• 한국정보통신학회논문지
• /
• 제23권6호
• /
• pp.682-689
• /
• 2019

부분 기반 영상 표현(part-based image representation)에서는 영상의 부분적인 모습을 기저 벡터로 표현하고 기저 벡터의 선형 조합으로 영상을 분해하며, 이 때 기저 벡터의 계수가 곧 물체의 부분적인 특징을 의미하게 된다. 본 논문에는 부분 기반 영상 표현 기법인 비음수 행렬 분해(non-negative matrix factorization, NMF)를 이용하여 얼굴 영상을 표현하고 신경망 기법을 적용하여 가려진 얼굴을 인식하는 얼굴 인식을 제안한다. 표준 비음수 행렬 분해, 투영 경사 비음수 행렬 분해, 직교 비음수 행렬 분해를 이용하여 얼굴 영상을 표현하였고, 각 기법의 성능을 비교하였다. 인식기로는 학습벡터양자화 신경망을 사용하였으며, 인식기에서의 거리 척도로는 유클리디언 거리를 사용하였다. 실험 결과, 전통적인 얼굴 인식 방법에 비하여 제안한 기법이 가려진 얼굴 인식에 보다 강인함을 보인다.

• 복식
• /
• 제52권1호
• /
• pp.103-115
• /
• 2002

The purpose of this study is understanding modern woman's various aesthetic values and aesthetic sense through observing expression aspects of gender images in the 1990s military fashion and analyzing their aesthetic characteristics and formative factors. Gender images in military fashion have expressed the masculine image of authoritative image and offensive image and offensive image, and the feminine image of conservative image and ostentatious image, sensual image. The authoritative image showed authority and dignity of military uniform by using the classic military uniform's image. This spoke for desire of women to rise their position. Heroism and androcentrism affected as its formation factor. The offensive image destroyed original dignified image of military uniform by that resistance to authoritative image and existing gender identity appeared as way-out form and deconstructive expression. Anti-establishment spirit, resistance to gender identity, and deconstructionism affected as its formation factor. The conservative image expressed military fashion only with slim and soft silhouette, curved line, color, and simple details by magnifying feminity. Fallen man's authority affected as its formation factor. The ostentatious image expressed military fashion with magnifying accessories such as gold button and belt by women who wanted to display ostentatiously their social position and charm. The aspiration for class of elite affected as its formation factor. The sensual image intended to show erotic voluptuous beauty of woman's body by indirect and direct body exposure. Narcissism, desire to show, and sexual amusement affected as its formation factor.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.777-780
• /
• 1993

Three optical fuzzy calculating modules, MAX/MIN, NOT/THROUGH, and SUP/THROUGH operating modules, are proposed. The MAX/MIN operating on inputted 2 membership functions. The NOT/THROUGH operating module calculates the complement of the membership function. The SUP/THROUGH operating module outputs an image representing the supremum (least upper bound) of the membership function. The THROUGH operation passes the image of the inputted membership function from the entrance to the exit. This paper demonstrates that these modules can output the image into which the modules transform inputted images on the basis of operation on fuzzy logic.

• 대한전자공학회논문지SP
• /
• 제46권4호
• /
• pp.34-41
• /
• 2009

본 논문에서는 IBCA(Intermediate Boundary Cellular Automata)에 기반을 둔 여원 MLCA(Maximum Length Cellular Automata)와 2D CAT(Cellular Automata Transform)를 단계적으로 이용하여 영상을 암호화하는 방법을 제안한다. 암호화 방법은 먼저, 여원 MLCA를 이용하여 원 영상의 크기만큼 PN(pseudo noise) 수열을 생성한다. 그리고, 원 영상과 생성된 수열을 XOR 연산하여 여원 MLCA 영상으로 변환한다. 그 후, 게이트웨이 값을 설정하여 2D CAT 기저함수를 생성한다. 생성된 기저 함수를 변환된 여원 MLCA 영상에 곱하여 암호화를 한다. 마지막으로 PSNR(Peak Signal to Noise Ratio) 및 안정성 분석을 통하여 제안한 방법이 높은 암호화 수준의 성질을 가졌음을 검증한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.32-34
• /
• 2007

The X-ray projection system has long been used for steel-tube inspection and weld monitoring. The thickness of tubes and welded areas is based on the evaluation of radiographic shadow projections. The traditional tangential measurement estimates the distance of border lines of the projected wall shadows of a tube onto a radiographic image detector. The detected image in which although there is a variety of noise may be sectioned into several partitions according to its specific blocks. Imaging noise originates from most of elements of the system, such as shielding CCD camera, imaging screen, X-ray source, inspected object, electronic circuits and etc. The tangential projection incorrectness and noise influence on imaging quality. In this paper we first sectionalize the X-ray image on the basis of vertical contrast difference. And next functional and statistic analysis are carried on at each region. Geometrical distance and unsharpness of the edge caused by visual evaluation uncertainties are also discussed.

• 디지털산업정보학회논문지
• /
• 제5권4호
• /
• pp.61-67
• /
• 2009

PACS and Medical Image System use only high level metadata in retrieving desired image nowadays. In order to retrieve Medical Image Data more efficiently, it would be needed to retrieve similarity by utilizing low level metadata as well as keyword retrieval by high level metadata. Thus, In this paper presents that it has realized similarity retrieval by low level metadata on the basis of MPEG-7, and keyword retrieval by high level metadata of DICOM base. It would be also available to look into medical image data in various methods and read accurate image promptly for diagnosis and treatment by retrieval with integrating two metadata.

• 대한전자공학회논문지SP
• /
• 제49권2호
• /
• pp.61-68
• /
• 2012

본 논문에서는 이미지 밝기와 명암을 명확하고 객관적으로 평가하기 위한 정규화된 수 표현자를 제안한다. 제안하는 수 표현자는 이미지를 구성하는 각각의 픽셀 데이터 값을 확률밀도함수(PDF)의 가중치로 사용하고 이를 정규화하여 객관적으로 표현되도록 정의되었다. 제안된 정규화 된 이미지 수 표현자는 감마보정 처리 시에 객관적인 감마 값 선택 기준을 제시하므로 적응형 감마보정처리가 가능하다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.221-225
• /
• 1998

This paper is to present a method for recognizing an image of a tracking object by processing the image from a camera, whose attitude is controlled in inertial space with inertial co-ordinate system. In order to recognize an object, a pseudo-random M-array is attached on the object and it is observed by the camera which is controlled on inertial coordinate basis by inertial stabilization unit. When the attitude of the camera is changed, the observed image of M-array is transformed by use of affine transformation to the image in inertial coordinate system. Taking the cross-correlation function between the affine-transformed image and the original image, we can recognize the object. As parameters of the attitude of the camera, we used the azimuth angle of camera, which is de-fected by gyroscope of an inertial sensor, and elevation an91e of camera which is calculated from the gravitational acceleration detected by servo accelerometer.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.847-850
• /
• 2000

This paper proposes an image compressing and template matching algorithm for face image using GHA (Generalized Hebbian Algorithm). GHA is a part of PCA (Principal Component Analysis), that has single-layer perceptrons and operates and self-organizing performance. We used this algorithm for feature extraction of face shape, and our simulations verify the high performance for the proposed method. The shape for face in the fact that the eigenvector of face image can be efficiently represented as a coefficient that can be acquired by a set of basis is to compress data of image. From the simulation results, the mean PSNR performance is 24.08[dB] at 0.047bpp, and reconstruction experiment shows that good reconstruction capacity for an image that not joins at leaning.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1405-1419
• /
• 2018

An image fusion method is proposed on the basis of depth model segmentation to overcome the shortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deep Boltzmann machine is used to perform the priori learning of infrared and visible target and background contour, and the depth segmentation model of the contour is constructed. The Split Bregman iterative algorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then, the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and the corresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results of MATLAB indicates that the proposed algorithm can obtain the fusion result of both target and background contours effectively, with a high contrast and noise suppression in subjective evaluation as well as great merits in objective quantitative indicators.