公开(公告)号：US07715657B2

公开(公告)日：2010-05-11

申请号：US11276196

申请日：2006-02-17

申请人： Zhouchen Lin ,  Liang Wan ,  Wei Feng ,  Tien-Tsin Wong ,  Zhi-Qiang Liu

发明人： Zhouchen Lin ,  Liang Wan ,  Wei Feng ,  Tien-Tsin Wong ,  Zhi-Qiang Liu

IPC分类号： G06K9/32 ,  G06K9/36 ,  G06K9/40 ,  G06F3/048

CPC分类号： G06T3/40 ,  G06T2207/20008

摘要： Systems and methods for perceptual image preview are described. In one aspect, a naïve preview image is generated by downsampling a larger image. Perceptual features of the larger image are then detected. Information associated with the detected perceptual features is then incorporated into the naïve preview image to create a perceptual preview image. Since the perceptual preview image incorporates information associated with the detected perceptual features, a viewer of the perceptual preview image will be more likely to detect the presence or absence of such perceptual features in the larger image.

摘要翻译： 描述了感知图像预览的系统和方法。 在一个方面，通过对更大的图像进行下采样来生成天真的预览图像。 然后检测较大图像的感知特征。 与检测到的感知特征相关联的信息然后被合并到初始预览图像中以创建感知预览图像。 由于感知预览图像包含与检测到的感知特征相关联的信息，感知预览图像的观看者将更可能检测更大图像中这种感知特征的存在或不存在。

公开(公告)号：US20100076723A1

公开(公告)日：2010-03-25

申请号：US12235927

申请日：2008-09-23

申请人： Wei Zhang ,  Zhouchen Lin ,  Xiaoou Tang

发明人： Wei Zhang ,  Zhouchen Lin ,  Xiaoou Tang

IPC分类号： G06F17/18 ,  G06F15/00 ,  G06F7/32 ,  G06F17/30

CPC分类号： G06F17/30598 ,  G06K9/6234

摘要： Tensor linear Laplacian discrimination for feature extraction is disclosed. One embodiment comprises generating a contextual distance based sample weight and class weight, calculating a within-class scatter using the at least one sample weight and a between-class scatter for multiple classes of data samples in a sample set using the class weight, performing a mode-k matrix unfolding on scatters and generating at least one orthogonal projection matrix.

摘要翻译： 公开了用于特征提取的张量线性拉普拉斯判别。 一个实施例包括生成基于上下文距离的样本权重和类权重，使用所述至少一个样本权重来计算类内散度，以及使用类权重在样本集合中的多类数据样本之间进行类间散射，执行 mode-k矩阵在散射上展开并生成至少一个正交投影矩阵。

公开(公告)号：US07664325B2

公开(公告)日：2010-02-16

申请号：US11314554

申请日：2005-12-21

申请人： Zhouchen Lin ,  Junfeng He ,  Zhicheng Zhong ,  Chun-Hui Hu ,  Jian Wang

发明人： Zhouchen Lin ,  Junfeng He ,  Zhicheng Zhong ,  Chun-Hui Hu ,  Jian Wang

IPC分类号： G06K9/18

CPC分类号： G06K9/00416 ,  G06K9/00449

摘要： Computer-readable media having computer-executable instructions and apparatuses detect a structured handwritten object is detected in a handwritten document. A primitive structure, which is associated with a set of component objects, is formed. A candidate handwritten object is identified by detecting a corresponding logical structure. A classifier for the candidate handwritten object is determined. Consequently, the candidate handwritten object is validated from the classifier.

摘要翻译： 具有计算机可执行指令和装置的计算机可读介质检测结构化手写对象在手写文档中被检测。 形成与一组组件对象相关联的原始结构。 通过检测相应的逻辑结构来识别候选手写对象。 确定候选手写物体的分类器。 因此，候选手写对象从分类器得到验证。

公开(公告)号：US07609271B2

公开(公告)日：2009-10-27

申请号：US11428195

申请日：2006-06-30

申请人： Zhouchen Lin ,  Lifeng Wang ,  Yunbo Wang ,  Jian Wang ,  Xiaoou Tang

发明人： Zhouchen Lin ,  Lifeng Wang ,  Yunbo Wang ,  Jian Wang ,  Xiaoou Tang

IPC分类号： G06T13/00

CPC分类号： G06T13/80 ,  G09G5/00 ,  G09G2340/0414 ,  G09G2340/0421

摘要： A strategy is described for producing an animated scene from multiple high resolution still images. The strategy involves: creating a graph based on an analysis of similarity among the plural still images; performing partial temporal order recovery to define a partial ordering among the plural still images; and extracting an output sequence from the plural still images using second-order Markov Chain analysis, using the partial ordering as a reference. The strategy can perform the above-described analysis with respect to multiple independent animated regions (IARs) within the still images. Further, the strategy can decompose any IAR with a significant amount of motion into multiple semi-independent animated regions (SIARs). The SIARs are defined to be weakly interdependent.

摘要翻译： 描述了从多个高分辨率静止图像生成动画场景的策略。 该策略涉及：基于对多个静止图像之间的相似性的分析来创建图; 执行部分时间顺序恢复以限定所述多个静止图像中的部分排序; 以及使用部分排序作为参考，使用二阶马尔可夫链分析从多个静止图像中提取输出序列。 该策略可以针对静止图像内的多个独立动画区域（IAR）执行上述分析。 此外，该策略可以将具有大量运动的任何IAR分解成多个半独立动画区域（SIAR）。 SIAR被定义为弱相互依赖。

公开(公告)号：US07567711B2

公开(公告)日：2009-07-28

申请号：US11195580

申请日：2005-08-01

申请人： Zhouchen Lin

发明人： Zhouchen Lin

IPC分类号： G06K9/00

CPC分类号： G06K9/00416

摘要： A method and system for cleaning handwriting for redisplay of the handwriting or for improved recognition accuracy is provided. The cleanup system receives handwriting that has been digitized. The cleanup system then analyzes the handwriting to identify strokes that satisfy a cleanup criterion. When a stroke has been identified as satisfying some cleanup criteria, the cleanup system cleans up the handwriting based on the detected criteria. In this way, the cleanup system generates handwriting that may have a more visually pleasing appearance to the reader.

摘要翻译： 提供了一种用于清除笔迹以重新显示笔迹或提高识别精度的方法和系统。 清理系统接收已经数字化的手写。 清理系统然后分析笔迹以识别满足清理标准的笔画。 当中风被确定为满足一些清理标准时，清理系统将根据检测到的标准清除手写。 以这种方式，清理系统产生可能对读者更加视觉上令人满意的外观的手写。

公开(公告)号：US20090119573A1

公开(公告)日：2009-05-07

申请号：US12180484

申请日：2008-07-25

申请人： Jian Wang ,  Zhouchen Lin ,  Yue Li ,  Chunhui Zhang ,  Yingnong Dang ,  Jiang Wu ,  Qiang Wang

发明人： Jian Wang ,  Zhouchen Lin ,  Yue Li ,  Chunhui Zhang ,  Yingnong Dang ,  Jiang Wu ,  Qiang Wang

IPC分类号： G06F17/00

CPC分类号： G06F17/242 ,  G06F3/0321 ,  G06F3/03545

摘要： In accordance with embodiments of the invention, global metadata, such as a document identifier, which may be a globally unique identifier, is embedded into an embedded interactive code document by combining a first m-array and a plurality of copies of the first m-array to generate a combined m-array with encoded global metadata such that respective start positions (xd,yd)i of the plurality of copies of the first m-array in the combined m-array are each shifted, by respective amounts that are based on respective portions of the global metadata, relative to a start position of the first m-array in the combined m-array. Global metadata may be decoded from the combined m-array by determining the respective amounts by which the plurality of copies of the first m-array are shifted, relative to the first m-array, in the combined m-array and by combining the respective amounts to produce a decoded value of the global metadata.

摘要翻译： 根据本发明的实施例，通过组合第一m阵列和第一m-阵列的多个副本，将嵌入式交互式代码文档中的全局元数据（诸如可以是全局唯一标识符的文档标识符）嵌入到嵌入式交互式代码文档中， 阵列以生成具有编码的全局元数据的组合m阵列，使得组合的m阵列中的第一m阵列的多个副本中的相应起始位置（xd，yd）i各自偏移基于 在全局元数据的相应部分上相对于组合的m阵列中的第一m阵列的开始位置。 可以通过确定在组合的m阵列中第一m阵列的多个副本相对于第一m阵列移位的相应量，并通过组合相应的数组来组合全局元数据 相当于产生全局元数据的解码值。

公开(公告)号：US20090080774A1

公开(公告)日：2009-03-26

申请号：US11860428

申请日：2007-09-24

申请人： Zhouchen Lin ,  Guangcan Liu ,  Xiaoou Tang

发明人： Zhouchen Lin ,  Guangcan Liu ,  Xiaoou Tang

IPC分类号： G06K9/34

CPC分类号： G06K9/34 ,  G06K9/342 ,  G06K9/6296 ,  G06T7/11 ,  G06T7/162 ,  G06T7/194

摘要： This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.

摘要翻译： 本公开描述了用于无人监督的对象分割的集成框架。 通过以集成的方式使用算法将自上而下的约束和自下而上的对象形状约束集成在一起，进行类无监督对象分割。 该算法描述了对象部分和超像素之间的关系。 该过程通过对象部分形成对象形状，并将像素图像监视到超像素中，该算法与约束相结合。 本公开描述了从混合图计算掩模图，将图像分割成前景对象和背景，以及从背景显示前景对象。

公开(公告)号：US07505606B2

公开(公告)日：2009-03-17

申请号：US11132865

申请日：2005-05-19

申请人： Zhouchen Lin ,  Rongrong Wang ,  Xiaoou Tang ,  Heung-Yeung Shum

发明人： Zhouchen Lin ,  Rongrong Wang ,  Xiaoou Tang ,  Heung-Yeung Shum

IPC分类号： G06K9/00

CPC分类号： G06K9/00 ,  G06K9/00899

摘要： Embodiments of the invention determine whether an image has been altered. Sets of patches are selected in the image, and corresponding inverse response functions are provided to a support vector machine (SVM). The support vector machine is trained with exemplary normal and abnormal inverse response functions. Once trained, the support vector machine analyzes inverse response functions corresponding to a suspected image. The support vector machine determines if the inverse response functions are normal or abnormal by analyzing a set of features. In one embodiment, features include measures for monotonic characteristics, fluctuation characteristics, and divergence characteristics of the red, green, and blue components of a tuple. Each tuple of inverse response functions is associated with a set of patches selected in the image.

摘要翻译： 本发明的实施例确定图像是否已被改变。 在图像中选择一组补丁，并将相应的反应函数提供给支持向量机（SVM）。 支持向量机用示例性正常和异常的反应函数进行训练。 训练后，支持向量机分析与疑似图像相对应的反应响应函数。 支持向量机通过分析一组特征来确定逆响应函数是正常还是异常。 在一个实施例中，特征包括用于元组的红，绿和蓝分量的单调特性，波动特性和发散特性的度量。 反向响应函数的每个元组与在图像中选择的一组补丁相关联。

公开(公告)号：US07421439B2

公开(公告)日：2008-09-02

申请号：US11112672

申请日：2005-04-22

申请人： Jian Wang ,  Zhouchen Lin ,  Yue Li ,  Chunhui Zhang ,  Yingnong Dang ,  Jiang Wu ,  Qiang Wang

发明人： Jian Wang ,  Zhouchen Lin ,  Yue Li ,  Chunhui Zhang ,  Yingnong Dang ,  Jiang Wu ,  Qiang Wang

IPC分类号： G06F7/00 ,  G06F17/00 ,  G06K9/00

CPC分类号： G06F17/242 ,  G06F3/0321 ,  G06F3/03545

摘要： Global metadata, such as a document identifier, which may be a globally unique identifier, is embedded into an embedded interactive code document by combining a first m-array and a plurality of copies of the first m-array to generate a combined m-array with encoded global metadata such that respective start positions (xd,yd)i of the plurality of copies of the first m-array in the combined m-array are each shifted, by respective amounts that are based on respective portions of the global metadata, relative to a start position of the first m-array in the combined m-array. Global metadata may be decoded from the combined m-array by determining the respective amounts by which the plurality of copies of the first m-array are shifted, relative to the first m-array, in the combined m-array and by combining the respective amounts to produce a decoded value of the global metadata.

摘要翻译： 通过组合第一m阵列和第一m阵列的多个副本来将全局元数据（诸如可以是全球唯一标识符的文档标识符）嵌入到嵌入式交互式代码文档中以生成组合的m阵列 具有编码的全局元数据，使得第一m阵列的多个拷贝的相应开始位置（x，d，i，...， 组合的m阵列相对于组合的m阵列中的第一m阵列的开始位置而被移位，相应于基于全局元数据的相应部分的量。 可以通过确定在组合的m阵列中第一m阵列的多个副本相对于第一m阵列移位的相应量，并通过组合相应的数组来组合全局元数据 相当于产生全局元数据的解码值。

公开(公告)号：US20080001950A1

公开(公告)日：2008-01-03

申请号：US11428195

申请日：2006-06-30

申请人： Zhouchen Lin ,  Lifeng Wang ,  Yunbo Wang ,  Jian Wang ,  Xiaoou Tang

发明人： Zhouchen Lin ,  Lifeng Wang ,  Yunbo Wang ,  Jian Wang ,  Xiaoou Tang

IPC分类号： G06T13/00

CPC分类号： G06T13/80 ,  G09G5/00 ,  G09G2340/0414 ,  G09G2340/0421

摘要： A strategy is described for producing an animated scene from multiple high resolution still images. The strategy involves: creating a graph based on an analysis of similarity among the plural still images; performing partial temporal order recovery to define a partial ordering among the plural still images; and extracting an output sequence from the plural still images using second-order Markov Chain analysis, using the partial ordering as a reference. The strategy can perform the above-described analysis with respect to multiple independent animated regions (IARs) within the still images. Further, the strategy can decompose any IAR with a significant amount of motion into multiple semi-independent animated regions (SIARs). The SIARs are defined to be weakly interdependent.

摘要翻译： 描述了从多个高分辨率静止图像生成动画场景的策略。 该策略涉及：基于对多个静止图像之间的相似性的分析来创建图; 执行部分时间顺序恢复以限定所述多个静止图像中的部分排序; 以及使用部分排序作为参考，使用二阶马尔可夫链分析从多个静止图像中提取输出序列。 该策略可以针对静止图像内的多个独立动画区域（IAR）执行上述分析。 此外，该策略可以将具有大量运动的任何IAR分解成多个半独立动画区域（SIAR）。 SIAR被定义为弱相互依赖。