专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07936906B2 Face recognition using discriminatively trained orthogonal tensor projections 有权
标题翻译：使用区分训练正交张量投影的人脸识别
公开(公告)号：US07936906B2
公开(公告)日：2011-05-03
申请号：US11763909
申请日：2007-06-15
申请人： Gang Hua , Paul A Viola , Steven M. Drucker , Michael Revow
发明人： Gang Hua , Paul A Viola , Steven M. Drucker , Michael Revow
IPC分类号： G06K9/00
CPC分类号： G06K9/00288 , G06K9/6232
摘要： Systems and methods are described for face recognition using discriminatively trained orthogonal rank one tensor projections. In an exemplary system, images are treated as tensors, rather than as conventional vectors of pixels. During runtime, the system designs visual features—embodied as tensor projections—that minimize intraclass differences between instances of the same face while maximizing interclass differences between the face and faces of different people. Tensor projections are pursued sequentially over a training set of images and take the form of a rank one tensor, i.e., the outer product of a set of vectors. An exemplary technique ensures that the tensor projections are orthogonal to one another, thereby increasing ability to generalize and discriminate image features over conventional techniques. Orthogonality among tensor projections is maintained by iteratively solving an ortho-constrained eigenvalue problem in one dimension of a tensor while solving unconstrained eigenvalue problems in additional dimensions of the tensor.
摘要翻译：使用区分训练的正交秩一张量投影描述用于人脸识别的系统和方法。在示例性系统中，图像被视为张量，而不是像传统的像素矢量。在运行期间，系统设计视觉特征 - 体现为张量投影 - 最大限度地减少不同人脸部和脸部之间的类间差异，从而最大限度地减少同一脸部实例之间的差异。张量投影在训练图像集上顺序追溯，并采取一级张量的形式，即一组向量的外积。示例性技术确保张量投影彼此正交，从而增加了与常规技术相比的概括和区分图像特征的能力。通过迭代求解张量的一维中的邻域约束特征值问题，同时解决张量的附加维度中的无约束特征值问题，维持张量投影中的正交性。

2. 发明授权

US07570816B2 Systems and methods for detecting text 有权
标题翻译：用于检测文本的系统和方法
公开(公告)号：US07570816B2
公开(公告)日：2009-08-04
申请号：US11095393
申请日：2005-03-31
申请人： David M Bargeron , Patrice Y Simard , Paul A Viola
发明人： David M Bargeron , Patrice Y Simard , Paul A Viola
IPC分类号： G06K9/62 , G06K9/34 , G06F7/00
CPC分类号： G06K9/6256 , G06K9/00442 , Y10S707/99942
摘要： The subject invention relates to facilitating text detection. The invention employs a boosted classifier and a transductive classifier to provide accurate and efficient text detection systems and/or methods. The boosted classifier is trained through features generated from a set of training connected components and labels. The boosted classifier utilizes the features to classify the training connected components, wherein inferred labels are conveyed to a transductive classifier, which generates additional properties. The initial set of features and the properties are utilized to train the transductive classifier. Upon training, the system and/or methods can be utilized to detect text in data under text detection, wherein unlabeled data is received, and connected components are extracted therefrom and utilized to generate corresponding feature vectors, which are employed to classify the connected components using the initial boosted classifier. Inferred labels are utilized to generate properties, which are utilized along with the initial feature vectors to classify each connected component using the transductive classifier.
摘要翻译：本发明涉及促进文本检测。本发明采用增强分类器和转换分类器来提供准确和有效的文本检测系统和/或方法。增强的分类器通过从一组训练连接的组件和标签产生的特征进行训练。增强分类器利用特征来对培训连接的组件进行分类，其中推断的标签被传送到转换分类器，其产生附加属性。使用初始特征和属性来训练转换分类器。在训练时，可以利用系统和/或方法来检测在文本检测下的数据中的文本，其中接收未标记的数据，并且从中提取连接的组件并用于产生对应的特征向量，其用于使用初始提升分类器。利用推断的标签来生成与初始特征向量一起使用的属性，以使用转换分类器对每个连接的分量进行分类。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式