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

US20080279426A1 SYSTEM AND METHOD FOR VERIFYING FACE OF USER USING LIGHT MASK 有权
标题翻译：使用光罩验证用户面部的系统和方法
公开(公告)号：US20080279426A1
公开(公告)日：2008-11-13
申请号：US12115905
申请日：2008-05-06
申请人： Hyun-Soo KIM , Je-Han Yoon , Ji-Hyo Lee , Jae-Yeon Lee , Su-Young Chi , Woo-Han Yun
发明人： Hyun-Soo KIM , Je-Han Yoon , Ji-Hyo Lee , Jae-Yeon Lee , Su-Young Chi , Woo-Han Yun
IPC分类号： G06K9/00
CPC分类号： G06K9/00275 , G06K9/00288 , G06K9/6255 , G06K9/6277
摘要： A system and method for verifying the face of a user using a light mask are provided. The system includes a facial feature extraction unit for extracting a facial feature vector from a facial image received from a camera. A non-user Gaussian Mixture Model (GMM) configuration unit generates a non-user GMM from a facial image stored in a non-user database (DB). A user GMM configuration unit generates a user GMM by applying light masks to a facial image stored in a user DB. A log-likelihood value calculation unit inputs the facial feature vector both to the non-user GMM and to the user GMM, thus calculating log-likelihood values. A user verification unit compares the calculated log-likelihood values with a predetermined threshold, thus verifying whether the received facial image is a facial image of the user.
摘要翻译：提供了一种用于使用光掩模验证用户的脸部的系统和方法。该系统包括面部特征提取单元，用于从从相机接收的面部图像中提取面部特征向量。非用户高斯混合模型（GMM）配置单元从存储在非用户数据库（DB）中的面部图像生成非用户GMM。用户GMM配置单元通过将光掩模应用于存储在用户DB中的面部图像来生成用户GMM。对数似然值计算单元将面部特征向量输入到非用户GMM和用户GMM，从而计算对数似然值。用户验证单元将所计算的对数似然值与预定阈值进行比较，从而验证所接收的面部图像是否是用户的面部图像。

2. 发明授权

US08116538B2 System and method for verifying face of user using light mask 有权
标题翻译：使用光罩验证用户面部的系统和方法
公开(公告)号：US08116538B2
公开(公告)日：2012-02-14
申请号：US12115905
申请日：2008-05-06
申请人： Hyun-Soo Kim , Je-Han Yoon , Ji-Hyo Lee , Jae-Yeon Lee , Su-Young Chi , Woo-Han Yun
发明人： Hyun-Soo Kim , Je-Han Yoon , Ji-Hyo Lee , Jae-Yeon Lee , Su-Young Chi , Woo-Han Yun
IPC分类号： G06K9/00 , G06K9/62 , G06K9/46 , G06F21/00
CPC分类号： G06K9/00275 , G06K9/00288 , G06K9/6255 , G06K9/6277
摘要： A system and method for verifying the face of a user using a light mask are provided. The system includes a facial feature extraction unit for extracting a facial feature vector from a facial image received from a camera. A non-user Gaussian Mixture Model (GMM) configuration unit generates a non-user GMM from a facial image stored in a non-user database (DB). A user GMM configuration unit generates a user GMM by applying light masks to a facial image stored in a user DB. A log-likelihood value calculation unit inputs the facial feature vector both to the non-user GMM and to the user GMM, thus calculating log-likelihood values. A user verification unit compares the calculated log-likelihood values with a predetermined threshold, thus verifying whether the received facial image is a facial image of the user.
摘要翻译：提供了一种用于使用光掩模验证用户的脸部的系统和方法。该系统包括面部特征提取单元，用于从从相机接收的面部图像中提取面部特征向量。非用户高斯混合模型（GMM）配置单元从存储在非用户数据库（DB）中的面部图像生成非用户GMM。用户GMM配置单元通过将光掩模应用于存储在用户DB中的面部图像来生成用户GMM。对数似然值计算单元将面部特征向量输入到非用户GMM和用户GMM，从而计算对数似然值。用户验证单元将所计算的对数似然值与预定阈值进行比较，从而验证所接收的面部图像是否是用户的面部图像。

3. 发明授权

US07634113B2 User authentication system and method thereof 有权
标题翻译：用户认证系统及其方法
公开(公告)号：US07634113B2
公开(公告)日：2009-12-15
申请号：US11291607
申请日：2005-11-30
申请人： Do-Hyung Kim , Jae-Yeon Lee , Su-Young Chi , Ho-Sub Yoon , Kye-Kyung Kim , Soo-Hyun Cho , Hye-Jin Kim , Young-Jo Cho
发明人： Do-Hyung Kim , Jae-Yeon Lee , Su-Young Chi , Ho-Sub Yoon , Kye-Kyung Kim , Soo-Hyun Cho , Hye-Jin Kim , Young-Jo Cho
IPC分类号： G06K9/00 , G06K5/00 , G05B19/00 , G10L21/00
CPC分类号： G06K9/00362
摘要： A user recognizing system and method is provided. According to the user recognizing system and method, user ID and predetermined user feature information are stored, first and second user feature information are extracted from the user image data transmitted from the image input unit, and first and second probabilities that the extracted first and second user feature information determine the predetermined user are respectively generated based on the information stored at the user information database, the first user feature information being absolutely unique biometric information and the second user feature information being unique semibiometric information under a predetermined condition, and ID of the input image is finally determined by combining the first probability and the second probability. According to the user recognizing system and method, a user identity can be authenticated even when the user freely moves.
摘要翻译：提供了一种用户识别系统和方法。根据用户识别系统和方法，存储用户ID和预定用户特征信息，从从图像输入单元发送的用户图像数据中提取第一和第二用户特征信息，以及提取的第一和第二概率的第一和第二概率基于存储在用户信息数据库中的信息分别生成预定用户的用户特征信息，第一用户特征信息是绝对唯一的生物体信息，第二用户特征信息是预定条件下的唯一半身测量信息，以及ID 最终通过组合第一概率和第二概率来确定输入图像。根据用户识别系统和方法，即使用户自由移动，也可以认证用户身份。

4. 发明申请

US20060120569A1 User authentication system and method thereof 有权
公开(公告)号：US20060120569A1
公开(公告)日：2006-06-08
申请号：US11291607
申请日：2005-11-30
申请人： Do-Hyung Kim , Jae-Yeon Lee , Su-Young Chi , Ho-Sub Yoon , Kye-Kyung Kim , Soo-Hyun Cho , Hye-Jin Kim , Young-Jo Cho
发明人： Do-Hyung Kim , Jae-Yeon Lee , Su-Young Chi , Ho-Sub Yoon , Kye-Kyung Kim , Soo-Hyun Cho , Hye-Jin Kim , Young-Jo Cho
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/00362
摘要： A user recognizing system and method is provided. According to the user recognizing system and method, user ID and predetermined user feature information are stored, first and second user feature information are extracted from the user image data transmitted from the image input unit, and first and second probabilities that the extracted first and second user feature information determine the predetermined user are respectively generated based on the information stored at the user information database, the first user feature information being absolutely unique biometric information and the second user feature information being unique semibiometric information under a predetermined condition, and ID of the input image is finally determined by combining the first probability and the second probability. According to the user recognizing system and method, a user identity can be authenticated even when the user freely moves.

5. 发明授权

US06728403B1 Method for analyzing structure of a treatise type of document image 失效
标题翻译：分析文献图像的论文类型结构的方法
公开(公告)号：US06728403B1
公开(公告)日：2004-04-27
申请号：US09496630
申请日：2000-02-02
申请人： Dae-Geun Jang , Kyung-Ae Moon , Young-Sup Hwang , Su-Young Chi , Weon-Geun Oh
发明人： Dae-Geun Jang , Kyung-Ae Moon , Young-Sup Hwang , Su-Young Chi , Weon-Geun Oh
IPC分类号： G06K934
CPC分类号： G06K9/00469
摘要： A method for analyzing structure of a treatise type of document image in order to detect a title, an author and an abstract region and recognize the content in each of the regions is provided. In order to analyze the structure of a treatise type of document, first, the document image divided into a number of regions and the divided regions are classified into text regions and non-text regions according to attributes of the regions. And then, the candidate regions representing an abstract and an introduction is selected, thereafter word regions are extracted from the candidate regions, and an abstract content portion is determined. Thereafter, the title and the author are separated by using the basic form and the type definition representing an arrangement of each of journals. Finally, the content of the separated regions is recognized to generate said table of contents.
摘要翻译：提供了一种用于分析文献图像的论文结构以便检测标题，作者和抽象区域并且识别每个区域中的内容的方法。为了分析论文类型的文档的结构，首先，根据区域的属性将分割成多个区域的文档图像和分割区域分类为文本区域和非文本区域。然后，选择表示抽象和引入的候选区域，之后从候选区域提取字区域，并且确定抽象内容部分。此后，标题和作者通过使用表示各期刊的排列的基本形式和类型定义分开。最后，识别分离区域的内容以产生所述目录。

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