公开(公告)号：US08933928B2

公开(公告)日：2015-01-13

申请号：US13303044

申请日：2011-11-22

申请人： Derek Shiell ,  Jing Xiao

发明人： Derek Shiell ,  Jing Xiao

IPC分类号： G06T15/00 ,  G06T17/00 ,  G06T15/20

CPC分类号： G06T17/00 ,  G06T15/205

摘要： New views of a 2D image are generated by identifying an object class within the image, such as through a face detector. The face is then fitted to a model face by means of an AAM, and the results extended to a fitted 3D polygon mesh face. A boundary perimeter with predefined anchor points and a predefined triangulation with the 3D polygon mesh is defined a predefined depth distance from the depth center of known landmarks within the 3D polygon mesh face. By rotating the 3D polygon mesh face relative to the boundary perimeter, which may follow the perimeter of the input image, new views of the input image are generated.

摘要翻译： 通过识别图像内的对象类（例如通过面部检测器）来生成2D图像的新视图。 然后通过AAM将面部安装到模型面上，并将结果扩展到拟合的3D多边形网格面。 定义了与3D多边形网格预定义三角剖分的边界周界，与3D多边形网格面内的已知界标深度中心的预定深度距离。 通过旋转3D多边形网格面相对于可能跟随输入图像的周边的边界周界，生成输入图像的新视图。

公开(公告)号：US08131063B2

公开(公告)日：2012-03-06

申请号：US12392808

申请日：2009-02-25

申请人： Jing Xiao ,  Derek Shiell

发明人： Jing Xiao ,  Derek Shiell

IPC分类号： G06K9/00 ,  G06T17/00 ,  G06F19/00

CPC分类号： G06T17/20 ,  G06K9/00248 ,  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：US20120299906A1

公开(公告)日：2012-11-29

申请号：US13114514

申请日：2011-05-24

申请人： Derek Shiell ,  Jing Xiao

发明人： Derek Shiell ,  Jing Xiao

IPC分类号： G06T15/00

CPC分类号： G06T15/04 ,  G06T2200/08

摘要： An output image of higher resolution than an input image is constructed by using a low resolution (LR) dictionary of triangle data entries, each having a one-to-one correlation with a high resolution (HR) data entry in an HR dictionary of triangle data entries. The input image is triangularized, and the closest matching LR data entry in the LR dictionary for each triangle in the triangularized input image is identified. The HR data entry correlated to each identified matching LR data entry is then used to construct the output image by wrapping the correlated HR data entry onto the corresponding triangle on the triangularized input image.

摘要翻译： 通过使用三角形数据条目的低分辨率（LR）字典来构造比输入图像更高分辨率的输出图像，每个三角形数据条目与三角形的HR字典中的高分辨率（HR）数据条目具有一对一的相关性 数据输入。 输入图像被三角化，并且识别在三角形化输入图像中的每个三角形的LR字典中最接近的匹配LR数据条目。 然后，通过将相关的HR数据条目包围在三角化输入图像上的相应三角形上，与每个识别的匹配LR数据条目相关的HR数据条目用于构建输出图像。

公开(公告)号：US20120141018A1

公开(公告)日：2012-06-07

申请号：US12961347

申请日：2010-12-06

申请人： Derek Shiell ,  Jing Xiao

发明人： Derek Shiell ,  Jing Xiao

IPC分类号： G06K9/62

CPC分类号： G06K9/621

摘要： An Active Appearance Model, AAM, uses an L1 minimization-based approach to aligning an input test image. In each iterative application of its statistical model fitting function, a shape parameter coefficient p and an appearance parameter coefficient λ within the statistical model fitting function are updated by L1 minimization. The AAM further includes a canonical classifier to determine if an aligned image is a true example of the class of object being sought before the AAM is permitted to output its aligned image.

摘要翻译： 主动外观模型AAM使用基于L1最小化的方法来对齐输入测试图像。 在其统计模型拟合函数的每个迭代应用中，通过L1最小化来更新统计模型拟合函数内的形状参数系数p和外观参数系数λ。 AAM还包括一个规范分类器，用于确定对齐的图像是否是在允许AAM输出其对齐图像之前正在寻找的对象类的真实示例。

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：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：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：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。

公开(公告)号：US08260039B2

公开(公告)日：2012-09-04

申请号：US12392849

申请日：2009-02-25

申请人： Derek Shiell ,  Jing Xiao

发明人： Derek Shiell ,  Jing Xiao

IPC分类号： G06K9/00 ,  G06T17/00

CPC分类号： G06T17/20 ,  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：US08204301B2

公开(公告)日：2012-06-19

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： G06K9/00 ,  G06T15/00 ,  G06T17/00

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。