• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.115-118
• /
• 2005

A workpiece with a large surface area is likely to be uneven due to form error and waviness. These geometric disturbances can cause inaccurate micro shapes to be formed when micro features are micro-grooved into the surface and cause the resulting workpiece to fail to function as desired. Thus, real-time measurement and compensation is required to guarantee the form accuracy of micro features while machining a workpiece with a large surface area. In this study, a method is suggested for real-time measurement of geometric error for the micro grooving of a large flat surface using a laser displacement sensor. The measurements are demonstrated for the workpieces with large surface areas and the experimental results show that the waviness and form error are well detected.

• Journal of Information Science Theory and Practice
• /
• 제7권2호
• /
• pp.32-39
• /
• 2019

A convolutional neural network (CNN) has been widely used in facial expression recognition (FER) because it can automatically learn discriminative appearance features from an expression image. To make full use of its discriminating capability, this paper suggests a simple but effective method for CNN based FER. Specifically, instead of an original expression image that contains facial appearance only, the expression image with facial geometry visualization is used as input to CNN. In this way, geometric and appearance features could be simultaneously learned, making CNN more discriminative for FER. A simple CNN extension is also presented in this paper, aiming to utilize geometric expression change derived from an expression image sequence. Experimental results on two public datasets (CK+ and MMI) show that CNN using facial geometry visualization clearly outperforms the conventional CNN using facial appearance only.

• 한국정밀공학회지
• /
• 제10권4호
• /
• pp.236-247
• /
• 1993

An davanced method for the automatic generation of parametric models in computer- aided design systems is required for most of two-dimensional model which is represented as a set of geometric elements, and constraining scheme formulas. The development system uses geometric constraints and support of topology parameters from feature recognition and grouping the design entities into optimal ones from pre-designed drawings. The aim of this paper is to present guidelines for the application and development of parametric design modules for the standard parts in mechanical system, the basic constitutional part of mold base, and other 2D features.

• 한국측량학회지
• /
• 제25권3호
• /
• pp.183-190
• /
• 2007

최첨단 측량기술로 획득되어진 고해상도 위성영상과 항공레이저측량 자료들을 의미 있는 지리정보로 활용하고 상호보완적인 가치를 창출하기 위해서는 이러한 자료들을 같은 좌표계 상에 표현할 수 있도록 기하보정 하는 과정이 선행되어야 한다. 본 연구에서는 고해상도 위성영상을 항공레이저측량 자료를 활용하여 기하보정하기 위한 방법론을 제안하였다. 이를 위해 항공레이저측량 자료와 고해상도 위성영상인 IKONOS-2 위성영상으로부터 선형 기하요소를 추출하였으며 추출된 선형요소를 기하보정의 기본요소로 활용하여 고해상도 위성영상의 단사진과 항공레이저측량 자료의 기하보정을 수행하였다. 마지막으로 연구를 위하여 수집된 실제 측량자료에 개발된 방법론들을 적용하고 도출된 결과에 대한 통계평가를 수행함으로써 연구결과의 효용성을 입증하였다.

• 대한교통학회지
• /
• 제19권6호
• /
• pp.255-256
• /
• 2001

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.643-646
• /
• 2006

This paper addresses the approach to extract linear features from satellite imagery using an efficient segmentation method. The extraction of linear features from satellite images has been the main concern of many scientists. There is a need to develop a more capable and cost effective method for the Iranian map revision tasks. The conventional approaches for producing, maintaining, and updating GIS map are time consuming and costly process. Hence, this research is intended to investigate how to obtain linear features from SPOT satellite imagery. This was accomplished using a discontinuity-based segmentation technique that encompasses four stages: low level bottom-up, middle level bottom-up, edge thinning and accuracy assessment. The first step is geometric correction and noise removal using suitable operator. The second step includes choosing the appropriate edge detection method, finding its proper threshold and designing the built-up image. The next step is implementing edge thinning method using mathematical morphology technique. Lastly, the geometric accuracy assessment task for feature extraction as well as an assessment for the built-up result has been carried out. Overall, this approach has been applied successfully for linear feature extraction from SPOT image.

• 한국CDE학회논문집
• /
• 제2권3호
• /
• pp.175-185
• /
• 1997

Given the widespread use of the Finite Element Method in strength analysis, automatic mesh generation is an important component in the computer-aided design of parts and assemblies. For a given resolution of geometric accuracy, the purpose of mesh generators is to discretize the continuous model of a part within this error limit. Sticking to this condition often produces many small elements around small features in spite that these regions are usually of little interest and computer resources are thus wasted. Therefore, it is desirable to selectively suppress small features from the model before discretization. This can be achieved by low-pass filtering a CAD model. A spatial function of one dimension higher than the model of interest is represented using the Fourier basis functions and the region where the function yields a value greater than a prescribed value is considered as the extent of a shape. Subsequently, the spatial function is low-pass filtered, yielding a shape without the small features. As an undesirable effect to this operation, all sharp corners are rounded. Preservation of sharp corners is important since stress concentrations might occur there. This is why the LPF (low-pass filtered) model can not be directly used. Instead, the distances of the boundary elements of the original shape from the LPF model are calculated and those that are far from the LPF model are identified and removed. It is shown that the number of mesh elements generated on the simplified model is much less than that of the original model.

• 대한전자공학회논문지SP
• /
• 제46권6호
• /
• pp.58-67
• /
• 2009

대응점 정합은 컴퓨터 비전에서 중요한 작업 중에 하나지만 스케일, 조명, 시점이 변한 환경에서 대응점을 찾는 과정은 매우 어렵다. 대응점 정합 알고리즘인 SURF(Speeded Up Robust Features) 기법은 SIFT(Scale Invariant Feature Transform) 기법에 비해 정합 속도가 매우 빠르고 비슷한 정합 성능을 보여 널리 사용되고 있다. 하지만 SURF 기법은 흑백 영상과 지역 공간정보를 사용하기 때문에 유사한 패턴이 존재하는 영상에서 대응점의 정합 성능이 매우 떨어진다. 이런 문제점을 해결하기 위해 본 논문에서는 강인한 컬러 특징 정보와 광역적 특징 정보를 이용하는 확장 SURF 알고리즘을 제안한다. 제안하는 알고리즘은 비슷한 패턴이 존재하더라도 색상정보과 광역 공간 정보를 추가로 사용되기 때문에 대응점 매칭 성능을 크게 향상시킨다. 본 논문에서는 제안하는 방법의 우수성을 조명과 시점이 변화하고 유사한 패턴들을 갖는 영상들에 적용하여 기존의 방법들과 비교 실험함으로서 입증하였다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제7권3호
• /
• pp.9-18
• /
• 2001

삼각 메쉬의 특징점을 찾는 것은 메쉬 편집, 메쉬 몰핑, 메쉬 압축, 메쉬 신호처리 등 여러 가지 응용 분야에서 중요하게 사용된다. 본 논문에서는 삼각 메쉬의 특징점을 찾기 위한 방법으로 기하학 스네이크를 제시하였다. 기하학 스네이크는 영상 스네이크를 확장한 것으로, 사용자가 초기 위치를 정하면 에너지 함수를 최소화함으로써 가까이에 있는 특징점을 찾는다. 기하학 스네이크는 항상 메쉬 표면 위에서만 이동하여야 하므로 메쉬를 매개 변수화하여 스네이크를 이차원 상에 매핑된 메쉬상에서 이동시켰다. 스네이크를 특징점으로 이동시키기 위한 외부 에너지는 메쉬 표면의 노말 변화를 이용하여 계산하였다.

• 한국의상디자인학회지
• /
• 제5권2호
• /
• pp.103-113
• /
• 2003

This paper analyses the geometric aspect of Sonia Delaunay′s works on the basis of design elements and principles. Geometric pattern is one of the distinct features of early 20th century avant-garde works. The significance of its pattern and colour comes from the fact that it has not only influenced the contemporary fine art but also offered the basic principle of modern costume design. In 1925 she was designing clothes which could be worn today without appearing old-fashioned. She foresaw the future trends in fashion and interior decoration. One might claim she belongs to the avant-garde even today and no less astonishing a phenomenon than she was in 1925. Sonia Delaunay′s art was one of the first expressions of abstract painting and her "simultaneous contrasts" are among the earliest example of the aesthetic. In Delaunay′s geometric abstraction it is found that the technique of "simultaneous contrasts" is exploited almost without exception. Colour as well as Collage was the favourite technique Delnaunay used in creating a distinct simultaneity. Many "inobjective" paintings as she herself called unite the rigour of simple geometric forms with an inner life and poetry which emanate from the richness of the colour, the musicality of the rhythm, the vibrant breadth of the execution.