-
公开(公告)号：KR100825756B1
公开(公告)日：2008-04-29
申请号：KR1020060122616
申请日：2006-12-05
Applicant: 한국전자통신연구원
CPC classification number: G06K9/00288 , G06K9/00275
Abstract: A method and an apparatus for extracting a special feature of a face are provided to give weights to face images according to an order of acquiring the face images and reflect recent face image data to update and extract a face feature suitable to face search to thereby achieve a high face recognition rate. Different weights are given to face images of candidates according to an order of acquiring the face images of the candidates and average image data of each candidate and overall average image data are calculated(S120,S130). Inter-class divergence based on a difference between the average image data of each candidate and the overall average image data and intra-class divergence based on a difference between arbitrary image data of each candidate and the average image data of each candidate are calculated(S140). A base vector which maximizes a reference value defined as a ratio of the inter-class divergence to the intra-class divergence is generated(S150).
Abstract translation: 提供用于提取面部特征的方法和装置，以根据获取面部图像的顺序给面部图像加权，并且反映最近的面部图像数据以更新和提取适于面部搜索的面部特征，从而实现 面部识别率高。 根据获取候选的面部图像的顺序和候选的每个候选的平均图像数据的顺序给出候选的面部图像的不同的权重，并且计算总平均图像数据（S120，S130）。 计算基于每个候选的平均图像数据与总平均图像数据之间的差异的类间差异，以及基于每个候选的任意图像数据与每个候选的平均图像数据之间的差异的类内散度（S140 ）。 产生使得定义为类间发散与类内散度的比率的参考值最大化的基向量（S150）。
-
公开(公告)号：KR1020080029685A
公开(公告)日：2008-04-03
申请号：KR1020060096588
申请日：2006-09-29
Applicant: 한국전자통신연구원
IPC: H04L9/32
CPC classification number: H04L63/06 , H04L63/0815 , H04L63/0823
Abstract: A symmetric key-based authentication method and apparatus in multi-domain are provided to solve scalability and efficiency in a symmetric key manner by defining an authentication manner adapted to a multi-domain circumstance having various authentication principal. A symmetric key-based authentication apparatus in multi-domain includes a certificate issue demanding unit(511) demanding a certificate issue from a home domain authentication sever. A certificate/symmetric key receiving unit(513) receives a certificate and a symmetric key issued from the home domain authentication sever according to a certificate issue demand. A certificate transmitting unit(515) transmits the certificate to the home domain authentication sever(520) or an outer domain authentication sever(530). A certificate result receiving unit(517) receives an inspection result of the transmitted certificate from the home domain authentication sever or the outer domain authentication sever.
Abstract translation: 提供了一种基于对称密钥的多域认证方法和装置，通过定义适应具有各种认证主体的多域环境的认证方式，以对称密钥方式解决可扩展性和效率。 多域中的基于对称密钥的认证装置包括要求来自归属域认证服务器的证书问题的证书颁发要求单元（511）。 证书/对称密钥接收单元（513）根据证书发行请求接收从归属域认证服务器发出的证书和对称密钥。 证书发送单元（515）将证书发送到归属域认证服务器（520）或外部域认证服务器（530）。 证书结果接收单元（517）从归属域认证服务器或外域认证服务器接收发送的证书的检查结果。
-
83.发明公开
公开(公告)号：KR1020080029601A
公开(公告)日：2008-04-03
申请号：KR1020060096433
申请日：2006-09-29
Applicant: 한국전자통신연구원
IPC: H04N21/8352
CPC classification number: H04N21/435 , G06Q30/06 , H04N21/234318 , H04N21/235 , H04N21/4725 , H04N21/84 , H04N21/85403 , H04N21/8586
Abstract: A cyber tag for cooperatively associating information of digital objects in video contents, and contents reproducing device, method and system are provided to allow a video contents provider to advertise various products without going through an actual CF(Commercial Film). A tag ID field(110) identifies video contents and a digital object in the video contents, and cooperatively associates the video contents to supplementary information of the digital object. An object generation position field(120) identifies a position where the digital object is generated in displaying the video contents. A time field(130) identifies time at which the digital object appears in displaying the video contents. A correction value field(140) tracks a position movement until the digital object is annihilated after being generated in displaying the video contents. The tag ID field includes a contents ID for identifying the video contents, an object ID for identifying the digital objects, and an information server address informing about an IP address of an information server having the supplementary information of the digital object.
Abstract translation: 提供用于协同地关联视频内容中的数字对象的信息的网络标签，以及内容再现装置，方法和系统，以允许视频内容提供商在不经过实际的CF（商业电影）的情况下广告各种产品。 标签ID字段（110）识别视频内容中的视频内容和数字对象，并且将视频内容协作地关联到数字对象的补充信息。 对象生成位置字段（120）在显示视频内容时识别生成数字对象的位置。 时间字段（130）表示数字对象在显示视频内容时出现的时间。 校正值字段（140）跟踪位置移动，直到数字对象在显示视频内容之后生成之后被消除。 标签ID字段包括用于识别视频内容的内容ID，用于识别数字对象的对象ID，以及通知具有数字对象的补充信息的信息服务器的IP地址的信息服务器地址。
-
公开(公告)号：KR100819027B1
公开(公告)日：2008-04-02
申请号：KR1020060037758
申请日：2006-04-26
Applicant: 한국전자통신연구원
CPC classification number: G06K9/00275 , G06K9/00288 , G06K9/522
Abstract: 본 발명은 얼굴 영상을 이용한 사용자 인증 방법 및 장치에 관한 것으로, (a) 정규화된 공간 영역의 얼굴 영상을 주파수 영역 데이터로 변환하는 단계; (b) 상기 변환된 주파수 영역 데이터로부터 에너지 밀집 영역 정보를 통하여 유효 변환 계수들을 추출하는 단계; (c) 상기 추출된 유효 변환 계수들로부터 특징 벡터를 추출하는 단계; 및 (d) 상기 추출된 특징 벡터와 기 등록된 특징 벡터를 비교하여 사용자 인증을 수행하는 단계로 구성되어, 최소한의 데이터 차원으로 얼굴 영상을 이용한 사용자 인증이 수행되기 때문에 속도와 정확도가 향상되는 사용자 인증 방법 및 장치를 제공할 수 있다.
-
公开(公告)号：KR1020080025610A
公开(公告)日：2008-03-21
申请号：KR1020060090310
申请日：2006-09-18
Applicant: 한국전자통신연구원
CPC classification number: G06K9/0061
Abstract: An iris recognition method and an apparatus for the iris recognition method are provided to detect the iris accurately and efficiently even though an eye is covered by eyebrows or an eyelid in an image of the eye. An iris recognition method includes a step of receiving an image of an eye(S100) and filtering the image with a threshold value to obtain a binary image(S105), a step of searching candidate central search regions for the pupil center using histogram information of the binary image(S110), a step of considering points belonging into the candidate central search regions in the binary image as candidate pupil center points and performing a masking operation on concentric circles obtained by varying the radius of a circle having each of the candidate pupil center points as a center point using eight pupil boundary mask templates to detect the boundary and the center point of the pupil(S115), and a step of performing a masking operation on concentric circles obtained by varying the radius of a circle having the detected center point of the pupil as a center point with six iris boundary mask templates to detect the boundary of the iris(S120).
Abstract translation: 提供了一种虹膜识别方法和用于虹膜识别方法的装置，即使眼睛被眼睛的图像中的眉毛或眼睑覆盖，也能够准确有效地检测虹膜。 虹膜识别方法包括接收眼睛图像的步骤（S100）并用阈值对图像进行滤波以获得二进制图像（S105），使用直方图信息搜索瞳孔中心的候选中心搜索区域的步骤 二进制图像（S110），考虑属于二进制图像中的候选中央搜索区域的点作为候选瞳孔中心点，并对通过改变具有每个候选瞳孔的圆的半径获得的同心圆执行掩蔽操作的步骤 中心点作为中心点，使用八个瞳孔边界掩模模板来检测瞳孔的边界和中心点（S115），以及对通过改变具有检测到的中心的圆的半径获得的同心圆进行掩蔽操作的步骤 瞳孔的点作为具有六个虹膜边界掩模模板的中心点，以检测虹膜的边界（S120）。
-
Patent Agency Ranking
公开(公告)号：KR100809431B1
公开(公告)日：2008-03-05
申请号：KR1020060115443
申请日：2006-11-21
Applicant: 한국전자통신연구원
CPC classification number: G06K9/0061
Abstract: An eye detecting method and apparatus resistant to a screening phenomenon are provided to extract precise eye coordinates by processing images according to a gradient descent method and a learned classifier. When a face image is inputted(S110), the inputted face image is processed based on an edge size and phase of image pixels to extract a face region having symmetry(S120). Eye candidate points are detected based on contrast information of the extracted face region(S130). The peripheral region of the eye candidate points is verified by a classifier(S140). Final eye information is outputted to detect eyes(S150).
Abstract translation: 提供一种抗筛选现象的眼睛检测方法和装置，通过根据梯度下降法和学习分类器处理图像来提取精确的眼睛坐标。 当输入面部图像时（S110），基于图像像素的边缘大小和相位来处理输入的面部图像，以提取具有对称性的面部区域（S120）。 基于所提取的面部区域的对比度信息检测眼睛候选点（S130）。 通过分类器验证眼睛候补点的外围区域（S140）。 输出最终眼睛信息以检测眼睛（S150）。
-
公开(公告)号：KR100785809B1
公开(公告)日：2007-12-13
申请号：KR1020060122601
申请日：2006-12-05
Applicant: 한국전자통신연구원
CPC classification number: G06K17/0029 , G06K19/07713 , G06K2017/0048
Abstract: A system and a method for searching a lost article with RFID are provided to search a location of an article effectively by attaching an RFID tag to personal articles and reduce management expenses by efficiently managing the lost articles in a lost article center. A communicator(310) receives a code including article ID information of the RFID tag attached to the articles. A memory(320) stores the code of the RFID tags. A transceiver(330) transmits an RFID tag code to a lost article management server to inquire the lost article when a user loses the article attached with the RFID tag, and receives lost article location information searched based on the RFID tag code from the lost article management server. The communicator is an infrared communicator receiving the RFID tag code from an infrared port of an RFID tag vending machine. The transceiver receives a text message including the RFID tag code by connecting to the RFID tag vending machine through the Internet and transmits the text message including the RFID tag code to the lost article management server. A removable RFID reader(350) directly reads the code of the RFID tag and transmits the read code to a terminal(200).
Abstract translation: 提供了一种利用RFID搜索丢失物品的系统和方法，通过将RFID标签附加到个人物品上有效地搜索物品的位置，并通过有效地管理丢失物品中心中的遗失物品来减少管理费用。 通信器（310）接收包含附在物品上的RFID标签的物品ID信息的代码。 存储器（320）存储RFID标签的代码。 收发器（330）将丢失的物品管理服务器的RFID标签代码发送到用户丢失附有RFID标签的物品时查询丢失的物品，并根据来自丢失的物品的RFID标签代码接收丢失的物品位置信息 管理服务器。 通信器是从RFID标签自动售货机的红外端口接收RFID标签代码的红外通信器。 收发机通过连接到RFID标签的自动售货机通过因特网接收包括RFID标签代码的文本消息，并将包含RFID标签代码的文本消息发送到丢失的文章管理服务器。 可移动RFID读取器（350）直接读取RFID标签的代码并将读取的代码发送到终端（200）。
-
公开(公告)号：KR100779085B1
公开(公告)日：2007-11-27
申请号：KR1020060054904
申请日：2006-06-19
Applicant: 한국전자통신연구원
Abstract: 본 발명은 전자기 액츄에이터를 이용한 펌프를 개시한다.
본 발명에 의하면, 구조가 간단하면서 소형으로 구현하는 것이 가능하며, 코일에 흐르는 전류를 위한 에너지 외에는 별도의 에너지가 필요없어서 에너지 소비가 적은 유체 수송용 미니 펌프에 사용될 수 있게 되며, 그 결과 비교적 작은 전압에 의해 큰 구동 거리를 가지며 높은 에너지 밀도를 얻을 수 있고 비교적 빠른 응답 속도를 가지는 초소형의 펌프를 제작할 수 있는 기술적인 기반을 제공한다.-
公开(公告)号：KR100759814B1
公开(公告)日：2007-09-20
申请号：KR1020060042014
申请日：2006-05-10
Applicant: 한국전자통신연구원
Abstract: RFID 서비스 제공 방법, 이를 위한 서버, 단말기 및 시스템이 개시된다. 본 발명의 RFID 서비스 제공 방법은 물품에 부착된 RFID 태그로부터 식별정보를 획득하는 단계; 식별정보를 이용하여 물품에 대한 정보를 갖고 있는 제1서버의 주소를 획득하는 단계; 제1서버에 접속하여 물품에 대한 정보 및 물품과 관련된 응용 서비스를 제공하는 복수의 제2서버들의 주소를 획득하는 단계; 및 제2서버들중 하나에 접속하여 해당 응용 서비스를 수신하는 단계를 포함한다.
-
公开(公告)号：KR100734837B1
公开(公告)日：2007-07-03
申请号：KR1020050087027
申请日：2005-09-16
Applicant: 한국전자통신연구원
IPC: G06K9/00
CPC classification number: G06K9/6293 , G06K9/00892
Abstract: 다중 생체 인식 시스템 및 그 방법이 개시된다. 본 발명에 따른 다중 생체 인식 시스템은 단일 비교값 생성부가 서로 다른 조합의 생체정보를 가진 후보자의 비교값 벡터와 상대적 비교가 가능하도록 단일화된 비교값을 생성하므로, 데이터베이스에 등록된 후보자들의 생체정보의 종류와 개수가 일치 하지 않더라도 다중 생체인식이 가능하다.
-
-
-
-
-
-
-
-
-
Search Results
346
records
(took 0.037 seconds)
