Abstract:
본 발명은 거울의 패닝과 틸팅을 이용한 원거리 홍채 영상 획득 시스템에 관한 것으로, 가시광선 영상 촬영용 광각카메라와 적외선 영상 촬영용 협각카메라 및 상기 협각카메라용 근적외선 조명장치의 광축을 미러 부재(예컨대, Hot mirror)를 통해 일치시키고, 일치된 광축을 1대의 거울 PT(Pan-Tilt) 장치로 제어하여 원거리에 있는 사용자의 홍채 영상을 획득한다. 본 발명에 의하면 1대의 거울 PT 장치로 협각카메라의 광축이 항상 광각카메라의 광축과 일치한 상태에서 근적외선 조명이 협각카메라의 화각 범위만을 비추도록 제어하므로 별도로 조명 제어를 하지 않더라도 양질의 밝은 홍채 영상을 획득할 수 있고, 협각카메라의 화각 범위만을 비출 규모의 조명이 필요하게 되므로 조명 장치를 종래에 비해 상대적으로 저렴한 가격으로 더 작은 규모로 구현하면서도 조명에 대한 눈 안전성을 향상시킬 수 있으며, 이와 더불어 기존의 메가픽셀급 협각카메라보다 저렴하면서 적은 조명으로도 홍채 영상을 획득할 수 있는 저조도 카메라(예컨대, VGA급 저조도 카메라) 혹은 근적외선 카메라 등을 협각카메라로 사용할 수 있다.
Abstract:
PURPOSE: An image normalization method using fuzzy based retinex and a device thereof are provided to perform modeling by using only the average and the standard deviation of an image, thereby reducing modeling time and the complexity. CONSTITUTION: An image input unit (110) receives a normalization object input image. An image information calculation unit (120) normalizes the input image to the size of a unit image and calculates the uniformity of the input image based on normalized images. A filtering adjustment value calculation unit (130) calculates a filtering adjustment value setting a filtering degree for the input image by using the uniformity of the input image. A filtering unit (140) filters the input image with the filtering adjustment value and generates an output image. The uniformity of the input image is calculated by using the brightness of the input image and includes the average and the standard deviation of the input image. [Reference numerals] (110) Image input unit; (120) Image information calculation unit; (130) Filtering adjustment value calculation unit; (140) Filtering unit
Abstract:
PURPOSE: A forged fingerprint detector and a method thereof are provided to enhance the reliability for authentication and identification by adding the illumination of different wavelength. CONSTITUTION: A lighting unit(140) successively generates the first light and the second light which wavelength is different, and illuminates in a fingerprint part. A fingerprint image sensing unit(150) acquires an fingerprint image corresponding to the first light and the second light by using the first light and the second light which is reflected in the fingerprint part. A forged fingerprint discriminating unit(160) discriminates fingerprint forgery by using difference between the brightness of the fingerprint image corresponding to the first light and the second light and the fingerprint brightness of the first light and the second light which saved in a storage, or difference between a brightness variation degree obtained through difference of the brightness of the fingerprint image corresponding to the first light and the second light and the brightness variation degree of the storage.
Abstract:
PURPOSE: A system and a method for obtaining non pressure 3D face data are provided to project straight light pattern or grid lighting pattern of near infrared ray band to a face of a user, thereby conveniently obtains 3D face data. CONSTITUTION: A line laser(20) projects linear lighting pattern using near IR from left to right or right to left in a rotating angel range based on face front direction. A main processor(30) finds intersection point between epipolar line of 2D left/right face image of two cameras(10,10') and straight light pattern as a corresponding point. The main processor obtains 3D face data by triangulation scheme.
Abstract:
PURPOSE: A long distance iris image obtaining system using panning and tilting of a mirror is provided to obtain a good bright iris image without controlling lighting by providing the lighting to a view angle range of a narrow angle camera. CONSTITUTION: A narrow angle camera(20) captures an iris image of a user. Near infrared ray lighting devices provide a capture area of the narrow angle camera. A mirror member matches an optical axis of a wide angle camera(10) and the narrow angle camera. A mirror PT(Pan/Tilt) device(40) changes a path of visible light or the infrared ray, which passes the mirror member or is reflected from the mirror member, by panning or tilting a total reflection mirror. A main processor(50) pans or tilts the total reflection mirror to place an eye to the center of the captured image of the wide angle camera. The main processor obtains the iris image through automatic-focus adjustment by varying a zoom level of a zoom lens of the narrow angle camera.
Abstract:
A non-intrusive iris image acquisition system and a method thereof are provided to obtain the iris image in a short time by reducing the motion range of the focus lens minimally. A lighting device(20) irradiates the near infrared ray to the front of a PTZ camera(10). An optics output device(30) irradiates the optical signal for detecting the horizontal position of the user. A wide angle camera(40) filters the optical signal which is reflected by using the specific optical signal frequency filter. The wide angle camera takes a picture of the horizontal position detection image of user. A main processor(50) obtains the horizontal constellation(X,Y) of user on the wide angle camera from the horizontal position detection image. The main processor automatically controls the focus of the focus lens of the PTZ camera.
Abstract:
An apparatus for obtaining the contactless series fingerprint image is provided to produce the expanded fingerprint image including the front side and right and left side domain of fingerprint are produce the three-dimensional model of fingerprint. The finger of user is inserted into the finger support stand(10) to support in order to prevent the move of the finger tremor of user. The one camera(20) takes a picture of the series fingerprint image according to the rotation quantity of the finger. The lighting device(30) is installed between the finger and the camera. The lighting device irradiates the light in the finger print region of user. The diffuser(40) makes the irradiated light distributed at the finger. The finger rotation sensing method(60) measures the rotation quantity in the rotation of the inserted finger. The controller(70) takes a picture of the fingerprint image of the inserted finger by controlling the camera.
Abstract:
A virtual face generating method is provided to extract biological feature information for the region of a face from the facial information of a user obtained from an image acquisition system and to create facial feature image based on the biological feature information. A virtual face generating method comprises extracting the biological feature information for each part of a face from a normalized facial image(S10-S30); selecting a specific facial part which is to be modified(S40); converting the specific facial part into the biological feature information of a part stored a facial feature information database(S42); and creating a virtual modified face(S44).
Abstract:
본 발명은 입력 지문영상의 이동 및 회전에 무관한 가변 지문템플릿 생성방법 및 이를 이용한 검증시스템에 관한 것으로, 입력 지문영상으로부터 추출한 특징점 주변의 영상정보로부터 지문영상의 이동 및 회전에도 변화가 적은 불변값을 추출하고, 추출된 불변값을 변경함수의 입력으로 해서 특징점의 변경량을 계산하여 특징점이 갖는 방향을 기준으로 계산된 변경량만큼 특징점을 변경하여 변경된 지문템플릿을 생성하고 변경된 지문템플릿을 이용하여 개인 인증을 할 수 있다. 본 발명은 원 지문의 특징점 정보를 변경하여 변경된 특징점 정보로 개인을 인증하므로 생성된 가변 지문템플릿과 변환 방법을 알더라도 원 지문템플릿의 복원이 불가능하고, 지문정보의 도난시 변경함수를 교체하여 도난된 지문정보를 취소하고 새로운 변경된 특징점을 생성할 수 있으므로 개인의 지문정보 도난시 발생할 수 있는 프라이버시 침해 및 개인지문정보 보호의 문제를 해결할 수 있다. 특히, 본 발명은 입력 지문영상들 간의 정렬이 불필요하고, 기존의 지문템플릿과 동일한 형식을 갖는 가변 지문템플릿을 사용하므로 정합 방법의 변경 없이 기존 정합 방법을 사용하는 지문시스템에 적용하더라도 개인인증이 가능하다. 지문인식, 지문영상, 지문템플릿