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. 发明申请

WO2005052673A2 LIQUID CRYSTAL DISPLAY WITH ADAPTIVE COLOR 审中-公开
标题翻译：具有自适应颜色的液晶显示
公开(公告)号：WO2005052673A2
公开(公告)日：2005-06-09
申请号：PCT/US2004/039085
申请日：2004-11-19
申请人： SHARP LABORATORIES OF AMERICA, INC. , LI, Baoxin , FENG, Xiao-Fan , DALY, Scott, J. , SEZAN, M., Ibrahim , VAN BEEK, Petrus, J., L. , PAN, Hao
发明人： LI, Baoxin , FENG, Xiao-Fan , DALY, Scott, J. , SEZAN, M., Ibrahim , VAN BEEK, Petrus, J., L. , PAN, Hao
IPC分类号： G02F
CPC分类号： H04N9/643 , G02B27/0093 , H04N9/30 , H04N9/68 , H04N17/04
摘要： The patent relates to displays with adaptive color.
摘要翻译：该专利涉及具有自适应颜色的显示器。

2. 发明申请

WO2007061495A2 VIRTUAL VIEW SPECIFICATION AND SYNTHESIS IN FREE VIEWPOINT TELEVISION APPLICATIONS 审中-公开
标题翻译：免费视点电视应用中的虚拟视图规范和综合
公开(公告)号：WO2007061495A2
公开(公告)日：2007-05-31
申请号：PCT/US2006/036566
申请日：2006-09-18
申请人： SHARP LABORATORIES OF AMERICA, INC. , LI, Baoxin
发明人： LI, Baoxin
IPC分类号： G06T15/20
CPC分类号： G06T15/20 , G06T7/97 , G06T2207/20088 , G06T2207/20228
摘要： A system that receives a first video stream of a scene having a first viewpoint and a second video stream having a second viewpoint wherein camera calibration between the first viewpoint and the second viewpoint is unknown. A viewer selects a viewer viewpoint generally between the first viewpoint and the second viewpoint, and the system synthesizes the viewer viewpoint based upon the first video stream and the second video stream.
摘要翻译：接收具有第一视点的场景的第一视频流和具有第二视点的第二视频流的系统，其中第一视点和第二视点之间的照相机校准未知。观众通常在第一视点和第二视点之间选择观看者视点，并且系统基于第一视频流和第二视频流来合成观看者视点。

3. 发明申请

WO2010144259A1 ULTRA-LOW DIMENSIONAL REPRESENTATION FOR FACE RECOGNITION UNDER VARYING EXPRESSIONS 审中-公开
标题翻译：用于在不断变化的表达下进行脸部识别的超低维度表示
公开(公告)号：WO2010144259A1
公开(公告)日：2010-12-16
申请号：PCT/US2010/036206
申请日：2010-05-26
申请人： ARIZONA BOARD OF REGENTS ACTING FOR AND ON BEHALF OF ARIZONA STATE UNIVERSITY , NAGESH, Pradeep , LI, Baoxin
发明人： NAGESH, Pradeep , LI, Baoxin
IPC分类号： G06K9/00
CPC分类号： G06K9/00288 , G06K9/00275 , G06K9/00308 , G06K9/624
摘要： A method, apparatus and computer program product are provided for identifying an unknown subject using face recognition. In particular, upon receiving a plurality of images depicting a subject, the method may include deriving and storing a common component image and a gross innovation component image associated with the subject, wherein the subject can later be identified in a new image using these two stored images. The common component image may capture features that are common to all of the received images depicting the subject, whereas the gross innovation component image may capture a combination of the features that are unique to each of the received images. The method may further include deriving and storing a low-rank data matrix associated with the received images, wherein the low-rank data matrix may capture any illumination differences and/or occlusions associated with the received images.
摘要翻译：提供了一种用于使用人脸识别识别未知对象的方法，装置和计算机程序产品。特别地，在接收到描绘对象的多个图像时，该方法可以包括导出和存储与对象相关联的公共分量图像和总体创新分量图像，其中随后可以使用这两个存储的新图像在新图像中识别对象图片。公共分量图像可以捕获描述主题的所有接收到的图像共有的特征，而总体创新分量图像可以捕获对每个接收到的图像是唯一的特征的组合。该方法还可以包括导出和存储与接收到的图像相关联的低秩数据矩阵，其中低等级数据矩阵可以捕获与接收到的图像相关联的任何照明差异和/或遮挡。

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