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

US20110141105A1 Facial Animation System and Production Method 有权
标题翻译：面部动画系统和制作方法
公开(公告)号：US20110141105A1
公开(公告)日：2011-06-16
申请号：US12831666
申请日：2010-07-07
申请人： Wen-Hung Ting , Chen-Lan Yen , Wen-Liang Chi , Duan-Li Liao
发明人： Wen-Hung Ting , Chen-Lan Yen , Wen-Liang Chi , Duan-Li Liao
IPC分类号： G06T15/70
CPC分类号： G06T13/40
摘要： A facial animation production method for producing 3-dimensional (3D) facial animation data in response to input video data includes the following steps. First, data positioning and character sorting processes are performed on the input video data to acquire first-layer character data, for indicating multiple first-layer character points, and first-layer model data. Next, first-layer model outline data and first-layer character outline data are respectively obtained according to the first-layer model data and the first-layer character data. Then, the first-layer character outline data is compared with the first-layer model outline data to judge whether a judgment condition is satisfied. If not, output character data are produced according to the first-layer character data, and fundamental facial-mesh transformation data are thus produced. Thereafter, the 3D facial animation data are displayed according to the fundamental facial-mesh transformation data.
摘要翻译：用于响应于输入视频数据产生三维（3D）面部动画数据的面部动画制作方法包括以下步骤。首先，对输入视频数据进行数据定位和字符排序处理，以获取用于指示多个第一层字符点的第一层字符数据和第一层模型数据。接下来，根据第一层模型数据和第一层字符数据分别获得第一层模型轮廓数据和第一层字符轮廓数据。然后，将第一层字符轮廓数据与第一层模型轮廓数据进行比较，以判断是否满足判断条件。如果不是，则根据第一层字符数据产生输出字符数据，从而产生基本面部网格变换数据。此后，根据基本面部网格变换数据显示3D面部动画数据。

2. 发明授权

US08648866B2 Facial animation system and production method 有权
标题翻译：面部动画制作及制作方法
公开(公告)号：US08648866B2
公开(公告)日：2014-02-11
申请号：US12831666
申请日：2010-07-07
申请人： Wen-Hung Ting , Chen-Lan Yen , Wen-Liang Chi , Duan-Li Liao
发明人： Wen-Hung Ting , Chen-Lan Yen , Wen-Liang Chi , Duan-Li Liao
IPC分类号： G06T13/00 , G06T1/00 , G06F17/00
CPC分类号： G06T13/40
摘要： A facial animation production method for producing 3-dimensional (3D) facial animation data in response to input video data includes the following steps. First, data positioning and character sorting processes are performed on the input video data to acquire first-layer character data, for indicating multiple first-layer character points, and first-layer model data. Next, first-layer model outline data and first-layer character outline data are respectively obtained according to the first-layer model data and the first-layer character data. Then, the first-layer character outline data is compared with the first-layer model outline data to judge whether a judgment condition is satisfied. If not, output character data are produced according to the first-layer character data, and fundamental facial-mesh transformation data are thus produced. Thereafter, the 3D facial animation data are displayed according to the fundamental facial-mesh transformation data.
摘要翻译：用于响应于输入视频数据产生三维（3D）面部动画数据的面部动画制作方法包括以下步骤。首先，对输入视频数据进行数据定位和字符排序处理，以获取用于指示多个第一层字符点的第一层字符数据和第一层模型数据。接下来，根据第一层模型数据和第一层字符数据分别获得第一层模型轮廓数据和第一层字符轮廓数据。然后，将第一层字符轮廓数据与第一层模型轮廓数据进行比较，以判断是否满足判断条件。如果不是，则根据第一层字符数据产生输出字符数据，从而产生基本面部网格变换数据。此后，根据基本面部网格变换数据显示3D面部动画数据。

3. 发明授权

US08010464B2 Computerized data equidistant-mapping method and computer system using the same 有权
标题翻译：计算机数据等距映射方法和使用该方法的计算机系统
公开(公告)号：US08010464B2
公开(公告)日：2011-08-30
申请号：US11965017
申请日：2007-12-27
申请人： Shih-Pin Chao , Chien-Chun Kuo , Chen-Lan Yen
发明人： Shih-Pin Chao , Chien-Chun Kuo , Chen-Lan Yen
IPC分类号： G06F15/16
CPC分类号： G06N3/08
摘要： A computerized data equidistant-mapping method and a computer system using the same are provided. The computerized data equidistant-mapping method is used for mapping M sets of K-dimensional original data into a D-dimensional space in a manner of equidistance. The computerized data equidistant-mapping method includes the following steps. M sets of D-dimensional mapping data each corresponding to each original data respectively and sequentially are generated. An initial mapping data and an initial original data are chosen arbitrarily, wherein the initial mapping data corresponds to the initial original data. The mapping distance between each mapping data and the initial mapping data is computed. The original distance between each original data and the initial original data is computed. Each mapping data is amended according to each mapping distance and each original distance for enabling each mapping data and each original data to have equidistant-mapping relationship gradually.
摘要翻译：提供了一种计算机数据等距映射方法和使用该方法的计算机系统。计算机化的数据等距映射方法用于以等距的方式将M组K维原始数据映射到D维空间中。计算机化数据等距映射方法包括以下步骤。分别和顺序地分别对应于每个原始数据的M组D维映射数据。任意选择初始映射数据和初始原始数据，其中初始映射数据对应于初始原始数据。计算每个映射数据与初始映射数据之间的映射距离。计算每个原始数据与初始原始数据之间的原始距离。每个映射数据根据每个映射距离和每个原始距离进行修改，以使每个映射数据和每个原始数据逐渐具有等距映射关系。

4. 发明授权

US08824750B2 Distributive facial matching and notification system 有权
标题翻译：分布式面部匹配和通知系统
公开(公告)号：US08824750B2
公开(公告)日：2014-09-02
申请号：US13423815
申请日：2012-03-19
申请人： Peter A. Jankowski , Chen-Lan Yen
发明人： Peter A. Jankowski , Chen-Lan Yen
IPC分类号： G06K9/00
CPC分类号： G06K9/00 , G06K9/00221 , G06K9/00979
摘要： A method and a system for distributing facial identifiers to gateways are described. The system has one or more gateways and a web server associate with the gateways. Each gateway is coupled to a video capturing device. The web server identifies one or more gateways using a metadata associated with a picture of a face. The web server then distributes the picture of the face and the metadata to the identified gateways.
摘要翻译：描述了一种用于向网关分发面部标识符的方法和系统。该系统具有一个或多个网关和与网关相关联的网络服务器。每个网关耦合到视频捕获设备。网络服务器使用与脸部照片相关联的元数据来识别一个或多个网关。然后，Web服务器将面部图片和元数据分发到所识别的网关。

5. 发明申请

US20120310657A1 RETURN FRAUD PROTECTION SYSTEM 有权
标题翻译：返回防盗保护系统
公开(公告)号：US20120310657A1
公开(公告)日：2012-12-06
申请号：US13154189
申请日：2011-06-06
申请人： Peter A. Jankowski , Chen-Lan Yen
发明人： Peter A. Jankowski , Chen-Lan Yen
IPC分类号： G06Q10/00 , H04N7/18
CPC分类号： H04N7/18
摘要： A method and a system for determining a return fraud at a store are described. The return fraud protection system has a video recording module, a face capture module, a face icon generator module, and an entrance video clip module. The video recording module records a video at an entrance of the store. The face capture module captures a face of a customer entering the store from the video. The face icon generator module generates a face icon comprising the face of the customer. The entrance video clip generator module generates a video clip of the customer entering the store, associates the video clip of the customer with the corresponding face icon, and provides a client device with a list of face icons with corresponding video clips.
摘要翻译：描述用于确定商店中的返回欺诈的方法和系统。返回欺诈保护系统具有视频记录模块，面部捕获模块，面部图标生成器模块和入口视频剪辑模块。视频记录模块在商店的入口处记录视频。脸部捕获模块从视频中捕获进入商店的客户的脸部。面部图标生成器模块生成包括顾客面部的面部图标。入口视频剪辑生成器模块生成进入商店的客户的视频剪辑，将客户的视频剪辑与相应的面部图标相关联，并向客户端设备提供具有相应视频剪辑的面部图标列表。

6. 发明授权

US08942990B2 Return fraud protection system 有权
标题翻译：退回欺诈保护制度
公开(公告)号：US08942990B2
公开(公告)日：2015-01-27
申请号：US13154189
申请日：2011-06-06
申请人： Peter A. Jankowski , Chen-Lan Yen
发明人： Peter A. Jankowski , Chen-Lan Yen
IPC分类号： G06Q30/02 , G06Q10/10 , G06Q10/06 , G06Q30/06 , G06Q10/08 , H04N7/18
CPC分类号： H04N7/18
摘要： A method and a system for determining a return fraud at a store are described. The return fraud protection system has a video recording module, a face capture module, a face icon generator module, and an entrance video clip module. The video recording module records a video at an entrance of the store. The face capture module captures a face of a customer entering the store from the video. The face icon generator module generates a face icon comprising the face of the customer. The entrance video clip generator module generates a video clip of the customer entering the store, associates the video clip of the customer with the corresponding face icon, and provides a client device with a list of face icons with corresponding video clips.
摘要翻译：描述用于确定商店中的返回欺诈的方法和系统。返回欺诈保护系统具有视频记录模块，面部捕获模块，面部图标生成器模块和入口视频剪辑模块。视频记录模块在商店的入口处记录视频。脸部捕获模块从视频中捕获进入商店的客户的脸部。面部图标生成器模块生成包括顾客面部的面部图标。入口视频剪辑生成器模块生成进入商店的客户的视频剪辑，将客户的视频剪辑与相应的面部图标相关联，并向客户端设备提供具有相应视频剪辑的面部图标列表。

7. 发明申请

US20130243269A1 DISTRIBUTIVE FACIAL MATCHING AND NOTIFICATION SYSTEM 有权
标题翻译：分布式面部匹配与通报系统
公开(公告)号：US20130243269A1
公开(公告)日：2013-09-19
申请号：US13423815
申请日：2012-03-19
申请人： Peter A. Jankowski , Chen-Lan Yen
发明人： Peter A. Jankowski , Chen-Lan Yen
IPC分类号： G06K9/62
CPC分类号： G06K9/00 , G06K9/00221 , G06K9/00979
摘要： A method and a system for distributing facial identifiers to gateways are described. The system has one or more gateways and a web server associate with the gateways. Each gateway is coupled to a video capturing device. The web server identifies one or more gateways using a metadata associated with a picture of a face. The web server then distributes the picture of the face and the metadata to the identified gateways.
摘要翻译：描述了一种用于向网关分发面部标识符的方法和系统。该系统具有一个或多个网关和与网关相关联的网络服务器。每个网关耦合到视频捕获设备。网络服务器使用与脸部照片相关联的元数据来识别一个或多个网关。然后，Web服务器将面部图片和元数据分发到所识别的网关。

8. 发明申请

US20090006281A1 COMPUTERIZED DATA EAUIDISTANT-MAPPING METHOD AND COMPUTER SYSTEM USING THE SAME 有权
标题翻译：计算机数据助理映射方法和使用它的计算机系统
公开(公告)号：US20090006281A1
公开(公告)日：2009-01-01
申请号：US11965017
申请日：2007-12-27
申请人： Shih-Pin Chao , Chien-Chun Kuo , Chen-Lan Yen
发明人： Shih-Pin Chao , Chien-Chun Kuo , Chen-Lan Yen
IPC分类号： G06N3/08 , G06F17/30
CPC分类号： G06N3/08
摘要： A computerized data equidistant-mapping method and a computer system using the same are provided. The computerized data equidistant-mapping method is used for mapping M sets of K-dimensional original data into a D-dimensional space in a manner of equidistance. The computerized data equidistant-mapping method includes the following steps. M sets of D-dimensional mapping data each corresponding to each original data respectively and sequentially are generated. An initial mapping data and an initial original data are chosen arbitrarily, wherein the initial mapping data corresponds to the initial original data. The mapping distance between each mapping data and the initial mapping data is computed. The original distance between each original data and the initial original data is computed. Each mapping data is amended according to each mapping distance and each original distance for enabling each mapping data and each original data to have equidistant-mapping relationship gradually.
摘要翻译：提供了一种计算机数据等距映射方法和使用该方法的计算机系统。计算机化的数据等距映射方法用于以等距的方式将M组K维原始数据映射到D维空间中。计算机化数据等距映射方法包括以下步骤。分别和顺序地分别对应于每个原始数据的M组D维映射数据。任意选择初始映射数据和初始原始数据，其中初始映射数据对应于初始原始数据。计算每个映射数据与初始映射数据之间的映射距离。计算每个原始数据与初始原始数据之间的原始距离。每个映射数据根据每个映射距离和每个原始距离进行修改，以使每个映射数据和每个原始数据逐渐具有等距映射关系。

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