• 한국통신학회논문지
• /
• 제32권3C호
• /
• pp.241-248
• /
• 2007

예측(predictive) 이미지 코딩에서는 최소 자승법을 기반으로 하는 적응적인 예측기가 에지 주변에 있는 픽셀(pixel)의 예측 결과를 향상시키는데 효과적인 방법으로 알려져있다. 본 논문에서는 가중치 윤곽선 검출기 (weighted edge detector)를 이용한 하이브리드 보간 알고리듬(hybrid interpolation algorithm)을 제안한다 전체적인 계산의 복잡도를 감소시키기 위해서 2차원 선형 보긴(bilinear interpolation)과 에지 방향성을 이용한 보간(edge directed interpolation) 알고리듬을 선택적으로 적용시키는 하이브리드 접근방법을 이용한다. 이런 접근 방법을 2차원 선형 보간 알고리듬과 에지 방향성을 이용한 보간 알고리듬을 적용했을 경우와 비교하기 위해서 PSNR과 SSIM 측정값을 이용하여 객관적이고 주관적인 영상의 화질 비교는 제안한 알고리듬이 비슷한 성능을 나타냄을 보여준다. 또한 제안하는 가중치 윤곽선 검출기를 이용한 하이브리드 보간 알고리듬은 정규화된 CPU 수행 시간을 에지 방향성을 이용한 보간 알고리듬과 비교하면 최대 20배의 복잡도 감소 효과를 얻을 수 있다.

• 지질공학
• /
• 제33권3호
• /
• pp.439-459
• /
• 2023

Numerical analysis has been adopted in nearly all modern scientific and engineering fields due to the rapid and ongoing evolution of computational technology, with the number of grid or mesh points in a given data field also increasing. Some values must be extracted from large data fields to evaluate and supplement numerical analysis results and observational data, thereby highlighting the need for a fast and effective interpolation approach. The quadrilateral irregular network (QIN) proposed in this study is a fast and reliable interpolation method that is capable of sufficiently satisfying these demands. A comparative sensitivity analysis is first performed using known test functions to assess the accuracy and computational requirements of QIN relative to conventional interpolation methods. These same interpolation methods are then employed to produce simple numerical model results for a real-world comparison. Unlike conventional interpolation methods, QIN can obtain reliable results with a guaranteed degree of accuracy since there is no need to determine the optimal parameter values. Furthermore, QIN is a computationally efficient method compared with conventional interpolation methods that require the entire data space to be evaluated during interpolation, even if only a subset of the data space requires interpolation.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제2권4호
• /
• pp.195-199
• /
• 2010

This paper addresses the problem of B-spline surface interpolation of scattered points for a hull form design, which are not arbitrarily scattered, but can be arranged in a series of contours permitting variable number of points in the contours. A new approach that allows different parameter value for each point on the same contour has been adopted. The usefulness and quality of the interpolation has been demonstrated with some experimental results.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2785-2788
• /
• 2001

In this paper, we present a new interpolation scheme for image enhancement using fuzzy inference. In general, interpolation techniques are based on linear operators which are essentially lowpass filters, hence, they tend to blur fine details in the original image. In our approach, the operator itself balances the strength of its sharpening and noise suppressing components according to the properties of the input image data.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.105-108
• /
• 1996

In this paper, we present an interpolation schema for image resolution enhancement using fuzzy logic. Proposed algorithm can recover both low and high frequency information in image data. In general, interpolation techniques are based on linear operators which are essentially details in the original image. In our fuzzy approach, the operator itself balances the strength of its sharpening and noise suppressing components according to the properties of the input image data. The proposed interpolation algorithm is performed in three step. First logic reasoning is applied to coarsely interpret the high frequency information. These results are combined to obtain the optical output. Using our approach, resolution of the original image can be applied to various kind of image processing topics such as image enhancement, subpixel edge detection, and filtering.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.235-239
• /
• 1992

The paper describes an approach for estimating unsteady flow rate through oil hydraulic pipelines and components in real time. Recently we have proposed following three unsteady flow rate measurement approaches; RIFM, QIFM and TPFM, in which hydraulic pipeline dynamics are made use of. In this paper, we firstly propose new approaches, i.e, an interpolation and an extrapolation methods in combination with RIFM and TPFM. In the interpolation method, unsteady flow rate at the arbitrary internal location along the pipeline between two points for measuring the two point pressure can be estimated. In this paper, the accuracy and dynamic response of interpolation method are mainly experimentally investigated in detail.

• 대한음성학회지:말소리
• /
• 제56호
• /
• pp.207-223
• /
• 2005

The goal of language model adaptation is to improve the background language model with a relatively small adaptation corpus. This study presents a language model adaptation technique where additional text data for the adaptation do not exist. We propose the information retrieval (IR) technique with N-gram language modeling to collect the adaptation corpus from baseline text data. We also propose to use a dynamic language model interpolation coefficient to combine the background language model and the adapted language model. The interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech data reserved for held-out validation data. This allows the final adapted model to improve the performance of the background model consistently The proposed approach reduces the word error rate by $13.6\%$ relative to baseline 4-gram for two-hour broadcast news speech recognition.

• Journal of Mechanical Science and Technology
• /
• 제15권2호
• /
• pp.192-198
• /
• 2001

We consider an interpolation problem with nonuniform rational B-spline curves given ordered data points. The existing approaches assume that weight for each point is available. But, it is not the case in practical applications. Schneider suggested a method which interpolates data points by automatically determining the weight of each control point. However, a drawback of Schneiders approach is that there is no guarantee of avoiding undesired poles; avoiding negative weights. Based on a quadratic programming technique, we use the weights of the control points for interpolating additional data. The weights are restricted to appropriate intervals; this guarantees the regularity of the interpolating curve. In a addition, a knot placement is proposed for pleasing interpolation. In comparison with integral B-spline interpolation, the proposed scheme leads to B-spline curves with fewer control points.

• 응용통계연구
• /
• 제5권2호
• /
• pp.255-268
• /
• 1992

본 논문에서는 이상점이 포함된 시계열 자료의 모수추정법으로 반복보간추정법을 제안하였 다. 제안된 방법은 이상점이 더 이상 탐지되지 않을 때까지 모수추정의 단계와 이상점의 탐 지 단계를 반복하는 접근 방법이다. 이상점의 탐지를 위해서는 비정상적인 자료를 보가추정 법으로 대치하는 보간 검진기법을 적용하였다. 또한 추정과정에서 비정상적인 자료의 비중 을 적게하는 대신에 비정상적인 자료를 시계열모형의 구조를 이용한 1-시점후의 예측값으 로 대치하는 수정된 GM-추정법을 제안하였다. 모의실험에 의해 제안된 추정법들과 기존의 로버스트추정법들의 성질을 비교하였다. 모의실험의 결과 반복보간추정법이 다른 추정법보 다 우월한 성질을 가짐을 알 수 있었으며, 특히 AO가 하나만 있는 경우와 모수의 절대값이 큰 경우에 가장 우수함을 확인 할 수 있었다.

• 한국통신학회논문지
• /
• 제35권12C호
• /
• pp.1010-1019
• /
• 2010

This article presents a PDE-based interpolation algorithm to effectively reproduce high resolution imagery. Conventional PDE-based interpolation methods can produce sharp edges without checkerboard effects; however, they are not interpolators but approximators and tend to weaken fine structures. In order to overcome the drawback, a texture enhancement method is suggested as a post-process of PDE-based interpolation methods. The new method rectifies the image by simply incorporating the bilinear interpolation of the weakened texture components and therefore makes the resulting algorithm an interpolator. It has been numerically verified that the new algorithm, called the PDE-based image interpolator (PII), restores sharp edges and enhances texture components satisfactorily. PII outperforms the PDE-based skeleton-texture decomposition (STD) approach. Various numerical examples are shown to verify the claim.