公开(公告)号：US20110194725A1

公开(公告)日：2011-08-11

申请号：US12701290

申请日：2010-02-05

申请人： Mithun Das Gupta ,  Jing Xiao

发明人： Mithun Das Gupta ,  Jing Xiao

IPC分类号： G06K9/00

CPC分类号： G06K19/06037

摘要： A watermarking system uses distinct bit patterns to identify a logic 0, a logic 1, and a marker bit, which demarcates segments of logic bit information. Marker bits, which are printed on both foreground and background areas of an image, outline message blocks. In message extraction, a preprocessing step removes any white boarders, identifies the best defined corner of a message block, crops the image, and rotates the image to place the identified corner at the top-left corner. Message extraction scans the rotated image in window segments of increasing size during multiple cycles. During each cycle, if a bit pattern cannot be identified as a data bit, then the size of the examined bit area is increased and rechecked to see it specifically is a marker bit. If no bit information can be definitively identified, then it is assigned a logic bit value based on a 50% random assignment.

摘要翻译： 水印系统使用不同的位模式来识别逻辑0，逻辑1和标记位，其标记逻辑位信息的段。 打印在图像的前景和背景区域上的标记位轮廓消息块。 在消息提取中，预处理步骤删除任何白色寄宿生，识别消息块的最佳定义角，裁剪图像，并旋转图像以将识别的角落放置在左上角。 消息提取在多个周期内以增加大小的窗口段扫描旋转后的图像。 在每个周期中，如果位模式不能被识别为数据位，则检查的位区域的大小将被增加并重新检查，以查看它是否具体是标记位。 如果不能确定位信息，则根据50％的随机分配给它分配一个逻辑位值。

公开(公告)号：US20110191400A1

公开(公告)日：2011-08-04

申请号：US12853886

申请日：2010-08-10

申请人： Mithun Das Gupta ,  Jing Xiao ,  Sanjeev Kumar

发明人： Mithun Das Gupta ,  Jing Xiao ,  Sanjeev Kumar

IPC分类号： G06F17/16 ,  G06F15/18

CPC分类号： G06F15/18 ,  G06F17/16

摘要： Similarities between simplex projection with upper bounds and L1 projection are explored. Criteria for a-priori determination of sequence in which various constraints become active are derived, and this sequence is used to develop efficient algorithms for projecting a vector onto the L1-ball while observing box constraints. Three projection methods are presented. The first projection method performs exact projection in O(n2) worst case complexity, where n is the space dimension. Using a novel criteria for ordering constraints, the second projection method has a worst case complexity of O(n log n). The third projection method is a worst case linear time algorithm having O(n) complexity. The upper bounds defined for the projected entries guide the L1-ball projection to more meaningful predictions.

摘要翻译： 探讨了单面投影与上界和L1投影之间的相似性。 导出先验确定各种约束变为有效的序列的标准，并且该序列用于开发用于在观察盒约束的情况下将向量投影到L1球上的有效算法。 提出了三种投影方法。 第一种投影方法在O（n2）最差情况复杂度中执行精确投影，其中n是空间维数。 使用新颖的排序约束条件，第二种投影方法具有O（n log n）的最差情况复杂度。 第三种投影方法是具有O（n）复杂度的最差情况线性时间算法。 为投影条目定义的上限将引导L1球投影更有意义的预测。

公开(公告)号：US07894689B2

公开(公告)日：2011-02-22

申请号：US11756517

申请日：2007-05-31

申请人： Che-Bin Liu ,  Jing Xiao

发明人： Che-Bin Liu ,  Jing Xiao

IPC分类号： G06K9/36

CPC分类号： G06T7/33 ,  G06T2200/32 ,  G06T2207/10008 ,  G06T2207/20164 ,  G06T2207/30176

摘要： Disclosed are embodiments of systems and methods to stitch two or more images together into a composite image. By finding matching point pairs for a pair of images, a homography transform may be obtained for the pair of images. The homography transform may be used to generate a composite image of the image pair. In an embodiment, the process of identifying a homography transform may be iterated. In an embodiment, when forming the composite image, the transformed foreground regions may be selected such that there is no intersection of foreground pixel regions. In an embodiment, foreground pixel regions on the border of an image may be removed. The resulting composite image is a larger image generated from the selected regions from the input images. In embodiments, the process may be repeated for sets of images with more than two images.

摘要翻译： 公开了将两个或多个图像拼接成合成图像的系统和方法的实施例。 通过找到一对图像的匹配点对，可以获得该对图像的单应变换。 单变形变换可用于生成图像对的合成图像。 在一个实施例中，可以迭代识别单变形变换的过程。 在一个实施例中，当形成合成图像时，可以选择变换的前景区域，使得不存在前景像素区域的交集。 在一个实施例中，可以去除图像边界上的前景像素区域。 所得到的合成图像是从输入图像从所选择的区域生成的较大图像。 在实施例中，可以对具有多于两个图像的图像集重复该过程。

公开(公告)号：US20100253915A1

公开(公告)日：2010-10-07

申请号：US12418137

申请日：2009-04-03

申请人： Chunyu Gao ,  Jing Xiao

发明人： Chunyu Gao ,  Jing Xiao

IPC分类号： G02B27/22 ,  G03B21/60

CPC分类号： G03B21/60 ,  G02B27/225

摘要： Aspects of the present invention involve novel display screens comprising light diffusion and retro-reflectivity. In embodiments, a retro-reflective light diffusion screen can be used to generate a three-dimensional autostereoscopic display by generating a plurality of viewing windows wherein each viewing window depicts a unique perspective image view.

摘要翻译： 本发明的方面涉及包括光扩散和反射反射性的新型显示屏。 在实施例中，可以使用回射光扩散屏幕来产生三维自动立体显示器，通过产生多个观看窗口，其中每个观看窗口描绘了独特的透视图像视图。

公开(公告)号：US20100215255A1

公开(公告)日：2010-08-26

申请号：US12392820

申请日：2009-02-25

申请人： Jing Xiao ,  Derek Shiell

发明人： Jing Xiao ,  Derek Shiell

IPC分类号： G06K9/62 ,  G06T15/00

CPC分类号： G06K9/00281 ,  G06K9/621

摘要： Aspects of the present invention include systems and methods for forming generative models, for utilizing those models, or both. In embodiments, an object model fitting system can be developed comprising a 3D active appearance model (AAM) model. The 3D AAM comprises an appearance model comprising a set of subcomponent appearance models that is constrained by a 3D shape model. In embodiments, the 3D AAM may be generated using a balanced set of training images. The object model fitting system may further comprise one or more manifold constraints, one or more weighting factors, or both. Applications of the present invention include, but are not limited to, modeling and/or fitting face images, although the teachings of the present invention can be applied to modeling/fitting other objects.

摘要翻译： 本发明的方面包括用于形成生成模型的系统和方法，用于利用这些模型或两者。 在实施例中，可以开发包括3D活动外观模型（AAM）模型的对象模型拟合系统。 3D AAM包括由3D形状模型约束的一组子组件外观模型的外观模型。 在实施例中，可以使用平衡的训练图像集来生成3D AAM。 对象模型拟合系统还可以包括一个或多个歧管约束，一个或多个加权因子，或两者。 本发明的应用包括但不限于建模和/或配合面部图像，尽管本发明的教导可以应用于建模/拟合其他对象。

公开(公告)号：US20090060354A1

公开(公告)日：2009-03-05

申请号：US11846343

申请日：2007-08-28

申请人： Jing Xiao ,  Anoop K. Bhattacharjya

发明人： Jing Xiao ,  Anoop K. Bhattacharjya

IPC分类号： G06K9/36

CPC分类号： H04N1/41 ,  H04N1/40062 ,  H04N1/64

摘要： Disclosed are embodiments of systems, devices, and methods to reduce compression artifacts in multi-layer images. Pixel dilation operations, such as morphological dilations, are performed to identify unlabeled pixels at boundaries between layers, and the colors of those pixels are adjusted to mitigate formation of artifacts during layer compression.

摘要翻译： 公开了减少多层图像中的压缩伪影的系统，装置和方法的实施例。 执行诸如形态学扩张的像素扩张操作以识别层之间边界处的未标记像素，并且调整那些像素的颜色以减轻层压缩期间的伪像的形成。

公开(公告)号：US20090046931A1

公开(公告)日：2009-02-19

申请号：US11891781

申请日：2007-08-13

申请人： Jing Xiao ,  Anoop K. Bhattacharjya

发明人： Jing Xiao ,  Anoop K. Bhattacharjya

IPC分类号： G06K9/34

CPC分类号： G06K9/38 ,  G06K2209/01 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/30176

摘要： Disclosed are embodiments of systems and methods for segmenting an image into at least two layers, a foreground and a background layer. An embodiment of the present invention includes rough labeling or segmenting at least a portion of the image into foreground and background pixels. The rough labeled pixels may be refined by using local classifications. In embodiments, additional processes may be performed on the image including, but not limited to, filtering, image enhancing, shape refining, image compression, etc.

摘要翻译： 公开了用于将图像分割成至少两个层，前景和背景层的系统和方法的实施例。 本发明的实施例包括将图像的至少一部分粗略标记或分割成前景和背景像素。 可以通过使用本地分类来改进粗略标记的像素。 在实施例中，可以对图像执行附加处理，包括但不限于过滤图像增强，形状精炼，图像压缩等。

公开(公告)号：US07460733B2

公开(公告)日：2008-12-02

申请号：US11215419

申请日：2005-08-30

申请人： Jing Xiao ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

发明人： Jing Xiao ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

IPC分类号： G06K9/32

CPC分类号： G06K9/00127 ,  G06K9/00221 ,  G06K9/00973 ,  G06T7/149

摘要： A method of registering and modeling a deformable shape in a digitized image is provided, comprising the steps of providing a measurement matrix W of N measurements of P points of a D-dimensional deformable shape, determining a basis number K for the N measurements, wherein K

公开(公告)号：US20060045347A1

公开(公告)日：2006-03-02

申请号：US11215419

申请日：2005-08-30

申请人： Jing Xiao ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

发明人： Jing Xiao ,  Bogdan Georgescu ,  Xiang Zhou ,  Dorin Comaniciu

IPC分类号： G06K9/46

CPC分类号： G06K9/00127 ,  G06K9/00221 ,  G06K9/00973 ,  G06T7/149

摘要： A method of registering and modeling a deformable shape in a digitized image is provided, comprising the steps of providing a measurement matrix W of N measurements of P points of a D-dimensional deformable shape, determining a basis number K for the N measurements, wherein K

公开(公告)号：US06662167B1

公开(公告)日：2003-12-09

申请号：US09461962

申请日：1999-12-15

申请人： Jing Xiao

发明人： Jing Xiao

IPC分类号： G06N300

CPC分类号： G06N3/126 ,  Y10S706/912

摘要： The present invention provides a method utilizing evolutionary processes for solving partial constraint satisfaction problems in order to produce a near-optimal or optimal sequence of products for manufacture. More specifically, a computer implemented method for generating an optimized sequence of “N” number of products for manufacture is provided, where said products are of “M” number of distinct types with a fixed number (“Nt”) of each type being desired and each product type comprising an array (“Q”) of distinct features, wherein said manufacture is optionally constrained by one or more of the following constraints: the production requirement for each product type, feature-based position equations, and feature-based position inequalities, wherein each of said constraints is individually designated as either a hard constraint which cannot be violated, or as a soft constraint which can be violated at a predetermined cost; said method comprising: generating an initial population of chromosomes, wherein each chromosome represents a feasible sequence of products of various types for manufacture, feasibility depending on satisfaction of all of said hard constraints; associating a fitness value with each chromosome, said fitness value being a function of the predetermined cost associated with the degree of violation of each of said soft constraints; sorting said chromosomes based on the fitness value associated with each chromosome; and applying iteratively to the population of chromosomes a reproductive process, comprising (1) selection of a genetic operator, (2) selection of one or two chromosomes, the number of chromosomes to be selected correlating with the selected genetic operator, (3) application of the selected genetic operator to the selected one or two chromosomes to cause generation of one or two offspring, (4) insertion of one offspring chromosome into the sorted population, and (5) discard of one of the least desirable chromosomes in the population; said iterative process being continuously run until the fitness value for the best chromosome satisfies a known criterion or until a pre-determined time has elapsed.