• 대한전자공학회논문지
• /
• 제26권8호
• /
• pp.1238-1246
• /
• 1989

In this paper, a texture synthesis technique based on the NCAR(non-causal auto-regressive) model and the pyramid structure is proposed. In order to estimate the NCAR model parameters accurately from a noisy texture, the MAP(maximum a posteriori) estimation technique is also employed. In our approach, since the input texture is decomposed into the Laplacian oyramid planes first and then the NCAR model is applied to each plane, we are able to obtain a good synthesized texture even if the texture exhibits some non-random local structure or non-homogenity. The usrfulness of the proposed method is demonstrated with seveal real textures in the Brodatz album. Finally, the 2-dimensional MAP estimation technique can be used to the image restoration for noisy images as well as a texture image synthesis.

• 한국지능시스템학회논문지
• /
• 제11권8호
• /
• pp.736-741
• /
• 2001

변형된 영상을 다시금 최적영상을 복원하는 것은 여러 영상변환의 복합적인 변환, 그 것의 역변환과 많은 다중 해의 계산을 요구하게 된다. 본 연구에서는 가공기의 운전 전이나 운전 중에 가공기의 외란-진동, 이동, 기계적 특성-에 능동적으로 대치하고 동시에 복잡한 수학적인 수식전개를 피하고, 인공지능인 기법인 퍼지논리(Fuzzy Logic)를 적용하여 전문가적인 경험지식을 바탕으로 보정이 가능함을 보였다.

• 대한전자공학회논문지
• /
• 제24권5호
• /
• pp.863-867
• /
• 1987

When digital image signals are transmitted or stored, they may be usually degraded by impulsive noise such as BSC noise. Though median filtering is a very effective method to reduce the impulsive noise, it brings non-negligible distortion after filtering. Several algorithms have been proposed to reduce such a distortion, but their reconstructed image quality are inadequate in some cases and they have a difficulty in real-time processing. In this paper, an effective filtering algorithm which can not only reduce the noise effectively but also preserve the edges well and lessen the distortion greatly, is presented. The proposed algorithm is an adaptive algorithm of median filter using local statistics, based on the characteristics of human eyes. The adaptive algorithm results shwo performance improvement of up to 3-4 dB over the nonadaptive one.

• International Journal of Advanced Culture Technology
• /
• 제7권1호
• /
• pp.64-69
• /
• 2019

With the advent of the fourth industry, the need for office automation with automatic character recognition capabilities is increasing day by day. Therefore, in this paper, we study a character recognition algorithm that effectively recognizes a new experimental data character by using learning data characters. The proposed algorithm computes the degree of similarity that the structural regions of learning data characters match the corresponding regions of the experimental data character. It has been confirmed that satisfactory results can be obtained by selecting the learning data character with the highest degree of similarity in the matching process as the final recognition result for a given experimental data character.

• 대한전자공학회논문지
• /
• 제23권4호
• /
• pp.529-534
• /
• 1986

A holographic iverse filter has been used for optical image deblurring by modeling the PSF(point spread function)of blurred system. This paper presents the optical image restoration of an accidentally blurred photograph by using a simgle inverse filter which is obtained from a blurrec PSF by analyzing the Fourier spectrum of the supposely defocused photograph itself. The filter, a positive transparency having gamma of 2, has amplitude and phase informations simulatneously.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.10-13
• /
• 2021

본 논문에서는 과다 노출된 영상을 영상 간 변환(Image-to-Image Translation)을 위해 설계된 적대적 생성 신경망(Generative Adversarial Network)을 활용하여 복원하는 연구를 수행한다. 과다 노출 복원을 위한 기존의 연구에서 과다 노출 영역 판별, 밝기 회복, 색상 보정 과정을 거치는데, 영상 내 과다 노출 영역을 판별하는 과정에서 임의로 결정하는 파라미터에 의해 복원된 영상 결과가 달라지는 한계점을 극복하기 위해 종단간(End-to-End) 신경망을 학습시켜 과다 노출 영역을 별도의 파라미터 선택과 분할된 과정 없이 한 번에 복원하는 방법을 제안한다. 영상 간 변환 신경망 학습에 필요한 과다 노출 여부로 도메인이 분할된 데이터셋은 게임 소프트웨어를 활용하여 만들어 사용하였다. 본 연구에서는 신경망이 생성한 영상이 실제로 과다 노출 영역을 탐지하여 복원하는 것을 확인하였다. 그리고 과다 노출 영역을 탐지하여 복원하는 과정을 학습 단계별로 확인함으로써 신경망이 실제로 과다 노출 복원 과정을 학습함을 보였다.

• 대한의용생체공학회:의공학회지
• /
• 제3권1호
• /
• pp.35-42
• /
• 1982

The objective of this phantom study is to develop a digital method for improving the lateral resolution of B-scan ultrasonographic images irs medical application of ultrasound. By utilizing a discrete state-space modeling approach and Kalman-Buch method for analysis of the transducer's beam profile and the measurement and sampling noise, a stable recursive restoration of the object image was obtained for improved lateral resolution. The point spread function (PSF) was measured for the reflective signals after scanning the small pins located along the depth of interest. One major advantage of the present recursive scheme over the transform method is in its applicability for the space-variant imaging, such as in the case of the rotational movement of transducer.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2013년도 제48차 하계학술발표논문집 21권2호
• /
• pp.307-310
• /
• 2013

아무르불가사리에 기인한 환경적, 경제적 피해는 해마다 증가되고 있습니다. 우리나라 남해와 동해 바다에 널려 있는 불가사리들이 최근 서해안에서도 급속히 늘어나고 있습니다. 특히 러시아 해역에 서식하는 아무르 불가사리의 개체수가 급증해 어장을 황폐화 시키고 있습니다. 이로 인하여 엄청난 번식력과 포식력을 지닌 아무르불가사리가 살아있는 조개류를 먹어치우고 있어서 어민들의 피해가 막심합니다. 이 논문은 변형되어진 아무르불가사리의 구조적 특징과 방사대칭 특성을 이용하여 불가사리 영상을 복원하는 복원기법으로 불가사리의 인식률을 높게 하여 불가사리 퇴치에 많은 도움이 될 것으로 기대합니다.

• Journal of information and communication convergence engineering
• /
• 제8권5호
• /
• pp.581-585
• /
• 2010

A grid was sandwiched between two cascaded imaging plates. Using a fan-beam X-ray tube and a single exposure scheme, the two imaging plates, respectively, recorded grid-less and grid type information of the object. Referring to the mathematical model of the Grid-less and grid technique, it was explained that the collected components whereas that of imaging plates with grid was of high together with large scattered components whereas that of imaging plate with grid was of low and suppressed scattered components. Based on this assumption and using a Gaussian convolution kernel representing the effect of scattering, the related data of the imaging plates were simulated by computer. These observed data were then employed in the developed post-processing estimation and restoration (kalman-filter) algorithms and accordingly, the quality of the resultant image was effectively improved.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.367-370
• /
• 2007

Both impluse noise and AWGN (additive white Gaussian noise) are easily corrupted into images, during signal transmission and acquisition. Thus, an algorithm for removing both noises is represented in this paper. An impulse noise detection step can effectively separate impulse noise with AWGN, then in the noise filtering step, by using several parameters, not only impulse noise but also AWGN can be reduced. The value of those parameters are automatically changeable when the standard deviation of AWGN, the impulse noise density, and the spatial distances between pixels are different. Results of computer simulations show that the proposed approach performs better than other conventional filters.