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。

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。

公开(公告)号：US08571698B2

公开(公告)日：2013-10-29

申请号：US12864870

申请日：2009-01-28

申请人： Jian Chen ,  Andy Eow ,  Xiaoxu Ma

发明人： Jian Chen ,  Andy Eow ,  Xiaoxu Ma

IPC分类号： G06F19/10

CPC分类号： G06F19/10 ,  G01B11/2513 ,  G06T7/579 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30208

摘要： Techniques which employ structure-from-motion modeling techniques to produce 3-D models of any desired accuracy of any surface I the techniques, a pattern is applied to the surface to be modeled The pattern includes elements which are unique within the pattern as applied to the surface and which have a density in the pattern such that when two-dimensional images are made of the surface, correlatable features having the density required for the desired accuracy may be extracted from the two dimensional images In one example of the techniques, a consumer may make the images required to produce a model of his or her body by donning a garment with a pattern having the necessary uniqueness and density, and then using any digital camera to take pictures of their body wearing the garment The model may then be produced from the pictures.

摘要翻译： 使用结构从运动建模技术产生任何表面任何所需精度的三维模型的技术我的技术，图案应用于要建模的表面图案包括在图案中独特的元素，如应用于 该表面具有图案中的密度，使得当由表面制成二维图像时，可以从二维图像中提取具有期望精度所需的密度的相关特征。在该技术的一个示例中，消费者 可以通过穿着具有必要的唯一性和密度的图案的衣服，然后使用任何数码相机拍摄穿着衣服的身体的照片来制作他或她的身体的模型所需的图像。然后可以从 图片。

公开(公告)号：US07885465B2

公开(公告)日：2011-02-08

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： G06K9/68 ,  G06K9/62 ,  G06K19/06 ,  G06F3/033

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。

公开(公告)号：US07136054B2

公开(公告)日：2006-11-14

申请号：US10753023

申请日：2004-01-06

申请人： Jian Wang ,  Liyong Chen ,  Yingnong Dang ,  Xiaoxu Ma

发明人： Jian Wang ,  Liyong Chen ,  Yingnong Dang ,  Xiaoxu Ma

IPC分类号： G09G5/00

CPC分类号： G06F3/03545 ,  G06F3/0321

摘要： X-y positions of a digital pen's tip may be determined by using a calibration parameter to map the x-y positions of the respective centers of images captured by the pen's camera. The calibration parameter may be generated by iteratively calculating estimates of the calibration parameter. Calibration input data may be produced by a user placing the pen tip in a fixed location on a surface, which may be a positionally encoded medium, such as paper, and then rotating the pen and/or moving the opposite end of the pen in various directions to capture multiple images for use in generating the calibration parameter. A user may perform such a calibration procedure without the need for complicated calibration equipment typically used in connection with conventional calibration techniques.

摘要翻译： 数字笔尖的X-Y位置可以通过使用校准参数来确定由笔的相机拍摄的各个中心的x-y位置来确定。 可以通过迭代地计算校准参数的估计来生成校准参数。 校准输入数据可以由用户将笔尖放置在表面上的固定位置（其可以是位置编码的介质，例如纸）然后旋转笔和/或使笔的相对端移动到各种 捕获多个图像以用于生成校准参数的方向。 用户可以执行这样的校准过程，而不需要通常结合常规校准技术使用的复杂校准设备。

公开(公告)号：US20050201621A1

公开(公告)日：2005-09-15

申请号：US10759357

申请日：2004-01-16

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： G06T1/00 ,  B60Q1/14 ,  G06F3/03 ,  G06F3/033 ,  G06F3/042 ,  G06K9/00 ,  G06K9/22 ,  G06K9/46 ,  G09G5/00

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。

公开(公告)号：US20050147281A1

公开(公告)日：2005-07-07

申请号：US10752081

申请日：2004-01-07

申请人： Jian Wang ,  Liyong Chen ,  Yingnong Dang ,  Qiang Wang ,  Xiaoxu Ma

发明人： Jian Wang ,  Liyong Chen ,  Yingnong Dang ,  Qiang Wang ,  Xiaoxu Ma

IPC分类号： G06K9/20 ,  G06F3/00 ,  G06F3/03 ,  G06F3/033 ,  G06F17/30 ,  G06K9/00 ,  G06K9/22 ,  G06K9/24 ,  G06K9/30 ,  G06K9/34 ,  G06K9/50 ,  G06K9/62 ,  G06T1/00 ,  G06T7/00 ,  G06T7/60

CPC分类号： G06F3/0321 ,  G06F3/03545 ,  G06K9/222 ,  G06K9/24 ,  G06T7/74

摘要： An efficient technique is disclosed for determining a portion of a document corresponding to a captured image. When a user employs a pen to create a stroke in a document, images of the document are captured by a camera mounted on the pen. While the location of some of the images will be determined from, for example, an analysis of a pattern on the document that is captured by the image or a pixel-by-pixel comparison of the image with the document, the location of other images will be determined by segmenting the sequence of images into groups that correspond to the shape of the stroke. Information relating to located images in a segment can then be employed to determine the position of unlocated images in the segment. For example, a document search region for an unlocated image can be established based upon the position of a previous located image and a maximum velocity or acceleration of the pen. The rotation and scale of the unlocated image are estimated as the same of the located image, and the unlocated image is warped using the rotation and scale. A pixel-by-pixel comparison can then be made between the warped unlocated image and the document search region. Further, if the warped unlocated image is matched successfully, the transform parameters of the image can be further refined.

摘要翻译： 公开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。 当用户使用笔在文档中创建笔画时，文档的图像由安装在笔上的相机捕获。 虽然一些图像的位置将通过例如对由图像捕获的文档上的图案或图像与文档的逐像素比较的分析来确定其他图像的位置 将通过将图像序列分割成对应于笔画形状的组来确定。 然后可以使用与片段中的定​​位图像相关的信息来确定片段中未定位图像的位置。 例如，可以基于先前定位的图像的位置和笔的最大速度或加速度来建立用于未定位图像的文档搜索区域。 未定位图像的旋转和缩放被估计为与所定位的图像相同，并且使用旋转和刻度来扭曲未定位的图像。 然后可以在翘曲的未定位图像和文档搜索区域之间进行逐像素比较。 此外，如果翘曲的未定位图像成功匹配，则可以进一步改进图像的变换参数。

公开(公告)号：US07995055B1

公开(公告)日：2011-08-09

申请号：US11753859

申请日：2007-05-25

申请人： Xiaoxu Ma ,  Lingyun Liu ,  Daniel Filip ,  Luc Vincent ,  Christopher R. Uhlik

发明人： Xiaoxu Ma ,  Lingyun Liu ,  Daniel Filip ,  Luc Vincent ,  Christopher R. Uhlik

IPC分类号： G06T17/00 ,  G06K9/00

CPC分类号： G06T17/00 ,  G06K9/00214 ,  G06K9/4604 ,  G06K9/6215 ,  G06T2210/56

摘要： In some implementations, a computer-implemented method of classifying image data includes receiving a plurality of data points corresponding to three-dimensional image data; creating from the plurality of data points a first subset of data points that are above a ground plane in a scene represented by the plurality of data points; identifying a second subset of data points associated with an object in the scene, from the first subset of data points; identifying a plurality of features associated with the second subset of data points and determining a signature for the identified plurality of features; and classifying the second set of data points according to a correspondence between the calculated signature and a reference signature.

摘要翻译： 在一些实施方式中，计算机实现的图像数据分类方法包括接收与三维图像数据对应的多个数据点; 从所述多个数据点创建在由所述多个数据点表示的场景中的地平面上方的数据点的第一子集; 从数据点的第一子集识别与场景中的对象相关联的数据点的第二子集; 识别与所述第二数据点子集相关联的多个特征并且确定所识别的多个特征的签名; 并且根据所计算的签名和参考签名之间的对应关系对第二组数据点进行分类。

公开(公告)号：US07684618B2

公开(公告)日：2010-03-23

申请号：US11385869

申请日：2006-03-22

申请人： Jian Wang ,  Yingnong Dang ,  Jiang Wu ,  Xiaoxu Ma

发明人： Jian Wang ,  Yingnong Dang ,  Jiang Wu ,  Xiaoxu Ma

IPC分类号： G06K9/34

CPC分类号： H04N19/94 ,  G06F3/03545

摘要： A system and method for encoding a document image and finding a location based on that image are described. A document page is encoded into codes associated with various locations of the document page. The codes are assembled into a code book. Captured images may then be similarly encoded and searched against the codes in the codebook. One or more codes and associated locations may be returned, thereby providing one or more possible locations for the captured images.

摘要翻译： 描述了用于对文档图像进行编码并基于该图像找到位置的系统和方法。 文档页面被编码成与文档页面的各个位置相关联的代码。 代码汇编成代码簿。 然后，捕获的图像可以相对于码本中的代码进行相似的编码和搜索。 可以返回一个或多个代码和相关联的位置，从而为捕获的图像提供一个或多个可能的位置。

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。