公开(公告)号：US08977648B2

公开(公告)日：2015-03-10

申请号：US13443615

申请日：2012-04-10

申请人： Derek Shiell ,  Jing Xiao

发明人： Derek Shiell ,  Jing Xiao

IPC分类号： G06F17/30 ,  G06K9/00 ,  G06N99/00

CPC分类号： G06F17/30 ,  G06K9/00 ,  G06K9/00885 ,  G06K2009/00932 ,  G06N99/005

摘要： A specific item within an item class is identified by defining sets of descriptor data from a training library. The collected descriptor data is grouped and organized into a hierarchical tree, where each leaf node is defined by relations between corresponding parts of the descriptor data. Registrable sets of descriptor data are then identified from a collection of registrable samples. The registrable sets of descriptors are sorted into the hierarchical tree. When an input sample to be identified is received, a test set of descriptor data is generated from the input sample. The test set is then sorted into the hierarchical tree. Each leaf node that receives a part of the test set provides a vote for the registered samples it contains. The registered sample with the most votes is deemed a match for the input sample.

摘要翻译： 通过从训练库中定义描述符数据集来识别项目类别中的特定项目。 收集的描述符数据被分组并组织成分层树，其中每个叶节点由描述符数据的相应部分之间的关​​系定义。 然后从可注册样本的集合中识别可注册的描述符数据集。 描述符的可注册集合被分类到分层树中。 当接收到要识别的输入样本时，从输入样本生成描述符数据的测试集。 然后将测试集排序到分层树中。 接收测试集的一部分的每个叶节点为其包含的已注册样本提供投票。 投票数最多的注册样本被认为是输入样本的匹配项。

公开(公告)号：US08914313B2

公开(公告)日：2014-12-16

申请号：US13552422

申请日：2012-07-18

申请人： Jinjun Wang ,  Jing Xiao

发明人： Jinjun Wang ,  Jing Xiao

IPC分类号： G06F15/18

CPC分类号： G06F17/30961 ,  G06F17/30247 ,  G06F17/30979

摘要： An indexed hierarchical tree search structure converts each registration sample into an equivalent registration model based on the clustering of its registration item descriptors in the leaf nodes of the hierarchical tree. Query item descriptors from a query sample from someone wanting to be recognized are distributed into the hierarchical tree. A query model is defined based on the clustering of query item descriptors at the leaf nodes, and registration and verification are made based on comparison of the query model and the registration models.

摘要翻译： 索引分层树搜索结构基于分层树叶节点中其注册项描述符的聚类将每个注册样本转换为等效的注册模型。 从想要被识别的人的查询样本中查询项目描述符被分发到分层树中。 基于叶节点上查询项描述符的聚类定义查询模型，并根据查询模型与注册模型的比较进行注册和验证。

公开(公告)号：US08688192B2

公开(公告)日：2014-04-01

申请号：US13017869

申请日：2011-01-31

申请人： Chenyu Wu ,  Jing Xiao

发明人： Chenyu Wu ,  Jing Xiao

IPC分类号： A61B5/04

CPC分类号： A61B5/04007 ,  A61B2562/046

摘要： Magnetocardiogram (MCG) provides temporal and spatial measurements of cardiac electric activities, which permits current localization. An MCG device usually consists of a small number of magnetic sensors in a planar array. Each sensor provides a highly low-resolution 2D MCG map. Such a low-res map is insufficient for cardiac electric current localization. To create a high resolution MCG image from the sparse measurements, an algorithm based on model learning is used. The model is constructed using a large number of randomly generated high resolution MCG images based on the Biot-Savart Law. By fitting the model with the sparse measurements, high resolution MCG image are created. Next, the 2D position of the electric current is localized by finding the peak in the tangential components of the high resolution MCG images. Finally, the 2D current localization is refined by a non-linear optimization algorithm, which simultaneously recovers the depth of the electric current from the sensor and its magnitude and orientation.

摘要翻译： 心电图（MCG）提供心脏电活动的时间和空间测量，这允许当前的定位。 MCG器件通常由平面阵列中的少量磁传感器组成。 每个传感器提供高度低分辨率的2D MCG图。 这样的低分辨率图不足以用于心电流定位。 为了从稀疏测量中创建高分辨率MCG图像，使用基于模型学习的算法。 该模型使用基于Biot-Savart定律的大量随机生成的高分辨率MCG图像来构建。 通过使用稀疏测量拟合模型，创建高分辨率MCG图像。 接下来，通过找到高分辨率MCG图像的切向分量中的峰值来定位电流的2D位置。 最后，通过非线性优化算法对2D电流定位进行了改进，该算法同时恢复了传感器电流的深度及其幅度和方向。

公开(公告)号：US20130266195A1

公开(公告)日：2013-10-10

申请号：US13443624

申请日：2012-04-10

申请人： Derek Shiell ,  Jing Xiao

发明人： Derek Shiell ,  Jing Xiao

IPC分类号： G06K9/00

CPC分类号： G06K9/00281 ,  G06K9/00288 ,  G06K9/621

摘要： In a face recognition system, overlapping patches are defined on a canonical face. Random clusters of pixel pairs are defined within each patch, and binary features are determined for each pixel pair by comparing their respective feature values. An inverted index hash table is constructed of the binary features. Similar binary features are then determined on a library of registrable samples of identified faces. A log probability of each registrable sample generating a binary feature from a corresponding cluster of pixel pairs at each specific patch location is determined and stored in the hash table. In a search phase, similar binary features are determined, and a hash key is determined for each binary feature. The log probabilities for each identity found in the hash table are summed for all clusters of pixel pairs and locations and sorted to find the high probability match.

摘要翻译： 在脸部识别系统中，在规范面上定义重叠的贴片。 在每个贴片内定义像素对的随机簇，并且通过比较它们各自的特征值来确定每个像素对的二进制特征。 反向索引散列表由二进制特征构成。 然后在识别的面部的可注册样本库中确定类似的二进制特征。 确定每个特定补丁位置处的对应的像素对簇的每个可注册样本的生成二进制特征的对数概率并将其存储在散列表中。 在搜索阶段，确定类似的二进制特征，并为每个二进制特征确定散列密钥。 在哈希表中找到的每个身份的日志概率对于所有的像素对和位置集合进行求和并排序以找到高概率匹配。

公开(公告)号：US08538081B2

公开(公告)日：2013-09-17

申请号：US13371847

申请日：2012-02-13

申请人： Yuanyuan Ding ,  Jing Xiao

发明人： Yuanyuan Ding ,  Jing Xiao

IPC分类号： G06K9/00

CPC分类号： G06K9/4671 ,  G06K9/4642 ,  G06K9/527

摘要： Aspects of the present invention includes systems and methods for generating detection models that consider contextual information of an image patch and for using detection models that consider contextual information. In embodiments, a multi-scale image context descriptor is generated to represent the contextual cues in multiple parameters, such as spatial, scaling, and color spaces. In embodiments, a classification context is defined using the contextual features and is used in a contextual boost classification scheme. In embodiments, the contextual boost propagates contextual cues to larger coverage through iterations to improve the detection accuracy.

摘要翻译： 本发明的方面包括用于产生考虑图像补丁的上下文信息以及使用考虑上下文信息的检测模型的检测模型的系统和方法。 在实施例中，生成多尺度图像上下文描述符以表示诸如空间，缩放和颜色空间的多个参数中的上下文提示。 在实施例中，使用上下文特征来定义分类上下文，并且在上下文增强分类方案中使用。 在实施例中，上下文提升通过迭代将上下文提示传播到更大的覆盖范围，以提高检测精度。

公开(公告)号：US20130132316A1

公开(公告)日：2013-05-23

申请号：US13491108

申请日：2012-06-07

申请人： Jinjun Wang ,  Zhaowen Wang ,  Jing Xiao

发明人： Jinjun Wang ,  Zhaowen Wang ,  Jing Xiao

IPC分类号： G06N5/02

CPC分类号： G06N99/005

摘要： Embodiments of the present invention include systems and methods for improved state space modeling (SSM) comprising two added layers to model the substructure transition dynamics and action duration distribution. In embodiments, the first layer represents a substructure transition model that encodes the sparse and global temporal transition probability. In embodiments, the second layer models the action boundary characteristics by injecting discriminative information into a logistic duration model such that transition boundaries between successive actions can be located more accurately; thus, the second layer exploits discriminative information to discover action boundaries adaptively.

摘要翻译： 本发明的实施例包括用于改进状态空间建模（SSM）的系统和方法，所述状态空间建模（SSM）包括两个附加的层，以模拟子结构转变动力学和动作持续时间分布。 在实施例中，第一层表示编码稀疏和全局时间转移概率的子结构转换模型。 在实施例中，第二层通过将识别信息注入逻辑持续时间模型来建模动作边界特征，使得可以更准确地定位连续动作之间的转移边界; 因此，第二层利用辨别信息自动发现行动界限。

公开(公告)号：US08432435B2

公开(公告)日：2013-04-30

申请号：US13207224

申请日：2011-08-10

申请人： Yuanyuan Ding ,  Jing Xiao

发明人： Yuanyuan Ding ,  Jing Xiao

IPC分类号： H04N7/12

CPC分类号： G02B5/09 ,  G02B5/10 ,  G03B35/08 ,  H04N13/218 ,  H04N13/271

摘要： A catadioptric camera creates image light fields from a 3D scene by creating ray images defined as 2D arrays of ray-structure picture-elements (ray-xels). Each ray-xel captures light intensity, mirror-reflection location, and mirror-incident light ray direction. A 3D image is then rendered from the ray images by combining the corresponding ray-xels.

摘要翻译： 反射折射照相机通过创建被定义为射线结构图像元素（ray-xels）的2D阵列的射线图像，从3D场景创建图像光场。 每个ray-xel捕获光强度，镜面反射位置和镜像入射光线方向。 然后通过组合相应的射线 - xels从射线图像渲染3D图像。

公开(公告)号：US08407171B2

公开(公告)日：2013-03-26

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： G06F17/00

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：US08309070B2

公开(公告)日：2012-11-13

申请号：US11130820

申请日：2005-05-17

申请人： Walter Low ,  Jing Xiao ,  Zhenhong Nan

发明人： Walter Low ,  Jing Xiao ,  Zhenhong Nan

IPC分类号： A01N63/00 ,  C12N5/071 ,  A01N65/00

CPC分类号： A61K35/51 ,  C12N5/0647 ,  C12N2501/11 ,  C12N2501/115

摘要： The invention relates generally to methods for isolation and culture of umbilical cord blood stem cells, cells isolated by the methods, and therapeutic uses for those cells.

摘要翻译： 本发明一般涉及用于分离和培养脐带血干细胞的方法，通过该方法分离的细胞，以及这些细胞的治疗用途。

公开(公告)号：US08306257B2

公开(公告)日：2012-11-06

申请号：US13017891

申请日：2011-01-31

申请人： Derek Shiell ,  Jing Xiao

发明人： Derek Shiell ,  Jing Xiao

IPC分类号： G06K9/00 ,  H04N5/225

CPC分类号： G06K9/00275 ,  G06K9/6219 ,  G06K9/6282

摘要： An active appearance model is built by arranging the training images in its training library into a hierarchical tree with the training images at each parent node being divided into two child nodes according to similarities in characteristic features. The number of node levels is such that the number of training images associated with each leaf node is smaller than a predefined maximum. A separate AAM, one per leaf node, is constructed using each leaf node's corresponding training images. In operation, starting at the root node, a test image is compared with each parent node's two child nodes and follows a node-path of model images that most closely matches the test image. The test image is submitted to an AAM selected for being associated with the leaf node at which the test image rests. The selected AAM's output aligned image may be resubmitted to the hierarchical tree if sufficient alignment is not achieved.

摘要翻译： 通过将其训练库中的训练图像布置到分级树中，根据特征特征的相似性，将每个父节点处的训练图像分为两个子节点，构建主动外观模型。 节点级别的数量使得与每个叶节点相关联的训练图像的数量小于预定义的最大值。 使用每个叶节点的相应训练图像构建单独的AAM，每个叶节点一个。 在操作中，从根节点开始，将测试图像与每个父节点的两个子节点进行比较，并跟随与测试图像最匹配的模型图像的节点路径。 测试图像被提交给被选择用于与测试图像所在的叶节点相关联的AAM。 如果未实现足够的对准，则所选择的AAM的输出对齐图像可以重新提交到分层树。