-
公开(公告)号：KR1020110048827A
公开(公告)日：2011-05-12
申请号：KR1020090105560
申请日：2009-11-03
Applicant: 한국전자통신연구원
Abstract: PURPOSE: An authentication system is provided to realize obtaining and processing of a facial image of a user in local distance. CONSTITUTION: A camera(110) photographs an image of a user(300). An acquisition unit(120) obtains a facial image in the image. A recognition part(130) recognizes the user. If the user is recognized, a main controller(140) searches user service information. A transmission unit(150) transmits the delivered user service information to a multimedia device. A display unit(170) indicates the image.
Abstract translation: 目的：提供一种认证系统，以实现用户在本地距离的面部图像的获取和处理。 构成：相机（110）拍摄用户的图像（300）。 获取单元（120）获得图像中的面部图像。 识别部件（130）识别用户。 如果用户被识别，则主控制器（140）搜索用户服务信息。 发送单元（150）将所递送的用户服务信息发送到多媒体设备。 显示单元（170）表示图像。
-
公开(公告)号：KR1020100062809A
公开(公告)日：2010-06-10
申请号：KR1020090023987
申请日：2009-03-20
Applicant: 한국전자통신연구원
CPC classification number: G06K9/00899 , G06K9/00228 , G06K9/2018
Abstract: PURPOSE: A method for detecting a forged face and an apparatus thereof are provided to detect a forgery face by extracting the characteristics of a forgery face based on an infrared ray image of a subject onto which a line beam is projected. CONSTITUTION: A beam projection unit(10) projects a line beam onto a subject, and an image acquisition unit(20) acquires an infrared image onto which the line beam is projected. An infrared ray image processing unit(40) extracts the characteristics of a forgery face based on the linear pattern projected onto the acquired infrared ray image. A forgery face detection unit(50) compares the range induced from the characteristics of the extracted forgery face, and detects whether or not the face is forged.
Abstract translation: 目的：提供一种用于检测锻造面的方法及其装置，用于通过基于投影线束的被摄体的红外线图像提取伪造面的特性来检测伪造面。 构成：射束投影单元（10）将线束投影到被摄体上，图像获取单元（20）获取投影线束的红外图像。 红外线图像处理单元（40）基于投影到获取的红外线图像上的线状图案来提取伪造面的特性。 伪造面部检测单元（50）比较从提取的伪造面的特性引起的范围，并且检测脸部是否被锻造。
-
公开(公告)号：KR100927596B1
公开(公告)日：2009-11-23
申请号：KR1020070096934
申请日：2007-09-21
Applicant: 한국전자통신연구원
CPC classification number: G06K9/6285 , G06F21/32
Abstract: Provided a secure pattern recognition method. The method includes: receiving data and generating a probe by converting the received data into a template for pattern recognition; accessing a gallery that is a template registered and stored in advance; determining a region to which the probe belongs and obtaining the center point of the region; obtaining a hash value of the center point and coordinate of the probe; and determining whether or not the hash value of the center point and a hash value stored in the gallery are equal and determining whether or not the probe and the gallery are classified into the same class by calculating whether or not the coordinate of the probe is inside a decision boundary configured with thresholds on the basis of the coordinates of the center point.
Abstract translation: 提供了一种安全模式识别方法。 该方法包括：通过将接收到的数据转换成用于模式识别的模板来接收数据并生成探测; 访问作为预先登记和存储的模板的图库; 确定所述探针所属的区域并获取所述区域的中心点; 获得探测点的中心点和坐标的散列值; 以及确定中心点的散列值和存储在图库中的散列值是否相等，并且通过计算探针的坐标是否在内部来确定探测器和图库是否被分类为相同的类别 基于中心点的坐标由阈值配置的判定边界。
-
公开(公告)号：KR1020090045010A
公开(公告)日：2009-05-07
申请号：KR1020080102461
申请日：2008-10-20
Applicant: 한국전자통신연구원
Abstract: 시스템이나 데이터베이스에 등록된 데이터가 유출되더라도 유출된 데이터로부터 원본 데이터에 관련된 정보를 유추해 낼 수 없도록 원본 데이터를 안전한 형태로 변환하는 데이터 보호기술이 필요하다. 본 발명에서는 이러한 과제를 해결하기 위해 정수(n) 차원의 등록 특징 벡터 g(g = [g
1 , g
2 , ..., g
n ]
T )를 생성하는 단계, 상기 등록 특징 벡터로부터 상기 정수(n)보다 작은 정수(m ＜ n) 차원의 저차원 좌표점들을 생성하는 단계, 상기 생성된 저차원 좌표점들 각각에 대해 상기 m차원의 좌표축 상에 하나 이상의 가좌표점들을 생성하는 단계 및 상기 저차원 좌표점들 및 상기 가좌표점들을 포함하는 등록 템플릿을 생성하는 단계를 포함하는 것을 특징으로 하는 데이터 보호를 위한 템플릿 생성 방법이 제공된다.
패턴 인식, 등록 템플릿, 프로부, 갤러리-
公开(公告)号：KR1020090031093A
公开(公告)日：2009-03-25
申请号：KR1020070096934
申请日：2007-09-21
Applicant: 한국전자통신연구원
CPC classification number: G06K9/6285 , G06F21/32
Abstract: A method and a device for data pattern recognition for data protection are provided to convert an original data into a safe form which is not to be analogized after an outflow of a converted original data. A data to be compared is inputted. The inputted data is converted into a template for pattern recognition, and a probe is generated(S1200). A gallery which is a registered template is called to determine whether a probe and a registered template are the same or not(S1210). An area where a probe belongs to is determined, and an area related value of the corresponding area is calculated(S1220). The coordinate of probe and an area related value are compared to each other, and it is determined that the coordinate of probe is in a boundary line which is comprised of thresholds values(S1230). A hash value of the center of the area in which probe belongs and the hash value stored in gallery are compared to determine whether the two hash value are the same. If the hash values are different, it is determined as different kind(S1260). If the hash values are the same, it is determined whether the coordinate of probe is inside the defined decision boundary based on the center point coordinate(S1240). The coordinate of probe and area related value are classified as the same kind(S1250).
Abstract translation: 提供用于数据保护的数据模式识别的方法和装置，用于将原始数据转换成在转换的原始数据流出之后不被类比的安全形式。 输入要比较的数据。 将输入的数据转换为用于模式识别的模板，并生成探测（S1200）。 调用作为注册模板的画廊来确定探针和注册的模板是否相同（S1210）。 确定探头属于的区域，并计算相应区域的面积相关值（S1220）。 将探测坐标和面积相关值进行比较，并确定探测器的坐标在由阈值组成的边界线（S1230）中。 比较探测器所属区域的中心和存储在画廊中的散列值的哈希值，以确定两个哈希值是否相同。 如果散列值不同，则确定为不同种类（S1260）。 如果哈希值相同，则基于中心点坐标来确定探针的坐标是否在定义的判定边界内（S1240）。 探测坐标和区域相关值被分类为相同类型（S1250）。
-
Patent Agency Ranking
公开(公告)号：KR1020090031084A
公开(公告)日：2009-03-25
申请号：KR1020070096923
申请日：2007-09-21
Applicant: 한국전자통신연구원
CPC classification number: G06K9/00228 , G06K9/6201
Abstract: A face recognition system, a method of face recognition registration and authentication are provided to improve a face recognition in a pose change by performing a standardization of facial image using facial elements correlation model of an acquired facial image. A registration unit(110) produces a correlation model between facial elements from the inputted face image, standardize a face by using the correlation model, and extracts a first facial characteristic vector. A database unit(100) stores the correlation model data and the first facial characteristic vector. An authentication unit(120) standardizes detected facial elements from inputted facial image, extracts a second facial characteristic vector, and compares the second facial characteristic vector with the first facial characteristic vector to authenticate. A first recognition unit(111) takes picture of the face of a registered person and recognizes the facial information. A first detector(112) detects facial elements from the facial image. The generating unit(113) produces the correlation model between the facial elements.
Abstract translation: 提供一种面部识别系统，一种面部识别登记和认证方法，通过使用获取的面部图像的面部元素相关模型执行面部图像的标准化来改善姿势变化中的面部识别。 注册单元（110）从输入的面部图像产生面部元素之间的相关模型，通过使用相关模型来标准化脸部，并提取第一面部特征向量。 数据库单元（100）存储相关模型数据和第一面部特征向量。 认证单元（120）对所输入的面部图像的检测到的面部元素进行标准化，提取第二面部特征向量，并将第二面部特征向量与第一面部特征向量进行比较以进行认证。 第一识别单元（111）拍摄登记的人的面部并识别面部信息。 第一检测器（112）从面部图像检测面部元素。 生成单元（113）产生面部元素之间的相关模型。
-
公开(公告)号：KR100862352B1
公开(公告)日：2008-10-13
申请号：KR1020070096922
申请日：2007-09-21
Applicant: 한국전자통신연구원
IPC: H04N5/63
CPC classification number: H04N5/63 , G06F1/32 , G06F3/012 , H04N21/44218
Abstract: An automatic power control apparatus of a video appliance and a method thereof are provided to control the power of the video appliance based on positions of a viewer by detecting position information of the viewer, comparing horizontality of the viewer with the set horizontality, and outputting a warning sound. An automatic power control apparatus(100) of a video appliance comprises an image input part(200), a position detecting part(201), a horizontality calculator(202), a warning sound output part(203), a power signal transmitting and receiving part(204), a power supply part(205), a vision control part(206), a storage part(207), a horizontality sensing part(208), and a setup part(209). The position detecting part detects position information from the photographed image. The horizontality calculator calculates horizontality by using the detected position information and compares the horizontality with a set horizontality. The warning sound output part outputs warning sound by corresponding to the compared horizontality. The power signal transmitting and receiving part outputs a power blocking signal to the image device by corresponding to the compared horizontality. The vision control part sets a photographing period of the image input part. The horizontality sensing part detects the horizontality of the position detecting part.
Abstract translation: 提供一种视频设备的自动电源控制装置及其方法，用于通过检测观众的位置信息，将观众的水平度与设定的水平度进行比较，并基于观看者的位置输出视频设备的功率， 警告声。 视频设备的自动功率控制设备（100）包括图像输入部分（200），位置检测部分（201），水平计算器（202），警告声音输出部分（203），功率信号传输和 接收部分（204），电源部分（205），视觉控制部分（206），存储部分（207），水平度感测部分（208）和设置部分（209）。 位置检测部分检测来自拍摄图像的位置信息。 水平度计算器通过使用检测到的位置信息来计算水平度，并将水平度与设定的水平度进行比较。 警告音输出部分根据比较的水平度输出警告声。 功率信号发送和接收部分对应于比较的水平度，向图像装置输出功率阻塞信号。 视觉控制部设定图像输入部的拍摄期间。 水平感测部检测位置检测部的水平度。
-
公开(公告)号：KR1020080077340A
公开(公告)日：2008-08-22
申请号：KR1020080068665
申请日：2008-07-15
Applicant: 한국전자통신연구원
IPC: G06F17/30
CPC classification number: G06F17/30961
Abstract: A computer-readable recording medium storing a data structure searching data is provided to offer the new data structure faster and more memory-efficient than a skip list data structure while guaranteeing search performance similar to a balanced tree-based data structure through probability-based balancing like the skip list data structure. A node has distance property for recognizing a node in data search by using a distance vertically reaching to a vertical surface from a predetermined starting point and height property equalizing node distribution of entire binary tree in data insertion or deletion by using a distance vertically reaching the horizontal surface from the starting point. A cloud comprises more than one node and is bound by a set arranging the modes forming the cloud according to the distance property of each node. A cloud field comprises more than one cloud. The cloud defines a representative node, the eldest node, and a younger node, and the height of the cloud is defined by the height property of the representative node of the cloud.
Abstract translation: 提供了一种存储数据结构搜索数据的计算机可读记录介质，以提供比跳过列表数据结构更快和更高存储效率的新数据结构，同时通过基于概率的平衡来保证类似于平衡的基于树的数据结构的搜索性能 像跳过列表数据结构一样。 节点具有距离属性，用于通过使用从预定起点垂直到达垂直表面的距离来识别数据搜索中的节点，并且通过使用垂直到达水平的距离来均衡整个二叉树的数据插入或删除中的节点分布 表面起点。 云包括多个节点，并且由根据每个节点的距离属性布置形成云的模式的集合来约束。 云场包含多个云。 云定义了一个代表性的节点，最大的节点和一个较小的节点，云的高度由云的代表性节点的height属性定义。
-
公开(公告)号：KR1020080052098A
公开(公告)日：2008-06-11
申请号：KR1020060124149
申请日：2006-12-07
Applicant: 한국전자통신연구원 , 조선대학교산학협력단
CPC classification number: G06K9/00087
Abstract: A method and an apparatus for matching a fingerprint by using minutiae and binary image of the fingerprint are provided to reduce false acceptance rate by executing the fingerprint matching. An apparatus for matching a fingerprint includes an extracting unit(210), a comparing unit(220), a compensating unit(230) and an authenticating unit(240). The extracting unit receives the first fingerprint image and the second fingerprint image, extracts minutiae and binary image from them, and outputs the minutiae and the binary image. The comparing unit acquires position and orientation difference between two minutiae on the basis of the minutiae information of the first fingerprint image and the second fingerprint image, and outputs the position and orientation difference. The compensating unit compensates the minutiae and the binary image of the comparing fingerprint and the registered fingerprint on the basis of compensating parameters obtained from the minutiae and the binary image outputted by the comparing unit. The authenticating unit performs an authentication procedure via similarity by comparing the compensated minutiae and binary image of the comparing fingerprint with those of the registered fingerprint.
Abstract translation: 提供了通过使用指纹的细节和二值图像来匹配指纹的方法和装置，以通过执行指纹匹配来减少错误接受率。 用于匹配指纹的装置包括提取单元（210），比较单元（220），补偿单元（230）和认证单元（240）。 提取单元接收第一指纹图像和第二指纹图像，从中提取细节和二进制图像，并输出细节和二进制图像。 比较单元基于第一指纹图像的细节信息和第二指纹图像获取两个细节之间的位置和取向差，并输出位置和方位差。 补偿单元根据从细节获得的补偿参数和由比较单元输出的二进制图像补偿比较指纹和登记指纹的细节和二进制图像。 认证单元通过将比较指纹的补偿细节和二进制图像与登记的指纹的相比较，通过相似性来执行认证过程。
-
公开(公告)号：KR1020080022729A
公开(公告)日：2008-03-12
申请号：KR1020060086266
申请日：2006-09-07
Applicant: 한국전자통신연구원
IPC: G06K9/00
CPC classification number: H04L9/3231
Abstract: A method and a device for recognizing biometrics are provided to lower an FRR(False Rejection Rate), prevent an unauthorized person from inferring biometric information of a user from a template, and generate new templates numerously from the same biometric information even if the template is leaked out. A user register(100) converts a first registration template extracted by receiving biometric information of a user into a second registration template by using a random number cross matrix and a random number vector, and stores the second registration template. A user authenticator(300) converts a first authentication template extracted by receiving the biometric information of the user into a second authentication template by using the random number cross matrix and the random number vector used in the user register, and stores the second authentication template. A conversion key storing part(200) provides the same random number cross matrix and vector to the user register and the user authenticator. The conversion key storing part is a device separated from the user authenticator and the user register.
Abstract translation: 提供用于识别生物识别的方法和装置以降低FRR（假拒绝率），防止未经授权的人从模板中推断用户的生物特征信息，并且从相同的生物特征信息生成新的模板，即使模板是 泄露出去。 用户寄存器（100）通过使用随机数字交叉矩阵和随机数向量将通过接收用户的生物特征信息提取的第一注册模板转换为第二注册模板，并存储第二注册模板。 用户认证器（300）通过使用在用户注册表中使用的随机数交叉矩阵和随机数向量将通过接收用户的生物特征信息提取的第一认证模板转换为第二认证模板，并存储第二认证模板。 转换密钥存储部分（200）向用户寄存器和用户认证器提供相同的随机数交叉矩阵和向量。 转换密钥存储部分是与用户认证器和用户注册器分离的设备。
-
-
-
-
-
-
-
-
-
Search Results
127
records
(took 0.029 seconds)
