公开(公告)号：US07050607B2

公开(公告)日：2006-05-23

申请号：US10091100

申请日：2002-03-04

申请人： ZiQing Li ,  HongJiang Zhang ,  ZhenQiu Zhang

发明人： ZiQing Li ,  HongJiang Zhang ,  ZhenQiu Zhang

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/4614 ,  G06K9/00228 ,  G06K9/6256 ,  G06K9/626

摘要： A system and method for real-time multi-view (i.e. not just frontal view) face detection. The system and method uses a sequence of detectors of increasing complexity and face/non-face discriminating thresholds to quickly discard non-faces at the earliest stage possible, thus saving much computation compared to prior art systems. The detector-pyramid architecture for multi-view face detection uses a coarse-to-fine and simple-to-complex scheme. This architecture solves the problem of lengthy processing that precludes real-time face detection effectively and efficiently by discarding most of non-face sub-windows using the simplest possible features at the earliest possible stage. This leads to the first real-time multi-view face detection system which has the accuracy almost as good as the state-of-the-art system yet 270 times faster, allowing real-time performance.

公开(公告)号：US20060120572A1

公开(公告)日：2006-06-08

申请号：US11299504

申请日：2005-12-12

申请人： ZiQing Li ,  HongJiang Zhang ,  ZhenQiu Zhang

发明人： ZiQing Li ,  HongJiang Zhang ,  ZhenQiu Zhang

IPC分类号： G06K9/00 ,  G06K9/36

CPC分类号： G06K9/4614 ,  G06K9/00228 ,  G06K9/6256 ,  G06K9/626

摘要： A system and method for real-time multi-view (i.e. not just frontal view) face detection. The system and method uses a sequence of detectors of increasing complexity and face/non-face discriminating thresholds to quickly discard non-faces at the earliest stage possible, thus saving much computation compared to prior art systems. The detector-pyramid architecture for multi-view face detection uses a coarse-to-fine and simple-to-complex scheme. This architecture solves the problem of lengthy processing that precludes real-time face detection effectively and efficiently by discarding most of non-face sub-windows using the simplest possible features at the earliest possible stage. This leads to the first real-time multi-view face detection system which has the accuracy almost as good as the state-of-the-art system yet 270 times faster, allowing real-time performance.

公开(公告)号：US07324671B2

公开(公告)日：2008-01-29

申请号：US11299504

申请日：2005-12-12

申请人： ZiQing Li ,  ZhenQiu Zhang ,  HongJiang Zhang

发明人： ZiQing Li ,  ZhenQiu Zhang ,  HongJiang Zhang

IPC分类号： G06K9/00

CPC分类号： G06K9/4614 ,  G06K9/00228 ,  G06K9/6256 ,  G06K9/626

摘要： A system and method for real-time multi-view (i.e. not just frontal view) face detection. The system and method uses a sequence of detectors of increasing complexity and face/non-face discriminating thresholds to quickly discard non-faces at the earliest stage possible, thus saving much computation compared to prior art systems. The detector-pyramid architecture for multi-view face detection uses a coarse-to-fine and simple-to-complex scheme. This architecture solves the problem of lengthy processing that precludes real-time face detection effectively and efficiently by discarding most of non-face sub-windows using the simplest possible features at the earliest possible stage. This leads to the first real-time multi-view face detection system which has the accuracy almost as good as the state-of-the-art system yet 270 times faster, allowing real-time performance.

摘要翻译： 用于实时多视图（即，不仅仅是前视图）面部检测的系统和方法。 该系统和方法使用增加复杂性和面部/非脸部鉴别阈值的检测器序列来尽可能快地丢弃非面部，从而与现有技术系统相比节省了大量的计算。 用于多视角人脸检测的检测器 - 金字塔架构使用粗略到精细和简单到复杂的方案。 该架构解决了长时间处理的问题，通过在最早阶段使用最简单的可能特征来废弃大多数非面子子窗口，从而有效且高效地排除了实时面部检测。 这导致了第一个实时多视角人脸检测系统，其精度几乎与最先进的系统一样好，但是快了270倍，从而允许实时性能。

公开(公告)号：US20100250190A1

公开(公告)日：2010-09-30

申请号：US12415722

申请日：2009-03-31

申请人： HongJiang Zhang ,  Dong Liu ,  Meng Wang ,  Linjun Yang ,  Xian-Sheng Hua

发明人： HongJiang Zhang ,  Dong Liu ,  Meng Wang ,  Linjun Yang ,  Xian-Sheng Hua

IPC分类号： G06F17/18

CPC分类号： G06F17/30038

摘要： Technologies for generating a boosted tag ranking for a media instance, the boosted tag ranking based on probabilistic relevance estimation and tag correlation refining. Such boosted tag rankings may be used for search result ranking, tag recommendation, and group recommendation.

摘要翻译： 用于生成媒体实例的增强标签排名的技术，基于概率相关性估计和标签相关性提炼的提升标签排名。 这种提升的标签排名可以用于搜索结果排名，标签推荐和组推荐。

公开(公告)号：US06389168B2

公开(公告)日：2002-05-14

申请号：US09172399

申请日：1998-10-13

申请人： Yucel Altunbasak ,  HongJiang Zhang

发明人： Yucel Altunbasak ,  HongJiang Zhang

IPC分类号： G06K962

CPC分类号： G06K9/00711 ,  G06F17/3079 ,  G06F17/30811 ,  G06F17/30858 ,  G06T9/005 ,  H04N5/147

摘要： A method and system for object-based video retrieval and indexing include a configuration detection processor for deriving quantitative attribute information for video frames in a compressed video stream. The quantitative attribute information includes object data for a video frame, including the number of objects and their orientation within the video frame and the size, shape, texture, and motion of each object. A configuration comparison processor compares object data from first and second frames to determine differences between first frame video objects and second frame video objects. The configuration comparison processor has a shot boundary detection mode in which it cooperates with a shot boundary detector to identify shot boundaries within a video sequence. In a key frame selection mode, the configuration comparison processor cooperates with a key frame selector to select key frames from the video sequence. A key instance selector communicates with the configuration comparison processor during a key instance selection mode to select key instances of video objects based on differences between first and second instances of video objects. The configuration comparison processor cooperates with a camera operation detector to identify camera operations such as zoom, tracking, and panning within the video sequence. A special effects detector cooperates with the configuration comparison processor to detect special effects video edits such as wipe, dissolve, and fade. The configuration comparison processor and a query match detector enable a user to configure object-based queries and to retrieve video sequences or video frames which include a query video object.

摘要翻译： 一种用于基于对象的视频检索和索引的方法和系统包括用于在压缩视频流中导出视频帧的定量属性信息的配置检测处理器。 定量属性信息包括视频帧的对象数据，包括对象的数量及其在视频帧内的取向以及每个对象的大小，形状，纹理和运动。 配置比较处理器将来自第一和第二帧的对象数据进行比较，以确定第一帧视频对象和第二帧视频对象之间的差异。 配置比较处理器具有镜头边界检测模式，其中它与镜头边界检测器配合以识别视频序列内的镜头边界。 在关键帧选择模式中，配置比较处理器与关键帧选择器协作，从视频序列中选择关键帧。 密钥实例选择器在密钥实例选择模式期间与配置比较处理器通信，以基于视频对象的第一和第二实例之间的差异来选择视频对象的关键实例。 配置比较处理器与相机操作检测器协作以识别诸如视频序列内的缩放，跟踪和平移的相机操作。 特效检测器与配置比较处理器配合检测特效影像编辑，如擦拭，溶解和淡化。 配置比较处理器和查询匹配检测器使得用户能够配置基于对象的查询并且检索包括查询视频对象的视频序列或视频帧。

公开(公告)号：US07983340B2

公开(公告)日：2011-07-19

申请号：US11279245

申请日：2006-04-10

申请人： HongJiang Zhang ,  Tianming Liu

发明人： HongJiang Zhang ,  Tianming Liu

IPC分类号： H04B1/66 ,  H04N7/12 ,  H04N11/02 ,  H04N11/04

CPC分类号： G06F17/30811 ,  G06F17/30843 ,  G11B27/28

摘要： A key frame extraction system and method for extracting key frames from a video based on motion analysis of frames within the video. Key frames are highlight frames that are effective in summarizing a video sequence. This allows a user to quickly find a desired spot in a video is long and contains differing subject matter. The key frame extraction system and method uses a triangle model of the motion energy in each frame and extracts key frames based on this model. More specifically, motion analysis is performed on the video frames in order to identify motion acceleration and motion deceleration points within the frames. A triangle model of motion then is constructed based on results of the motion analysis. The apex of the triangle represents a turning point between motion acceleration and motion deceleration. Frames corresponding to this apex are selected as key frames.

摘要翻译： 一种关键帧提取系统和方法，用于基于视频内的帧的运动分析从视频中提取关键帧。 关键帧是对汇总视频序列有效的突出显示帧。 这允许用户快速地在视频中找到期望的地点很长并且包含不同的主题。 关键帧提取系统和方法使用每帧运动能量的三角形模型，并基于该模型提取关键帧。 更具体地，对视频帧执行运动分析，以便识别帧内的运动加速度和运动减速点。 然后基于运动分析的结果构建运动的三角形模型。 三角形的顶点表示运动加速度与运动减速度之间的转折点。 对应于该顶点的框架被选为关键帧。

公开(公告)号：US20060165382A1

公开(公告)日：2006-07-27

申请号：US11279245

申请日：2006-04-10

申请人： HongJiang Zhang ,  Tianming Liu

发明人： HongJiang Zhang ,  Tianming Liu

IPC分类号： H04N5/91

CPC分类号： G06F17/30811 ,  G06F17/30843 ,  G11B27/28

摘要： A key frame extraction system and method for extracting key frames from a video based on motion analysis of frames within the video. Key frames are highlight frames that are effective in summarizing a video sequence. This allows a user to quickly find a desired spot in a video is long and contains differing subject matter. The key frame extraction system and method uses a triangle model of the motion energy in each frame and extracts key frames based on this model. More specifically, motion analysis is performed on the video frames in order to identify motion acceleration and motion deceleration points within the frames. A triangle model of motion then is constructed based on results of the motion analysis. The apex of the triangle represents a turning point between motion acceleration and motion deceleration. Frames corresponding to this apex are selected as key frames.

摘要翻译： 一种关键帧提取系统和方法，用于基于视频内的帧的运动分析从视频中提取关键帧。 关键帧是对汇总视频序列有效的突出显示帧。 这允许用户快速地在视频中找到期望的地点很长并且包含不同的主题。 关键帧提取系统和方法使用每帧运动能量的三角形模型，并基于该模型提取关键帧。 更具体地，对视频帧执行运动分析，以便识别帧内的运动加速度和运动减速点。 然后基于运动分析的结果构建运动的三角形模型。 三角形的顶点表示运动加速度与运动减速度之间的转折点。 对应于该顶点的框架被选为关键帧。

公开(公告)号：US06278491B1

公开(公告)日：2001-08-21

申请号：US09015407

申请日：1998-01-29

申请人： John Y. A. Wang ,  HongJiang Zhang

发明人： John Y. A. Wang ,  HongJiang Zhang

IPC分类号： H04N5222

CPC分类号： G06K9/0061 ,  G06T5/005 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30216 ,  H04N1/62 ,  H04N1/624

摘要： An automatic red-eye detection and reduction system is described. The automatic red-eye detection and reduction system includes a red-eye detector that detects if an image contains a red pupil without user intervention. The red-eye detector detects location and size of the red pupil if the image is detected to contain the red pupil. The automatic red-eye detection and reduction system also includes a red-eye reduction system that is coupled to the red-eye detector to change each red color pixel within the red pupil into a predetermined color such that color of the red pupil can be detected and changed without user intervention. A method of automatically detecting and reducing red-eye effect in a digital image is also described.

摘要翻译： 描述了自动红眼检测和减少系统。 自动红眼检测和还原系统包括一个红眼探测器，可以在没有用户干预的情况下检测图像中是否包含红光瞳孔。 如果检测到图像包含红色瞳孔，则红眼探测器检测红色瞳孔的位置和大小。 自动红眼检测和还原系统还包括红眼减轻系统，其耦合到红眼探测器以将红光瞳内的每个红色像素改变成预定颜色，使得可以检测红光瞳的颜色 并在没有用户干预的情况下改变。 还描述了一种在数字图像中自动检测和减少红眼效果的方法。

公开(公告)号：US07027513B2

公开(公告)日：2006-04-11

申请号：US10346160

申请日：2003-01-15

申请人： HongJiang Zhang ,  Tianming Liu

发明人： HongJiang Zhang ,  Tianming Liu

IPC分类号： H04B1/66

CPC分类号： G06F17/30811 ,  G06F17/30843 ,  G11B27/28

摘要： The present invention includes a key frame extraction system and method for extracting key frames from a video based on motion analysis of frames within the video. Key frames are highlight frames that are effective in summarizing a video sequence. This allows a user to quickly find a desired spot in a video is long and contains differing subject matter. The key frame extraction system and method uses a triangle model of the motion energy in each frame and extracts key frames based on this model. More specifically, motion analysis is performed on the video frames in order to identify motion acceleration and motion deceleration points within the frames. A triangle model of motion then is constructed based on results of the motion analysis. The apex of the triangle represents a turning point between motion acceleration and motion deceleration. Frames corresponding to this apex are selected as key frames.

摘要翻译： 本发明包括一种关键帧提取系统和方法，用于基于视频内的帧的运动分析从视频中提取关键帧。 关键帧是对汇总视频序列有效的突出显示帧。 这允许用户快速地在视频中找到期望的地点很长并且包含不同的主题。 关键帧提取系统和方法使用每帧运动能量的三角形模型，并基于该模型提取关键帧。 更具体地，对视频帧执行运动分析，以便识别帧内的运动加速度和运动减速点。 然后基于运动分析的结果构建运动的三角形模型。 三角形的顶点表示运动加速度与运动减速度之间的转折点。 对应于该顶点的框架被选为关键帧。

公开(公告)号：US06347313B1

公开(公告)日：2002-02-12

申请号：US09260215

申请日：1999-03-01

申请人： Wei-Ying Ma ,  Catherine S. Lee ,  HongJiang Zhang

发明人： Wei-Ying Ma ,  Catherine S. Lee ,  HongJiang Zhang

IPC分类号： G06F1730

CPC分类号： G06K9/6253 ,  G06F17/30256 ,  G06K9/6218 ,  G06K9/6263 ,  G06K9/6273 ,  Y10S707/99933 ,  Y10S707/99934 ,  Y10S707/99935

摘要： A method and system for indexing and retrieving database objects, such as images, include a database manager which initializes database objects based on vectors for values of quantified features associated with the database objects. Similar database objects are grouped into common clusters that are based on system-perceived relationships among the objects. For each search session, a vector for a search query is calculated and database objects from the closest cluster within feature space are selected for presentation at a user device. The user indicates which of the selected objects are relevant to the search session and which of the objects are irrelevant. If one of the clusters includes both relevant and irrelevant objects, the cluster is split into two clusters, so that one of the resulting clusters includes the relevant objects and the other cluster includes irrelevant objects. The correlation matrix is updated to indicate that the resulting clusters have a weak correlation. If two of the clusters include database objects which were indicated to be relevant to the search session, the correlation matrix is updated to indicate that the two clusters have a strong correlation. To avoid an excessive proliferation of database clusters, mergers are performed on clusters which are closely located within the feature space and share a strong correlation within the correlation matrix. Following continued use, the groupings of objects into clusters and the cluster-to-cluster correlations will reflect user-perceived relationships.

摘要翻译： 用于索引和检索数据库对象（诸如图像）的方法和系统包括数据库管理器，其基于与数据库对象相关联的量化特征的值的向量初始化数据库对象。 类似的数据库对象被分组成基于对象之间的系统感知关系的公共集群。 对于每个搜索会话，计算用于搜索查询的向量，并且选择来自特征空间内最近的簇的数据库对象以在用户设备处呈现。 用户指示哪些选择的对象与搜索会话相关，哪些对象是不相关的。 如果其中一个集群包含相关对象和不相关的对象，则将集群分为两个集群，以便其中一个生成的集群包含相关对象，而另一个集群包含不相关的对象。 相关矩阵被更新以指示所得到的集群具有弱相关性。 如果两个集群包括被指示为与搜索会话相关的数据库对象，则更新相关矩阵以指示两个集群具有强相关性。 为了避免数据库集群的过度扩散，对位于特征空间内的集群进行合并，并在相关矩阵内共享强相关性。 继续使用后，将对象分组到群集和群集到群集相关性将反映用户感知的关系。