Abstract:
자동차의 도어를 잠금 또는 해제하는 스마트 키 장치는, 사용자의 적어도 하나의 생물학적 정보로부터 상기 사용자의 음주 여부를 판단하여 구동 제어 신호를 생성하는 제어부, 접촉되는 상기 사용자의 손가락에 광을 조사하는 발광부, 상기 손가락에 반사되거나 투과되는 광을 수집하여 상기 복수의 생물학적 정보 중 적어도 하나의 생물학적 정보에 대응하는 인체 정보를 생성하는 수광부, 그리고 상기 구동 제어 신호에 따라 상기 스마트 키 장치의 동작을 제어하는 구동부를 포함한다. 운전, 사고, 예방, 혈중 산소 포화도, 맥박수, 광학, 스마트키, 자동차
Abstract:
PURPOSE: A system for recognizing a forged and altered face using gabor feature and a support vector machine (SVM) classification machine and a method thereof are provided to recognize the face efficiently as to peripheral lighting influence or various patterns of the face, by estimating feature point positions of the face from the face area and extracting the gabor feature from the estimated face feature points and using the gabor feature as an input vector of the SVM classification machine. CONSTITUTION: A graph generation unit (100) generates a standard face graph from face image samples. A support vector machine (SVM) learning unit (200) determines an optimum classification plane to discriminate a forged and altered face from face image samples and forged and altered face image samples. A face recognition unit (300) determines forgery of an inputted face image, using the optimum classification plane. The face recognition unit detects a rectangular face area from the face image, and normalizes the rectangular face area into a fixed size, and generates an optimum face graph, using adaboost algorithm. [Reference numerals] (100) Graph generation unit; (200) SVM learning unit; (300) Face recognition unit
Abstract:
PURPOSE: A method for assigning roles to a multi robot is provided to improve the degree of the completion in a task by performing a corresponding role with a different robot if any robot among the robots cannot perform the task. CONSTITUTION: A method for assigning roles to a multi robot comprises: a step of attempting a specific role by a first robot among the robots(210); a step of assigning the specific role to one or more second robots if the first robot cannot perform the specific role(240); and a step of performing the role by the second robot(250). [Reference numerals] (210) First robot executes or attempt execution of a specific role; (220) First robot is unable to execute the role?; (230) First robot keeps executing the role; (240) Execution of the role is assigned to a second robot; (250) Second robot executes the role; (AA) Yes; (BB) No
Abstract:
매개 인터페이스 장치를 이용하여 입력된 단어를 사전 기반으로 보정하여 정확한 단어를 인식할 수 있는 타이프라이터 시스템 및 문자열 인식 방법이 제공된다. 매개 인터페이스 장치를 통해 입력되는 문자열로부터, 문자의 인식결과를 인식순서에 따라 배열한 문자 인식순서셋을 참조하여 다수의 문자열이 조합되고, 조합된 문자열을 완전한 단어를 이루는 문자들의 누적 셋인 부분단어들로 구성된 부분단어 인덱스 맵을 이용하여 필터링한다. 부분단어 인덱스 맵을 통과한 부분단어들에 대하여 특정한 범주의 단어 집합으로 이루어지는 문맥정보를 포함하는 사전을 이용하여 다시 필터링함으로써 정확한 단어를 인식할 수 있다. 부분단어 인덱스 맵을 이용하여 더 이상 조합하여도 사전단어가 될 수 없는 부분단어들을 미리 제거함으로써 인식의 효율을 높인다. 제스처 인식, 매개 인터페이스 장치, 단어 보정, 부분 단어
Abstract:
PURPOSE: A personal dress recommending device and a method thereof are provided to reduce a probability to recommend awkward dress by recommending dress for today based on past dress information of a user. CONSTITUTION: A human sensor(130) senses humans. A camera unit(120) photographs a user. When the human sensor senses a human, a control unit(200) recognizes the user based on data photographed by controlling the camera unit and searches for a database about the user. A coordination recommending unit(212) provides dress recommendation information for today based on preference information and searched dress information. [Reference numerals] (120) Camera; (130) Human sensor; (140) Display device; (200) Control unit; (202) Input unit; (204) User recognizing unit; (206) Top and bottom extracting and recognizing unit; (208) Existing dress data output unit; (210) User-specific dress and styling DB; (212) Styling recommendation unit; (214) Transceiving unit
Abstract:
동작 인식 장치가 제공된다. 동작 인식 장치는, 광원과 관성 센서를 포함하는 입력 장치 및 관성 센서의 센싱 신호로부터 판단된 사용자 동작 구간 동안 광원의 위치 변화를 검출하여 사용자의 동작 궤적을 추출하는 동작 인식부를 포함한다. 관성 센서, 광원, 동작 인식
Abstract:
PURPOSE: An apparatus for measuring water quality and an apparatus for sensing are provided to continuously manage water quality information. CONSTITUTION: An apparatus for measuring water quality comprises a fixed frame, a magnetic body(102), a first communication device(104), a second communication device(106), a sensing device(200a,200b), a sensor(300a,300b), a sensor support(302a,302b), and a sensor protection case(400a,400b). The sensing frame is fixed on an underwater moving body and comprises a sensing device. The magnetic body comprises a permanent magnet or electromagnet.
Abstract:
PURPOSE: A multiple camera based gesture recognition apparatus and a method thereof are provided to extract inputted points from gestures which are inputted to each camera and to obtain an integrated gesture by using displacement of points. CONSTITUTION: A locus point extracting unit(110) extracts locus points which are obtained at the same time zone from gestures images. A gesture locus generating unit(120) generates a gesture locus in consideration of displacement data. A gesture recognizing unit(130) recognizes the gesture of the same object based on the gesture locus.
Abstract:
PURPOSE: An encoding apparatus and a method thereof are provided to perform a chain code on each layer and to distinguish a character or a gesture through an encoded direction component value. CONSTITUTION: A depth chain code encoding unit(120) calculates distance between a center and each point. The depth chain code encoding unit calculates an average value. The depth chain code encoding unit sets up depth of each pointer. The depth chain code encoding unit calculates a chain code by set depth. A recognition unit(130) recognizes a character and a gestures based on encoded chain code.
Abstract:
PURPOSE: A device and method for measuring a pulse wave and sensing a fall are provided to improve reliability by mutually compensating the pulse wave and the fall. CONSTITUTION: A sensor unit(101) senses acceleration and a pulse wave. A pulse wave/fall determining module(102) determines an emergency situation according to the pulse wave or fall by comprehensively inspecting a pulse signal and an acceleration signal sensed by the sensor unit. A communication module(103) transmits the determination result. The pulse wave/fall determining module frames the acceleration signal and the pulse wave and determines the acceleration signal and the pulse signal of a frame unit. The pulse wave and acceleration determining module classify the fall or general action of the user by inspecting the acceleration signal for one frame.