该方法通常使用字符“i”进行分析。然而，对于具有有限数量的“i”的文档，例如，如所有大写字母的俄文文件或文件，也可以使用“T”。

8. 发明申请

US20090274392A1 PAGE ORIENTATION DETECTION BASED ON SELECTIVE CHARACTER RECOGNITION 失效
标题翻译：基于选择性字符识别的页面方向检测
公开(公告)号：US20090274392A1
公开(公告)日：2009-11-05
申请号：US12113264
申请日：2008-05-01
申请人： Zhigang Fan , Michael R. Campanelli , Dennis Venable
发明人： Zhigang Fan , Michael R. Campanelli , Dennis Venable
IPC分类号： G06K9/36
CPC分类号： G06K9/3208 , G06K2209/01
摘要： A system and method for character recognition with document orientation determination is shown. The method is a detection of simple page orientation based on a limited version of character recognition. The method includes binairizing an input image which has a plurality of alphanumeric characters with a first orientation. The method continues with extracting the connected components and determining a second orientation where the second orientation is based on a 90° turn clockwise or counterclockwise or, in the alternative, no turn from the first orientation. The second orientation will result in a 180° variance from the proper orientation or it will be the proper orientation. The method continues with implementing a limited version of optical character recognition for an analysis of a character and determining if that second orientation is upside down, based at least in part on the analysis. This method generally uses the character “i” for analysis. However, for documents that have a limited number of “i”s, e.g. such as Russian documents or documents with all capital letters, the “T” may also be used.
摘要翻译：示出了用于文档取向确定的字符识别的系统和方法。该方法是基于有限版本的字符识别来检测简单的页面定向。该方法包括使具有第一取向的多个字母数字字符的输入图像。该方法继续提取连接的部件并且确定第二方向，其中第二方位是基于顺时针或逆时针方向的90°转弯，或者替代地，不与第一方向相反。第二个方向将导致与正确方向的180°偏差，否则将是正确的方向。该方法至少部分地基于分析，继续实施用于角色分析的有限版本的光学字符识别和确定该第二取向是否颠倒。该方法通常使用字符“i”进行分析。然而，对于具有有限数量的“i”的文档，例如，如俄罗斯文件或所有大写字母的文件，也可以使用“T”。

9. 发明授权

US08619340B2 Augmenting page orientation direction detection in a digital document processing environment 有权
标题翻译：在数字文档处理环境中增强页面方向检测
公开(公告)号：US08619340B2
公开(公告)日：2013-12-31
申请号：US12915249
申请日：2010-10-29
申请人： Zhigang Fan , Michael R. Campanelli
发明人： Zhigang Fan , Michael R. Campanelli
IPC分类号： H04N1/40
CPC分类号： G06K9/3208 , G06K2209/01
摘要： What is disclosed is a novel system and method for augmenting present methods used for determining the orientation direction automatically being detected of digital pages of a plurality of scanned documents in a digital document processing environment. The present method takes advantage of the observation that pages scanned in data processing centers are often highly correlated. The present method contains five primary steps. 1) Page orientation (i.e., up/down) is detected using a traditional method. 2) Each page is classified as either directional or non-directional. 3) The pages classified as directional are clustered into groups. 4) The direction for each group is determined. 5) The directional group's direction is used to revise the orientation for pages contained in the group. Through the implementation of the teachings hereof, performance, in terms of both speed and accuracy, are very high relative to current methods and detection error rates can be reduced significantly.
摘要翻译：所公开的是一种新颖的系统和方法，用于增加用于确定在数字文档处理环境中自动检测到多个扫描文档的数字页面的取向方向的现有方法。本方法利用观察结果，数据处理中心扫描的页面通常是高度相关的。本方法包含五个主要步骤。 1）使用传统方法检测页面方向（即，上/下）。 2）每个页面被分类为定向或非定向。 3）分类为定向的页面被分组。 4）确定每组的方向。 5）定向组的方向用于修改组中包含的页面的方向。通过实施本文的教导，相对于当前的方法，速度和精度方面的性能都非常高，检测错误率可以显着降低。

10. 发明授权

US07991235B2 Light compression for color images using error diffusion 有权
标题翻译：使用误差扩散的彩色图像的光压缩
公开(公告)号：US07991235B2
公开(公告)日：2011-08-02
申请号：US11711110
申请日：2007-02-27
申请人： Zhigang Fan , Francis Tse , John Christopher Cassidy
发明人： Zhigang Fan , Francis Tse , John Christopher Cassidy
IPC分类号： G06K9/46 , G06K9/00 , G06K9/40 , H04N11/20 , H04N7/01 , H04N5/00
CPC分类号： H04N19/59 , H04N19/186 , H04N19/80 , H04N19/90
摘要： A light compression method that error diffuses image data provided with luminance and chrominance channels. During error diffusion, a higher number of bits are allocated to the luminance channel. A decompression method for the image data based on sigma filtering is also provided. By manipulating the bits in the luminance and chrominance color spaces, the image output quality may be increased in reconstructed images.
摘要翻译：一种光压缩方法，其误差扩散具有亮度和色度通道的图像数据。在误差扩散期间，较高数量的位被分配给亮度通道。还提供了基于西格玛滤波的图像数据的解压缩方法。通过操纵亮度和色度色彩空间中的比特，可以在重建图像中增加图像输出质量。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式