Abstract:
뇌 고랑의 구조적 특성을 반영한 뇌 고랑 깊이 측정 방법 및 시스템이 개시된다. 뇌 고랑 깊이 측정 방법은 자기공명영상으로부터 대뇌피질 모델을 추출하는 단계, 상기 자기공명영상과 상기 추출한 대뇌피질 모델을 이용하여 뇌 고랑의 내부영역을 정의하는 단계 및 상기 정의한 뇌 고랑의 내부영역에서 뇌의 겉면과 상기 추출한 대뇌피질 모델의 꼭지점 간의 최소경로를 계산하는 단계를 포함할 수 있다.
Abstract:
PURPOSE: A method and system for classifying a functional change pattern of a default mode network according to the progression of Alzheimer's disease are provided to early diagnose a patient by accurately classifying a change pattern of a functional connection of the default mode network. CONSTITUTION: An area with a difference between default mode networks of an Alzheimer's patient, a patient with mild cognitive impairment, and a healthy person over a preset value is extracted (130). Functional connection information about the default mode network is extracted from the extracted area (140). A relation between the extracted functional connection information and dementia classification information showing the progression of dementia is analyzed. A functional change pattern of the default mode network is classified according to the progression of the dementia (150). [Reference numerals] (110) Obtain MRIs of a patient with Alzheimer's, a patient with mild cognitive impairment, and a healthy person; (120) Extract the three groups' default mode networks by performing an independent element analysis process based on the obtained MRIs; (130) Extract areas with larger differences than a previously-set value by performing a covariance analysis process based on the default mode networks of the three groups; (140) Extract functional connection information from the extracted areas; (150) Distinguish the patterns of functional changes in the default mode networks by analyzing the relationship between the extracted functional connection information and Alzheimer's identification information; (AA) Start; (BB) End
Abstract:
영상 디블러링 기법을 이용한 구조물 점검 시스템 및 그 방법을 개시한다. 구조물 점검 시스템은 구조물과 관련된 입력 영상에 대하여 흔들림 정도를 추정하는 흔들림 추정부; 상기 흔들림 정도에 따른 디블러링(deblurring)을 통해 상기 입력 영상을 복원하는 영상 복원부; 및, 상기 복원된 입력 영상을 이용하여 상기 구조물의 균열을 검출하는 균열 검출부를 포함할 수 있다. 교량 점검(bridge inspection), 구조물 점검, 균열, 모션 블러(motion blur), PSF(point spread function), 디블러링(deblurring)
Abstract:
PURPOSE: A structure inspection system using an image deblurring technique and a method thereof are provided to accurately detect cracks on a structure through images of high definition by revising the images through software. CONSTITUTION: A structure inspection system(130) using an image deblurring technique comprises a shake estimating unit(201), an image recovery part(202), and a crack detection part(203). The shake estimating unit estimates the shaking degree on input images related to a structure. The image recovery part restores the input images through deblurring according to shaking degree. The crack detection part detects the cracks of the structure using restored input images. The shake estimating unit comprises an image transformer, a zero approximate point extracting unit, and a PSF(point spread function). The image transformer changes the input image into a frequency domain.
Abstract:
An apparatus and Method for extracting Epiphysis image is provided to calculate the accumulated value with the determining unit based on the central axis and to accurately extract the epiphyseal plate location of the finger used for the bone age evaluation regardless of the form of the finger. The finger image is extracted from the finger image abstraction section(110) in the input image. The finger image abstraction section(120) extracts the finger image by using the extracted finger image. The central axis output unit(130) produces the central axis of the finger by using the extracted finger image. The determining unit(140) produces the location of the epiphyseal plate by using the finger image and central axis. The central axis output unit produces the center of the big point of the amount of change of the horizontal brightness value of the finger image by median. The central axis is produced by using the calculated median. The central output unit produces the background, and the boundary point between the bones by using the amount of change of the horizontal brightness value of the finger image.
Abstract:
Provided is a method for preparing trans-4-methylcyclohexyl amine by catalytic hydrogenation, wherein reaction rate and selectivity are increased and a noble metal catalyst is recyclable. The method for preparing trans-4-methylcyclohexyl amine by catalytic hydrogenation consists of hydrogenating p-toluidine in the presence of alkali hydroxide together with a noble metal catalyst and solvent. The alkali hydroxide is selected from lithium hydroxide, sodium hydroxide, or potassium hydroxide, and is added in an amount of 0.4-7.2 parts by weight based on 100 parts by weight of p-toluidine.