-
公开(公告)号：KR1020100090864A
公开(公告)日：2010-08-18
申请号：KR1020090010071
申请日：2009-02-09
Applicant: 삼성전자주식회사
CPC classification number: G06K9/00375 , G06K9/6256 , G06K2009/4666 , G06T7/40 , H04B1/40
Abstract: PURPOSE: A method and a device for recognizing hand shape in portable terminal are provided to generate uniformed training image data which generates a plurality of image of interest area in the same pose and the same size, thereby conveniently obtaining large amount of training images. CONSTITUTION: A device comprises a training unit(122) and a detection unit(124). The training unit generates uniformed training image data which generates a plurality of images of an interest region obtained from an original image in the same pose and the same size. A training unit trains not to make special point in a part which the point is not wanted to be detected in the training image data. After the training processes, the detection unit detects a rotating object from an inputted data.
Abstract translation: 目的：提供一种用于识别便携式终端中的手形的方法和装置，以产生均匀的训练图像数据，该训练图像数据以相同的姿态和相同的大小生成感兴趣区域的多个图像，从而方便地获得大量的训练图像。 构成：装置包括训练单元（122）和检测单元（124）。 训练单元产生均匀的训练图像数据，其生成以相同姿态和相同大小从原始图像获得的感兴趣区域的多个图像。 训练单元不训练在训练图像数据中不希望检测到的部分的特殊点。 在训练处理之后，检测单元从输入的数据检测旋转物体。
-
公开(公告)号：KR1020100081049A
公开(公告)日：2010-07-14
申请号：KR1020090000310
申请日：2009-01-05
Applicant: 삼성전자주식회사
CPC classification number: H04N5/232 , H04N5/23216 , H04N5/23219
Abstract: PURPOSE: A device and a method for photographing image in a portable terminal are provide to determine photographing composition automatically, thereby photographing an image. CONSTITUTION: A camera receives input of an image. A control unit(110) recognizes the received image through an image recognition algorithm. The control unit determines photographing composition corresponding to the recognition result. According to the determined photographing composition, an adjusting unit adjusts the angle of the camera. The adjusting unit adjusts a sensor angle of the camera according to angle adjustment value calculated from the control unit.
Abstract translation: 目的：提供一种用于在便携式终端中拍摄图像的装置和方法，用于自动确定拍摄合成，从而拍摄图像。 构成：相机接收图像的输入。 控制单元（110）通过图像识别算法识别所接收的图像。 控制单元确定与识别结果相对应的拍摄结果。 根据所确定的拍摄结构，调节单元调节相机的角度。 调整单元根据从控制单元计算的角度调整值来调整摄像机的传感器角度。
-
Patent Agency Ranking
公开(公告)号：KR1020090017355A
公开(公告)日：2009-02-18
申请号：KR1020070082027
申请日：2007-08-14
Applicant: 삼성전자주식회사
Abstract: An image photographing apparatus and a method thereof are provided to select a photographing point of time so as to automatically photograph an image where an image tool is controlled after automatically controlling the image tool. An image photographing module changes an angle and focus of a camera lens to photograph an image. A face area extraction module(120) detects and traces a face area in a preview image of the photographed image. An image photographing control module(130) performs a control operation so as to change the angle and focus of the camera lens so that an image structure of the traced and defected face area can satisfy a predetermined criteria.
Abstract translation: 提供一种图像拍摄装置及其方法来选择拍摄时间点，以便在自动控制图像工具之后自动拍摄图像工具被控制的图像。 图像拍摄模块改变相机镜头的角度和焦点以拍摄图像。 脸部区域提取模块（120）检测和追踪拍摄图像的预览图像中的脸部区域。 图像拍摄控制模块（130）执行控制操作，以改变相机镜头的角度和焦点，使得跟踪和缺陷的脸部区域的图像结构可以满足预定标准。
-
公开(公告)号：KR100866234B1
公开(公告)日：2008-10-30
申请号：KR1020060110514
申请日：2006-11-09
Applicant: 삼성전자주식회사
Abstract: 본 발명은 사용자를 판별하여 현재 사용자의 등급을 파악하고, 파악한 사용자 등급에 따라 서비스를 제공하는 사용자 처리장치에 관한 것으로, 사용자 인식을 수행하여 사용자 식별정보를 생성하며, 생성된 사용자 식별정보에 따라 사용자가 등록자 또는 준등록자 또는 비등록자 중의 하나에 해당하는 지 파악하고, 파악된 사용자 등급에 따라 미리 설정된 서비스를 제공한다. 그리고 사용자 처리장치는 사용자에 의해 등록자 변경이 요청되면, 준등록자로 등록된 사용자를 비등록자로 변경할 수 있다.
등록자, 비등록자, 방문자, 사용자 인식-
公开(公告)号：KR1020080090035A
公开(公告)日：2008-10-08
申请号：KR1020070032989
申请日：2007-04-03
CPC classification number: G06K9/00268 , G06F17/30247 , G06K9/6202
Abstract: A system and a method for identifying a visitor with a web service are provided to transfer a message between a server and a client without any message format conversion even if the system is operated in heterogeneous OSs(Operating System), and detect face feature of the visitor periodically on the network without making the visitor register a face image to a visitor database. A visitor database(630) stores a visitor face feature template including face feature of each visitor. A web service client(611) periodically obtains a visitor image output from a camera, detects a face image of the visitor from the obtained image, extracts the face feature from the detected face image, and transmits the extracted face feature to a web service server(620) by using a visitor authentication request message. The server extracts the face feature from the received message, and determines whether the visitor face feature template similar to the extracted face feature is found in the visitor database by using similarity between the visitor face feature templates with the extracted face feature. The server transfers a visitor authentication response message when the visitor face feature template similar to the extracted face feature is found.
Abstract translation: 提供了一种用于识别具有Web服务的访问者的系统和方法，用于在服务器和客户端之间传递消息而不进行任何消息格式转换，即使系统在异构OS（操作系统）中操作，并且检测 访问者定期在网络上，而不使访问者向访问者数据库注册脸部图像。 访问者数据库（630）存储包括每个访问者的面部特征的访问者面部特征模板。 Web服务客户端（611）周期性地获取从相机输出的访问者图像，从所获得的图像中检测访问者的面部图像，从检测到的面部图像中提取面部特征，并将提取的面部特征发送到web服务服务器 （620）通过使用访问者认证请求消息。 服务器从接收到的消息中提取面部特征，并且通过使用访问者面部特征模板与提取的面部特征之间的相似度来确定在访问者数据库中是否找到与提取的面部特征相似的访问者面部特征模板。 当找到与提取的面部特征相似的访问者面部特征模板时，服务器传送访问者身份验证响应消息。
-
公开(公告)号：KR1020080073993A
公开(公告)日：2008-08-12
申请号：KR1020070012950
申请日：2007-02-07
Applicant: 삼성전자주식회사
IPC: G06K17/00 , G08B25/10 , G08B13/196
CPC classification number: G08B25/10 , G06K17/00 , G08B13/196
Abstract: A method for controlling a target and an intelligent robot monitoring service system using the same are provided to perform an intelligent monitoring service by performing a control operation corresponding to a tracking target according to various states. A tracking target is recognized by using at least one or more sensors installed within a predetermined region in a monitoring mode(210). A control region for the recognized tracking target is recognized by using the prestored target information and a process for recognizing a present state of the tracking target is performed(215,220,225,230). A command is outputted to an apparatus for performing a service corresponding to the recognized state when the tracking target enters into the control region(240,245).
Abstract translation: 提供一种用于控制目标的方法和使用其的智能机器人监视服务系统，以通过根据各种状态执行与跟踪目标相对应的控制操作来执行智能监控服务。 通过在监视模式（210）中使用安装在预定区域内的至少一个或多个传感器来识别跟踪目标。 通过使用预存的目标信息来识别用于识别的跟踪目标的控制区域，并且执行用于识别跟踪目标的当前状态的处理（215,220,225,230）。 当跟踪目标进入控制区域（240,245）时，向用于执行对应于识别状态的服务的装置输出命令。
-
公开(公告)号：KR1020080054090A
公开(公告)日：2008-06-17
申请号：KR1020060126235
申请日：2006-12-12
Applicant: 삼성전자주식회사
IPC: H04N5/76
CPC classification number: H04N5/772 , H04N5/23219 , H04N5/775 , H04N9/7921 , H04N9/8063 , H04N2101/00 , H04N2201/0084 , H04N2201/3264 , H04N2201/3266
Abstract: A method and an apparatus for automatically recording images are provided to generate/edit image data automatically and to save a time for editing image data. An information input unit(103) generates image data and voice data of a user. A recognition processing unit(105) performs user recognition with the image data to extract feature points, and compares the feature points and those of image data of a previously stored following target person to check whether the user is the following target person. When the user is a following target person, a following unit(107) sets the user as the following target person and follows him. An information selecting unit(113) checks whether the image data and the voice data satisfy a record reference. If the image data satisfies the record reference, an information editing unit(111) edits the image data and the voice data to generate one or more record image data and record voice data. A memory unit(109) previously stores the image data and the voice data of the following target person, and stores the record image data and the record voice data. A controller(101) controls the respective elements to perform their functions.
Abstract translation: 提供自动记录图像的方法和装置，以自动生成/编辑图像数据，并节省编辑图像数据的时间。 信息输入单元（103）生成用户的图像数据和语音数据。 识别处理单元（105）利用图像数据进行用户识别以提取特征点，并且比较先前存储的跟随目标人物的特征点和图像数据的特征点，以检查用户是否是以下目标人物。 当用户是以下目标人时，以下单元（107）将用户设置为以下目标人并跟随他。 信息选择单元（113）检查图像数据和语音数据是否满足记录参考。 如果图像数据满足记录参考，则信息编辑单元（111）编辑图像数据和语音数据以生成一个或多个记录图像数据并记录语音数据。 存储单元（109）预先存储以下目标人物的图像数据和语音数据，并存储记录图像数据和记录语音数据。 控制器（101）控制各个元件执行其功能。
-
-
-
-
-
-
Search Results
47
records
(took 0.026 seconds)
