• Journal of Integrative Natural Science
• /
• v.5 no.2
• /
• pp.120-126
• /
• 2012

This paper describes the algorithm that lowers the dimension, maintains the gesture recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.1
• /
• pp.44-49
• /
• 2003

This paper describes a method of estimating miniature train location by color vision for development of an intelligent railway system model. In the teal world, to control trains automatically, GPS(Global Positioning System) is indispensable to determine the location of trains. A color vision system was used for estimating the location of trains in an indoor experiment. Two different rectangular color bars were attached to the top of each train as a means of identifying them. Several trains were detected where they were located on the track by color feature, geometric features and moment invariant, and tracked simultaneously. In the experiment the identity, location and direction of each train were estimated and transferred to the control computer using serial communication. Processing speed of up to 8 frames/sec could be achieved, which was enough speed for the real-time train control.

• Korean Journal of Computational Design and Engineering
• /
• v.10 no.5
• /
• pp.303-313
• /
• 2005

This paper proposes a generalized NURBS model, called Volumetric NURBS or VNURBS for representing volumetric objects with multiple attributes embedded in multidimensional space. This model provides a mathematical framework for modeling complex structure of heterogeneous objects and analyzing inside of objects to discover features that are directly inaccessible, for deeper understanding of complex field configurations. The defining procedure of VNURBS, which explains two directional extensions of NURBS, shows VNURBS is a generalized volume function not depending on the domain and its range dimensionality. And the recursive a1gorithm for VNURBS derivatives is described as a computational basis for efficient and robust volume modeling. In addition, the specialized versions of VNURBS demonstrate that VNURBS is applicable to various applications such as geometric modeling, volume rendering, and physical field modeling.

• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.4
• /
• pp.49-70
• /
• 1993

The purpose of this study was to develop a semigenerative process planning system for the turning processes required for rotational parts. The system developed in this study showed three major roles for a given part : selection of appropriate turning processes, scheduling of selected processes, and selection of appropriate tools to be used for selected processes. Four information files and six modules were developed to produce a process plan. When geometric features, dimension, tolerance, material types, and surface finish data are inputted to the system, optimal processes, processing sequences, selected tools, and machining costs are to be produced as a process plan.

• Journal of applied mathematics & informatics
• /
• v.11 no.1_2
• /
• pp.1-57
• /
• 2003

Vector fields in three-space admit bundles of internal variables such as a Heisenberg algebra bundle. Information transmission along field lines of vector fields is described by a wave linked to the Schrodinger representation in the realm of time-frequency analysis. The preservation of local information causes geometric optics and a quantization scheme. A natural circle bundle models quantum information visualized by holographic methods. Features of this setting are applied to magnetic resonance imaging.

• Journal of Fisheries and Marine Sciences Education
• /
• v.28 no.6
• /
• pp.1848-1857
• /
• 2016

In order to discriminate the morphologically analogous smallscale blackfish, Girella leonina and largescale blackfish, G. punctata, various methods were used by using biometric and geometric approaches. Morphometric analysis showed considerable 19 differences of total 44 morphometric dimensions: classical dimension 1 part; truss dimension 12 parts; and head part dimension 6 parts (P < 0.05). Some differences of morphological features primarily involved in caudal part of truss dimension. Our results of this study confirmed that two species adequately can distinguish with external body shape, and we hope that the results of our study could be used to identify in Girellidae family as taxonomical parameters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.673-676
• /
• 2006

생명현상을 이해하기 위해서는 단백질의 기능 규명이 이루어져야한다. 단백질 기능 규명을 위한 서열분석 방법은 서열 상동성이 현저히 낮은 경우 단백질 기능 예측이 불가능하고, 과거의 전체적인 단백질 구조 분석을 통한 기능 예측의 문제점이 보고되고 있다. 이 논문에서는 기능상 중요한 의미를 가지고 있는 단백질의 특정하위구조의 기하학적 특징을 추출하여 이 특징과 잔기의 위치와의 관계를 규명하였다. 또한 NaiveBayes, SVM, C4.5의 분류알고리즘을 이용하여 각 알고리즘별 분류성능을 평가하였다. 기능상 중요한 의미를 가지고 있는 특정하위구조를 비교함으로써 모르는 단백질의 기능을 예측할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.377-380
• /
• 2003

본 논문은 2차원 이미지상에서 사용자 의도에 따른 에지를 효과적으로 찾기 위한 다양한 알고리즘 (인공 가위 기법, 라이브 와이어 기법, 라이브 레인 기법, 인헨스드레인 기법)들을 3 차윈 삼각형 매쉬상에서 기하학적 특정을 추출하기 위해 적용할 때 주요하게 고려해야 할 사항을 논의하고 이들 사항을 고려한 수정된 알고리즘들을 제안한다. 제안된 이들 알고리즘들을 사용하여 주어진 3차원 삼각형 메쉬상의 기하학적 특정을 사용자 의도대로 찾은 결과를 가시적으로 보여준다.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.387-390
• /
• 1993

The most important technique for an indoor robot navigation is to find out the direction and the distance from the current location to the destination through the information achieved from the sensor. For this purpose, we suggest sensor-based local homing method which compares the destination sensory data with the current location. As for the sensors, we use the CCD camera and the ultrasonic sensor, and recorded entire 360 degree panoramic data. We match the features of the image data, and the distance and the direction of the matched point will be considered as fuzzy numbers. Through a simple fuzzy arithmetic, we infer the geometric relations between the current location and the destination location.

• Journal of KIISE:Software and Applications
• /
• v.27 no.1
• /
• pp.33-40
• /
• 2000

Computer Aided Process Planning (CAPP) plays a key role by linking CAD and CAM. Given CAD data of a part, CAPP has to recognize manufacturing features of the part. Despite the long history of research on feature recognition, its research results have rarely been transferred into industry. One of the reasons lies in the separation of feature recognition and process planning. This paper proposes to integrate the two activities through AI techniques, and presents efforts for manufacturable feature recognition, setup minimization, feature dependency construction, and generation of an optimal machining sequence.