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

US07580576B2 Stroke localization and binding to electronic document 有权
标题翻译：笔画本地化和绑定到电子文档
公开(公告)号：US07580576B2
公开(公告)日：2009-08-25
申请号：US11142910
申请日：2005-06-02
申请人： Jian Wang , Jiang Wu , Liyong Chen , Qiang Wang , Yingnong Dang , Youjun Liu
发明人： Jian Wang , Jiang Wu , Liyong Chen , Qiang Wang , Yingnong Dang , Youjun Liu
IPC分类号： G06K9/00
CPC分类号： G06F3/038 , G06F3/03545
摘要： A method and apparatus for capturing information encoded within a surface, such as location information or document metadata, and associating the information with a document is described. The captured information may be obtained by a camera associated with a pointing or writing device having a camera, such as an image-capturing pen.
摘要翻译：描述用于捕获表面内编码的信息（诸如位置信息或文档元数据）以及将信息与文档相关联的方法和装置。捕获的信息可以通过与具有诸如图像捕获笔的相机的指示或写入装置相关联的相机获得。

2. 发明申请

US20060242622A1 Embedded interaction code recognition 有权
公开(公告)号：US20060242622A1
公开(公告)日：2006-10-26
申请号：US11112604
申请日：2005-04-22
申请人： Qiang Wang , Liyong Chen , Yingnong Dang , Jiang Wu , Jian Wang
发明人： Qiang Wang , Liyong Chen , Yingnong Dang , Jiang Wu , Jian Wang
IPC分类号： G06F9/44
CPC分类号： G06K7/1456 , G06F3/0321 , G06K7/14
摘要： In accordance with embodiments of the invention, embedded interaction code (EIC) symbols are recognized. EIC dots are generated based on effective EIC symbols, which have been generated by processing an image containing the EIC symbols, by obtaining graylevels of selected positions of the EIC-symbols. Rotated EIC dots are generated based on the EIC dots by determining which grid cells correspond to the EIC symbols and by determining which direction is a correct orientation of the EIC symbols. A homography matrix is updated with orientation information based on the EIC dots. EIC bits are extracted from the rotated EIC dots based on graylevels of selected positions of the rotated EIC dots.

3. 发明授权

US07529410B2 Local localization using fast image match 有权
标题翻译：本地本地化使用快速图像匹配
公开(公告)号：US07529410B2
公开(公告)日：2009-05-05
申请号：US10752081
申请日：2004-01-07
申请人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
发明人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
IPC分类号： G06K9/46 , G06K9/62 , G06F3/033 , G01B7/00
CPC分类号： G06F3/0321 , G06F3/03545 , G06K9/222 , G06K9/24 , G06T7/74
摘要： A technique is disclosed for determining a portion of a document corresponding to a captured image. A user employs a pen to create a stroke in a document, and images are captured by a camera mounted on the pen. The locations of some of the images are determined by, e.g., analyzing a pattern on the document captured by the image or by a pixel-by-pixel comparison of the image with the document. The locations of other images are determined by segmenting the sequence of images into groups corresponding to the shape of the stroke. Information relating to a located image in a segment is employed to determine the position of an unlocated image in the segment. This determined position is used for obtaining further information that may be used to determine the position of another unlocated image in the segment, and so on, until the segment is finished.
摘要翻译：公开了一种用于确定与拍摄图像相对应的文档的一部分的技术。用户使用笔在文档中创建笔画，并且图像由安装在笔上的相机捕获。一些图像的位置通过例如分析由图像捕获的文档上的图案或通过图像与文档的逐像素比较来确定。通过将图像序列分割成对应于笔画形状的组来确定其他图像的位置。使用与片段中的定位图像有关的信息来确定片段中未定位图像的位置。该确定的位置用于获得可用于确定片段中另一未定位图像的位置的其它信息，依此类推，直到片段完成。

4. 发明申请

US20060045307A1 Maze pattern analysis 有权
标题翻译：迷宫模式分析
公开(公告)号：US20060045307A1
公开(公告)日：2006-03-02
申请号：US10932803
申请日：2004-09-02
申请人： Liyong Chen , Yingnong Dang , Xiaoxu Ma , Jian Wang , Qiang Wang
发明人： Liyong Chen , Yingnong Dang , Xiaoxu Ma , Jian Wang , Qiang Wang
IPC分类号： G06K9/00
CPC分类号： G06F3/0321 , G06F3/03545 , G06T7/80 , H04N1/32208 , H04N2201/3269
摘要： Processes and apparatuses analyze an image of maze pattern in order to extract bits encoded in the maze pattern. Grid lines of a maze pattern are determined. Directions for effective pixels of associated bars are estimated and are grouped into clusters. Lines are estimated for selected effective pixels of a selected cluster that is associated with a first principal direction. Grid lines of another cluster are determined, where the other cluster is associated with a second principal direction that is perpendicular with the first principal direction. Estimated lines are pruned based on slope variation analysis, grouped based on a distance analysis, and a best fit line is selected from each group. Affine parameters are determined from best fit lines. The correct orientation of a maze pattern is obtained by determining a type of missing corner of the maze pattern. Bits are extracted from the image of maze pattern by processing gray level values of the associated maze pattern cells.
摘要翻译：过程和设备分析迷宫图案的图像，以便提取在迷宫图案中编码的比特。确定迷宫图案的网格线。估计关联条的有效像素的方向，并将其分组成簇。对于与第一主方向相关联的所选择的集群的所选有效像素估计行。确定另一个簇的网格线，其中另一个簇与与第一主方向垂直的第二主方向相关联。基于斜率变化分析修剪估计行，根据距离分析进行分组，并从每组中选择最佳拟合线。仿射参数由最佳拟合线确定。通过确定迷宫图案的缺失角落的类型，可以获得迷宫图案的正确方向。通过处理相关联的迷宫图案单元的灰度值，从迷宫图案的图像中提取位。

5. 发明授权

US07570813B2 Strokes localization by m-array decoding and fast image matching 失效
标题翻译：通过m阵列解码和快速图像匹配进行笔画定位
公开(公告)号：US07570813B2
公开(公告)日：2009-08-04
申请号：US11845584
申请日：2007-08-27
申请人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
发明人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
IPC分类号： G06K9/00
CPC分类号： G06F3/03545 , G06F3/0321
摘要： Systems and methods that determine a path of a pen tip as the pen tip is moved across a document are described. The document is watermarked with a maze pattern from which encoded position information is determined. A sequence of images is captured by a camera that is located in a pen. The path of the pen tip is determined by decoding the associated maze pattern and by matching the captured images with document images. If the position coordinates of any frame that is associated with a stroke cannot be determined from m-array decoding, the frames are transformed and then matched with an area of a document image. Once the position coordinates of at least one frame is determined, the position coordinates of other frames are determined by matching the frames in a neighboring area.
摘要翻译：描述当笔尖移动通过文档时确定笔尖的路径的系统和方法。文档用迷宫图案加水印，从而确定编码位置信息。图像序列由位于笔中的相机捕获。笔尖的路径通过解码相关联的迷宫图案并通过将拍摄的图像与文档图像相匹配来确定。如果不能从m阵列解码中确定与笔划相关联的任何帧的位置坐标，则将帧变换，然后与文档图像的区域匹配。一旦确定了至少一帧的位置坐标，则通过匹配相邻区域中的帧来确定其他帧的位置坐标。

6. 发明申请

US20090016614A1 GLOBAL LOCALIZATION BY FAST IMAGE MATCHING 有权
标题翻译：通过快速图像匹配进行全球定位
公开(公告)号：US20090016614A1
公开(公告)日：2009-01-15
申请号：US12211473
申请日：2008-09-16
申请人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
发明人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
IPC分类号： G06K9/64
CPC分类号： G06F3/03545 , G06F3/0321
摘要： An efficient technique is provided for determining a portion of a document corresponding to a captured image. Areas of a document in which the pattern is at least partially obscured are identified. A reference pixel in the image is selected, and an offset between the pixel and the pattern is determined. A pixel-by-pixel comparison is then made of the image with the document such that the reference pixel is only compared with locations in the document that are both within the identified areas and have the determined offset from the pattern. The comparison with the highest correspondence between the image pixels and the electronic document then identifies the position of the reference pixel relative to the electronic document.
摘要翻译：提供了一种用于确定与捕获图像相对应的文档的一部分的有效技术。识别出图案至少部分模糊的文档的区域。选择图像中的参考像素，并且确定像素和图案之间的偏移。然后，对具有文档的图像进行逐像素比较，使得仅将参考像素与文档中位于所识别的区域内的位置进行比较，并且具有从图案确定的偏移。与图像像素和电子文档之间的最高对应关系的比较然后识别参考像素相对于电子文档的位置。

7. 发明授权

US07430497B2 Statistical model for global localization 有权
标题翻译：全球定位统计模型
公开(公告)号：US07430497B2
公开(公告)日：2008-09-30
申请号：US10284421
申请日：2002-10-31
申请人： Jian Wang , Zheng Chen , Xiaoxu Ma , Yingnong Dang , Liyong Chen , Jiang Wu
发明人： Jian Wang , Zheng Chen , Xiaoxu Ma , Yingnong Dang , Liyong Chen , Jiang Wu
IPC分类号： G06F17/00
CPC分类号： G06F3/03545 , G06F3/0321 , G06K9/222
摘要： A system and process for determining the location of a captured image from a larger image is described. Using a list of determined locations, the system is able to determine the best or most likely path of a pen tip.
摘要翻译：描述用于确定来自较大图像的拍摄图像的位置的系统和过程。使用确定位置的列表，系统能够确定笔尖的最佳或最可能的路径。

8. 发明授权

US07349554B2 Maze pattern analysis 有权
标题翻译：迷宫模式分析
公开(公告)号：US07349554B2
公开(公告)日：2008-03-25
申请号：US10932803
申请日：2004-09-02
申请人： Liyong Chen , Yingnong Dang , Xiaoxu Ma , Jian Wang , Qiang Wang
发明人： Liyong Chen , Yingnong Dang , Xiaoxu Ma , Jian Wang , Qiang Wang
IPC分类号： H04K1/00
CPC分类号： G06F3/0321 , G06F3/03545 , G06T7/80 , H04N1/32208 , H04N2201/3269
摘要： Processes and apparatuses analyze an image of maze pattern in order to extract bits encoded in the maze pattern. Grid lines of a maze pattern are determined. Directions for effective pixels of associated bars are estimated and are grouped into clusters. Lines are estimated for selected effective pixels of a selected cluster that is associated with a first principal direction. Grid lines of another cluster are determined, where the other cluster is associated with a second principal direction that is perpendicular with the first principal direction. Estimated lines are pruned based on slope variation analysis, grouped based on a distance analysis, and a best fit line is selected from each group. Affine parameters are determined from best fit lines. The correct orientation of a maze pattern is obtained by determining a type of missing corner of the maze pattern. Bits are extracted from the image of maze pattern by processing gray level values of the associated maze pattern cells.
摘要翻译：过程和设备分析迷宫图案的图像，以便提取在迷宫图案中编码的比特。确定迷宫图案的网格线。估计关联条的有效像素的方向，并将其分组成簇。对于与第一主方向相关联的所选择的集群的所选有效像素估计行。确定另一个簇的网格线，其中另一个簇与与第一主方向垂直的第二主方向相关联。基于斜率变化分析修剪估计行，根据距离分析进行分组，并从每组中选择最佳拟合线。仿射参数由最佳拟合线确定。通过确定迷宫图案的缺失角落的类型，可以获得迷宫图案的正确方向。通过处理相关联的迷宫图案单元的灰度值，从迷宫图案的图像中提取位。

9. 发明申请

US20080025612A1 Strokes Localization by m-Array Decoding and Fast Image Matching 失效
标题翻译：通过m阵列解码和快速图像匹配进行笔画定位
公开(公告)号：US20080025612A1
公开(公告)日：2008-01-31
申请号：US11845584
申请日：2007-08-27
申请人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
发明人： Jian Wang , Yingnong Dang , Qiang Wang , Liyong Chen , Xiaoxu Ma
IPC分类号： G06K9/00
CPC分类号： G06F3/03545 , G06F3/0321
摘要： Systems and methods that determine a path of a pen tip as the pen tip is moved across a document are described. The document is watermarked with a maze pattern from which encoded position information is determined. A sequence of images is captured by a camera that is located in a pen. The path of the pen tip is determined by decoding the associated maze pattern and by matching the captured images with document images. If the position coordinates of any frame that is associated with a stroke cannot be determined from m-array decoding, the frames are transformed and then matched with an area of a document image. Once the position coordinates of at least one frame is determined, the position coordinates of other frames are determined by matching the frames in a neighboring area.
摘要翻译：描述当笔尖移动通过文档时确定笔尖的路径的系统和方法。文档用迷宫图案加水印，从而确定编码位置信息。图像序列由位于笔中的相机捕获。笔尖的路径通过解码相关联的迷宫图案并通过将拍摄的图像与文档图像相匹配来确定。如果不能从m阵列解码中确定与笔划相关联的任何帧的位置坐标，则将帧变换，然后与文档图像的区域匹配。一旦确定了至少一帧的位置坐标，则通过匹配相邻区域中的帧来确定其他帧的位置坐标。

10. 发明申请

US20070003150A1 Embedded interaction code decoding for a liquid crystal display 有权
标题翻译：用于液晶显示器的嵌入式交互码解码
公开(公告)号：US20070003150A1
公开(公告)日：2007-01-04
申请号：US11169744
申请日：2005-06-30
申请人： An Xu , Chunhui Zhang , Jian Wang , Liyong Chen , Qiang Wang , Yingnong Dang
发明人： An Xu , Chunhui Zhang , Jian Wang , Liyong Chen , Qiang Wang , Yingnong Dang
IPC分类号： G06K9/36
CPC分类号： G06F3/03545
摘要： A method and system for decoding data on a medium that is captured by an input device is described. The method decodes a symbol design, such as an embedded interaction code (EIC), on a display screen, such as a liquid crystal display (LCD). An image that is captured by an input device, such as a universal pen-type input device with a camera, is received. The captured image is processed to output an extracted bit stream. Position data and/or metadata information is decoded from the extracted bit stream and a position of the captured image with respect to a screen of the LCD is determined based upon the decoded position data. The EIC pattern may be recognized from LCD pixel grids and a bit stream of EIC bits may be extracted based upon the recognized EIC pattern.
摘要翻译：描述用于对由输入装置捕获的介质上的数据进行解码的方法和系统。该方法在诸如液晶显示器（LCD）的显示屏上解码符号设计，例如嵌入式交互码（EIC）。接收由输入装置拍摄的图像，例如具有照相机的通用笔型输入装置。捕获的图像被处理以输出提取的比特流。位置数据和/或元数据信息从提取的比特流解码，并且基于解码的位置数据确定捕获图像相对于LCD的屏幕的位置。可以从LCD像素网格识别EIC图案，并且可以基于所识别的EIC图案来提取EIC位的比特流。

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