公开(公告)号：US08135183B2

公开(公告)日：2012-03-13

申请号：US12940408

申请日：2010-11-05

申请人： Yuxiao Hu ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

发明人： Yuxiao Hu ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

IPC分类号： G06K9/00

CPC分类号： G06F3/012 ,  G06K9/00268 ,  G06K9/6211 ,  G06T7/73 ,  G06T2207/30201

摘要： Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.

摘要翻译： 提供了改进以有效地评估用户的脸部和头部姿势，使得计算机或类似装置可以跟踪用户对显示装置的注意。 然后可以自动选择用户转向的显示或图形用户界面的区域，而不需要用户提供进一步的输入。 应用前置面部检测器来检测使用者的正面，然后通过部件检测器检测左右眼中心，左/右口角，鼻尖等的关键面部点。 然后，系统通过图像跟踪器跟踪用户的头部，并且通过姿态估计器根据关键面部点和/或置信输出，通过粗略到精细处理确定用户头部的偏航，倾斜和滚动角度和其他姿态信息。

公开(公告)号：US20110050568A1

公开(公告)日：2011-03-03

申请号：US12940408

申请日：2010-11-05

申请人： Yuxiao HU ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

发明人： Yuxiao HU ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

IPC分类号： G06F3/033 ,  G06F3/01

CPC分类号： G06F3/012 ,  G06K9/00268 ,  G06K9/6211 ,  G06T7/73 ,  G06T2207/30201

摘要： Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.

摘要翻译： 提供了改进以有效地评估用户的脸部和头部姿势，使得计算机或类似装置可以跟踪用户对显示装置的注意。 然后可以自动选择用户转向的显示或图形用户界面的区域，而不需要用户提供进一步的输入。 应用前置面部检测器来检测使用者的正面，然后通过部件检测器检测左右眼中心，左/右口角，鼻尖等的关键面部点。 然后，系统通过图像跟踪器跟踪用户的头部，并且通过姿态估计器根据关键面部点和/或置信输出，通过粗略到精细处理确定用户头部的偏航，倾斜和滚动角度和其他姿态信息。

公开(公告)号：US07292737B2

公开(公告)日：2007-11-06

申请号：US10641608

申请日：2003-08-15

申请人： Yi Zhou ,  Lie Gu ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

发明人： Yi Zhou ,  Lie Gu ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

IPC分类号： G06K9/32 ,  G06K9/36

CPC分类号： G06K9/00281 ,  G06K9/621

摘要： Systems and methods for shape registration are described. In one aspect, training shape vectors are generated from images in an image database. The training shape vectors identify landmark points associated with one or more object types. A distribution of shape in the training shape vectors is represented as a prior of tangent shape in tangent shape space. The prior of tangent shape is then incorporated into a unified Bayesian framework for shape registration.

摘要翻译： 描述了用于形状配准的系统和方法。 在一个方面，训练形状向量是从图像数据库中的图像生成的。 训练形状向量识别与一个或多个对象类型相关联的地标点。 训练形状矢量中的形状分布被表示为切线形状空间中的切线形状之前。 之前的切线形状然后被并入到用于形状注册的统一的贝叶斯框架中。

公开(公告)号：US07274822B2

公开(公告)日：2007-09-25

申请号：US10609974

申请日：2003-06-30

申请人： Lei Zhang ,  Longbin Chen ,  Mingjing Li ,  Hong-Jiang Zhang

发明人： Lei Zhang ,  Longbin Chen ,  Mingjing Li ,  Hong-Jiang Zhang

IPC分类号： G06K9/62

CPC分类号： G06F17/30265 ,  G06K9/00288 ,  G06K2009/00328

摘要： Systems and methods for annotating a face in a digital image are described. In one aspect, a probability model is trained by mapping one or more sets of sample facial features to corresponding names of individuals. A face from an input data set of at least one the digital image is then detected. Facial features are then automatically extracted from the detected face. A similarity measure is them modeled as a posterior probability that the facial features match a particular set of features identified in the probability model. The similarity measure is statistically learned. A name is then inferred as a function of the similarity measure. The face is then annotated with the name.

摘要翻译： 描述了用于在数字图像中注释面部的系统和方法。 在一个方面，通过将一组或多组样本面部特征映射到个人的相应名称来训练概率模型。 然后检测来自至少一个数字图像的输入数据集的面。 然后从检测到的脸部自动提取面部特征。 相似性度量是他们被模型化为面部特征与在概率模型中识别的特定特征集合相匹配的后验概率。 统计学习相似性度量。 然后将该名称推定为相似性度量的函数。 然后用该名称注明脸部。

公开(公告)号：US07231381B2

公开(公告)日：2007-06-12

申请号：US09805626

申请日：2001-03-13

申请人： Mingjing Li ,  Hong-Jiang Zhang ,  Wen-Yin Liu ,  Zhen Chen

发明人： Mingjing Li ,  Hong-Jiang Zhang ,  Wen-Yin Liu ,  Zhen Chen

IPC分类号： G06F17/30

CPC分类号： G06F17/30017 ,  Y10S707/913 ,  Y10S707/915 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99936

摘要： Text features corresponding to pieces of media content (e.g., images, audio, multimedia content, etc.) are extracted from media content sources. One or more text features (e.g., one or more words) for a piece of media content are extracted from text associated with the piece of media content and text feature vectors generated therefrom and used during subsequent searching. Additional low-level feature vectors may also be extracted from the piece of media content and used during the subsequent searching. Relevance feedback can also be received from a user(s) identifying the relevance of pieces of media content rendered to the user in response to his or her search request. The relevance feedback is logged and can be used in determining how to respond to subsequent search requests, such as by modifying feature vectors (e.g., text feature vectors) corresponding to the pieces of media content for which relevance feedback is received.

摘要翻译： 从媒体内容源提取对应于媒体内容（例如，图像，音频，多媒体内容等）的文本特征。 从与其相关联的文本内容和从其生成的文本特征向量的文本中提取用于一段媒体内容的一个或多个文本特征（例如，一个或多个单词），并在随后的搜索期间使用。 还可以从媒体内容中提取附加的低级特征向量，并在随后的搜索期间使用。 还可以从用户识别响应于他或她的搜索请求而呈现给用户的媒体内容的相关性的用户接收到相关性反馈。 记录相关性反馈，并且可以用于确定如何响应随后的搜索请求，例如通过修改对应于接收到相关性反馈的多条媒体内容的特征向量（例如，文本特征向量）。

公开(公告)号：US20050084154A1

公开(公告)日：2005-04-21

申请号：US10689106

申请日：2003-10-20

申请人： Mingjing Li ,  Lei Zhang ,  Yanfeng Sun ,  Hong-Jiang Zhang ,  David Parlin

发明人： Mingjing Li ,  Lei Zhang ,  Yanfeng Sun ,  Hong-Jiang Zhang ,  David Parlin

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/66

CPC分类号： G06K9/4652 ,  G06K9/00664 ,  Y10S707/99945 ,  Y10S707/99948

摘要： A process for comparing two digital images is described. The process includes comparing texture moment data for the two images to provide a similarity index, combining the similarity index with other data to provide a similarity value and determining that the two images match when the similarity value exceeds a first threshold value.

摘要翻译： 描述用于比较两个数字图像的过程。 该过程包括比较两个图像的纹理时刻数据以提供相似性索引，将相似性索引与其他数据组合以提供相似性值，并且当相似度值超过第一阈值时确定两个图像匹配。

公开(公告)号：US20050013479A1

公开(公告)日：2005-01-20

申请号：US10621260

申请日：2003-07-16

申请人： Rong Xiao ,  Long Zhu ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

发明人： Rong Xiao ,  Long Zhu ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/4614 ,  G06K9/00228

摘要： Face detection techniques are provided that use a multiple-stage face detection algorithm. An exemplary three-stage algorithm includes a first stage that applies linear-filtering to enhance detection performance by removing many non-face-like portions within an image, a second stage that uses a boosting chain that is adopted to combine boosting classifiers within a hierarchy “chain” structure, and a third stage that performs post-filtering using image pre-processing, SVM-filtering and color-filtering to refine the final face detection prediction. In certain further implementations, the face detection techniques include a two-level hierarchy in-plane pose estimator to provide a rapid multi-view face detector that further improves the accuracy and robustness of face detection.

摘要翻译： 提供了使用多级面部检测算法的人脸检测技术。 示例性的三阶段算法包括第一阶段，其通过去除图像内的许多非面部部分来应用线性滤波以增强检测性能;第二阶段，其使用用于组合层级内的增强分类器的升压链 “链”结构，以及使用图像预处理，SVM滤波和颜色滤波来完成最终面部检测预测来执行后置滤波的第三阶段。 在某些进一步的实施方式中，面部检测技术包括两层次平面姿态估计器，以提供进一步提高面部检测的准确性和鲁棒性的快速多视角面部检测器。

公开(公告)号：US08457358B2

公开(公告)日：2013-06-04

申请号：US13398171

申请日：2012-02-16

申请人： Yuxiao Hu ,  Hong-Jiang Zhang ,  Mingjing Li ,  Lei Zhang

发明人： Yuxiao Hu ,  Hong-Jiang Zhang ,  Mingjing Li ,  Lei Zhang

IPC分类号： G06K9/00

CPC分类号： G06F3/012 ,  G06K9/00268 ,  G06K9/6211 ,  G06T7/73 ,  G06T2207/30201

摘要： Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.

摘要翻译： 提供了改进以有效地评估用户的脸部和头部姿势，使得计算机或类似装置可以跟踪用户对显示装置的注意。 然后可以自动选择用户转向的显示或图形用户界面的区域，而不需要用户提供进一步的输入。 应用前置面部检测器来检测使用者的正面，然后通过部件检测器检测左右眼中心，左/右口角，鼻尖等的关键面部点。 然后，系统通过图像跟踪器跟踪用户的头部，并且通过姿态估计器根据关键面部点和/或置信输出，通过粗略到精细处理确定用户头部的偏航，倾斜和滚动角度和其他姿态信息。

公开(公告)号：US20120139832A1

公开(公告)日：2012-06-07

申请号：US13398171

申请日：2012-02-16

申请人： Yuxiao HU ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

发明人： Yuxiao HU ,  Lei Zhang ,  Mingjing Li ,  Hong-Jiang Zhang

IPC分类号： G06F3/01

CPC分类号： G06F3/012 ,  G06K9/00268 ,  G06K9/6211 ,  G06T7/73 ,  G06T2207/30201

摘要： Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.

摘要翻译： 提供了改进以有效地评估用户的脸部和头部姿势，使得计算机或类似装置可以跟踪用户对显示装置的注意。 然后可以自动选择用户转向的显示或图形用户界面的区域，而不需要用户提供进一步的输入。 应用前置面部检测器来检测使用者的正面，然后通过部件检测器检测左右眼中心，左/右口角，鼻尖等的关键面部点。 然后，系统通过图像跟踪器跟踪用户的头部，并且通过姿态估计器根据关键面部点和/或置信输出，通过粗略到精细处理确定用户头部的偏航，倾斜和滚动角度和其他姿态信息。

公开(公告)号：US07430566B2

公开(公告)日：2008-09-30

申请号：US11056555

申请日：2005-02-11

申请人： Mingjing Li ,  Zheng Chen ,  Liu Wenyin ,  Hong-Jiang Zhang

发明人： Mingjing Li ,  Zheng Chen ,  Liu Wenyin ,  Hong-Jiang Zhang

IPC分类号： G06F17/30

CPC分类号： G06F17/30247 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99936 ,  Y10S707/99945 ,  Y10S707/99948

摘要： The disclosed subject matter improves iterative results of content-based image retrieval (CBIR) using a bigram model to correlate relevance feedback. Specifically, multiple images are received responsive to multiple image search sessions. Relevance feedback is used to determine whether the received images are semantically relevant. A respective semantic correlation between each of at least one pair of the images is then estimated using respective bigram frequencies. The bigram frequencies are based on multiple search sessions in which each image of a pair of images is semantically relevant.

摘要翻译： 所公开的主题改进了基于内容的图像检索（CBIR）的迭代结果，其使用二元模型来相关联反馈。 具体地，响应于多个图像搜索会话接收多个图像。 相关性反馈用于确定接收的图像是否具有语义相关性。 然后使用相应的二进制频率来估计至少一对图像中的每一个之间的相应语义相关性。 双频频率基于多个搜索会话，其中一对图像的每个图像在语义上相关。