专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明申请

WO2013152455A1 SYSTEM AND METHOD FOR AVATAR GENERATION, RENDERING AND ANIMATION 审中-公开
标题翻译：用于产生，渲染和动画的系统和方法
公开(公告)号：WO2013152455A1
公开(公告)日：2013-10-17
申请号：PCT/CN2012/000460
申请日：2012-04-09
申请人： INTEL CORPORATION , TONG, Xiaofeng , LI, Wenlong , DU, Yangzhou , HU, Wei , ZHANG, Yimin , LI, Jianguo
发明人： TONG, Xiaofeng , LI, Wenlong , DU, Yangzhou , HU, Wei , ZHANG, Yimin , LI, Jianguo
IPC分类号： G06T13/80
CPC分类号： G06T11/60 , H04N7/157
摘要： A video communication system that replaces actual live images of the participating users with animated avatars. The system allows generation, rendering and animation of a two-dimensional (2-D) avatar of a user's face. The 2-D avatar represents a user's basic face shape and key facial characteristics, including, but not limited to, position and shape of the eyes, nose, mouth, and face contour. The system further allows adaptive rendering for displaying, allowing different scales of the 2-D avatar to be displayed on associated different sized displays of user devices.
摘要翻译：视频通信系统，用动画头像代替参与用户的实际实况图像。该系统允许用户脸部的二维（2-D）头像的生成，呈现和动画。 2-D头像表示用户的基本面部形状和关键面部特征，包括但不限于眼睛，鼻子，嘴巴和脸部轮廓的位置和形状。该系统进一步允许显示的自适应渲染，允许将不同比例的2D头像显示在用户设备的相关不同大小的显示器上。

52. 发明申请

WO2013143113A1 TECHNIQUES FOR MEDIA QUALITY CONTROL 审中-公开
标题翻译：媒体质量控制技术
公开(公告)号：WO2013143113A1
公开(公告)日：2013-10-03
申请号：PCT/CN2012/073293
申请日：2012-03-30
申请人： INTEL CORPORATION , DU, Yangzhou , CHEN, Yurong , LI, Qiang , LI, Wenlong
发明人： DU, Yangzhou , CHEN, Yurong , LI, Qiang , LI, Wenlong
IPC分类号： G06F17/00
CPC分类号： H04N21/23418 , H04N21/25435 , H04N21/2743 , H04N21/485 , H04N21/4854 , H04N21/4882
摘要： Techniques for media quality control may include receiving media information and determining the quality of the media information. The media information may be presented when the quality of the media information meets a quality control threshold. A warning may be generated when the quality of the media information does not meet the quality control threshold. Other embodiments are described and claimed.
摘要翻译：用于媒体质量控制的技术可以包括接收媒体信息并确定媒体信息的质量。当媒体信息的质量满足质量控制阈值时，可以呈现媒体信息。当媒体信息的质量不符合质量控制阈值时，可能会产生警告。描述和要求保护其他实施例。

53. 发明申请

WO2013037082A1 USING GESTURES TO CAPTURE MULTIMEDIA CLIPS 审中-公开
标题翻译：使用手势捕获多媒体CLIPS
公开(公告)号：WO2013037082A1
公开(公告)日：2013-03-21
申请号：PCT/CN2011/001548
申请日：2011-09-12
申请人： INTEL CORPORATION , LI, Wenlong , DING, Dayong , TONG, Xiaofeng , DU, Yangzhou , WANG, Peng
发明人： LI, Wenlong , DING, Dayong , TONG, Xiaofeng , DU, Yangzhou
IPC分类号： H04N7/173 , G06F17/30
CPC分类号： H04N21/482 , G06F17/30017 , H04N21/25891 , H04N21/4126 , H04N21/4183 , H04N21/4223 , H04N21/44008 , H04N21/44218 , H04N21/4722 , H04N21/4788 , H04N21/632
摘要： In response to a gestural command, a video currently being watched can be identified by extracting at least one decoded frame from a television transmission. The frame can be transmitted to a separate mobile device for requesting an image search and for receiving the search results. The search results can be used to obtain more information. The user's social networking friends can also be contacted to obtain more information about the clip.
摘要翻译：响应于手势命令，可以通过从电视传输中提取至少一个解码的帧来识别当前正在观看的视频。该帧可以被发送到单独的移动设备，用于请求图像搜索和接收搜索结果。搜索结果可用于获取更多信息。还可以联系用户的社交网络朋友以获取有关剪辑的更多信息。

54. 发明申请

WO2013020247A1 PARAMETERIZED 3D FACE GENERATION 审中-公开
标题翻译：参数化3D面产生
公开(公告)号：WO2013020247A1
公开(公告)日：2013-02-14
申请号：PCT/CN2011/001305
申请日：2011-08-09
申请人： INTEL CORPORATION , TONG, Xiaofeng , HU, Wei , DU, Yangzhou , ZHANG, Yimin
发明人： TONG, Xiaofeng , HU, Wei , DU, Yangzhou , ZHANG, Yimin
IPC分类号： G06T17/00
CPC分类号： G06T17/00
摘要： Systems, devices and methods are described including receiving a semantic description and associated measurement criteria for a facial control parameter, obtaining principal component analysis (PCA) coefficients, generating 3D faces in response to the PCA coefficients, determining a measurement value for each of the 3D faces based on the measurement criteria, and determining a regression parameters for the facial control parameter based on the measurement values.
摘要翻译：描述了系统，设备和方法，包括接收面部控制参数的语义描述和相关联的测量标准，获得主成分分析（PCA）系数，响应于PCA系数生成3D面，确定3D中每一个的测量值基于测量标准的面部，以及基于测量值确定面部控制参数的回归参数。

55. 发明申请

WO2012139269A1 TRACKING AND RECOGNITION OF FACES USING SELECTED REGION CLASSIFICATION 审中-公开
标题翻译：使用选定区域分类来跟踪和识别
公开(公告)号：WO2012139269A1
公开(公告)日：2012-10-18
申请号：PCT/CN2011/072583
申请日：2011-04-11
申请人： INTEL CORPORATION , WANG, Tao , LI, Jianguo , DU, Yangzhou , LI, Qiang , ZHANG, Yimin
发明人： WANG, Tao , LI, Jianguo , DU, Yangzhou , LI, Qiang , ZHANG, Yimin
IPC分类号： G06K9/00
CPC分类号： G06K9/00288 , G06K9/00221
摘要： Methods, apparatuses, and articles associated with facial tracking and recognition are disclosed. In embodiments, facial images may be detected in video or still images and tracked. After normalization of the facial images, feature data may be extracted from selected regions of the faces to compare to associated feature data in known faces. The selected regions may be determined using a boosting machine learning processes over a set of known images. After extraction, individual two-class comparisons may be performed between corresponding feature data from regions on the tested facial images and from the known facial image. The individual two-class classifications may then be combined to determine a similarity score for the tested face and the known face. If the similarity score exceeds a threshold, an identification of the known face may be output or otherwise used. Additionally, tracking with voting may be performed on faces detected in video. After a threshold of votes is reached, a given tracked face may be associated with a known face.
摘要翻译：公开了与面部跟踪和识别有关的方法，装置和文章。在实施例中，可以在视频或静止图像中检测面部图像并进行跟踪。在面部图像归一化之后，可以从面部的选定区域提取特征数据，以与已知面部中的相关特征数据进行比较。可以使用一组已知图像上的升压机学习处理来确定所选择的区域。提取后，可以在来自所测试的面部图像上的区域和来自已知面部图像的相应特征数据之间进行单独的两类比较。然后可以组合个体两类分类以确定测试面部和已知面部的相似性得分。如果相似性分数超过阈值，则可以输出或以其他方式使用已知面部的识别。此外，可以对在视频中检测到的脸部进行投票跟踪。在达成一个选票之后，一个给定的被追踪的面孔可能与一个已知的面孔相关联。

56. 发明申请

US20090169065A1 Detecting and indexing characters of videos by NCuts and page ranking 有权
标题翻译：通过NCuts和页面排名检测和索引视频的字符
公开(公告)号：US20090169065A1
公开(公告)日：2009-07-02
申请号：US12006019
申请日：2007-12-28
申请人： Tao Wang , Jianguo Li , Du Yangzhou , Yimin Zhang
发明人： Tao Wang , Jianguo Li , Du Yangzhou , Yimin Zhang
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/00268 , G06F17/30781
摘要： Apparatuses, systems, and computer program products that detect and/or index characters of videos are disclosed. One or more embodiments comprise an apparatus an apparatus having a feature extraction module and a cast indexing module. The feature extraction module may extract features of a scale invariant feature transform (SIFT) for face sets of a video and the cast indexing module may detect one or more characters of the video via one or more associations of clusters of the features. Some alternative embodiments may include a cast ranking module to sort characters of the video, considering such factors as appearance times of the characters, appearance frequencies of the characters, and page rankings of the characters. The apparatus may associate or partition the clusters based on a normalized cut process, as well as detect the characters based on measures of distances of nodes associated with the features. Numerous embodiments may detect the characters based upon partitioning the clusters via solutions for eigenvalue systems for matrices of nodes of the clusters.
摘要翻译：公开了检测和/或索引视频字符的装置，系统和计算机程序产品。一个或多个实施例包括具有特征提取模块和铸造分度模块的装置的装置。特征提取模块可以提取视频的面部集合的尺度不变特征变换（SIFT）的特征，并且投射索引模块可以经由特征的聚类的一个或多个关联来检测视频的一个或多个字符。考虑到字符的出现时间，字符的出现频率以及字符的页面排序等因素，一些备选实施例可以包括用于对视频的字符进行排序的投射排序模块。该设备可以基于归一化的切割过程来关联或分割群集，并且基于与特征相关联的节点的距离的测量来检测角色。许多实施例可以基于通过针对簇的节点的矩阵的特征值系统的解决方案来划分簇来检测字符。

57. 发明授权

US08705810B2 Detecting and indexing characters of videos by NCuts and page ranking 有权
标题翻译：通过NCuts和页面排名检测和索引视频的字符
公开(公告)号：US08705810B2
公开(公告)日：2014-04-22
申请号：US12006019
申请日：2007-12-28
申请人： Tao Wang , Jianguo Li , Du Yangzhou , Yimin Zhang
发明人： Tao Wang , Jianguo Li , Du Yangzhou , Yimin Zhang
IPC分类号： G06K9/00
CPC分类号： G06K9/00268 , G06F17/30781
摘要： Apparatuses, systems, and computer program products that detect and/or index characters of videos are disclosed. One or more embodiments comprise an apparatus an apparatus having a feature extraction module and a cast indexing module. The feature extraction module may extract features of a scale invariant feature transform (SIFT) for face sets of a video and the cast indexing module may detect one or more characters of the video via one or more associations of clusters of the features. Some alternative embodiments may include a cast ranking module to sort characters of the video, considering such factors as appearance times of the characters, appearance frequencies of the characters, and page rankings of the characters. The apparatus may associate or partition the clusters based on a normalized cut process, as well as detect the characters based on measures of distances of nodes associated with the features. Numerous embodiments may detect the characters based upon partitioning the clusters via solutions for eigenvalue systems for matrices of nodes of the clusters.
摘要翻译：公开了检测和/或索引视频字符的装置，系统和计算机程序产品。一个或多个实施例包括具有特征提取模块和铸造分度模块的装置的装置。特征提取模块可以提取视频的面部集合的尺度不变特征变换（SIFT）的特征，并且投射索引模块可以经由特征的聚类的一个或多个关联来检测视频的一个或多个字符。考虑到字符的出现时间，字符的出现频率以及字符的页面排序等因素，一些备选实施例可以包括用于对视频的字符进行排序的投射排序模块。该设备可以基于归一化的切割过程来关联或分割群集，并且基于与特征相关联的节点的距离的测量来检测角色。许多实施例可以基于通过针对簇的节点的矩阵的特征值系统的解决方案来划分簇来检测字符。

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