• Journal of Korea Multimedia Society
• /
• v.8 no.3
• /
• pp.336-344
• /
• 2005

In this paper, we extracted the contour of lung parenchyma on EBT images with the improved active contour model. The objects boundary in conventional active contour model can be extracted by controlling internal energy and external energy as energy minimizing form. However, there are a number of problems such as initialization and the poor convergence about concave part. Expecially, contour can not enter the concave region by discouraging characteristic about stretching and bending in internal energy. We controlled internal energy by moving local perpendicular bisector point of each control point in the contour and implemented the object boundary by minimizing energy with external energy The convergence of concave part could be efficiently implemented toward lung parenchyma region by this internal energy and both lung images for initial contour could also be detected by multi-detection method. We were sure this method could be applied detection of lung parenchyma region in medical image.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.130-134
• /
• 1992

The ability of a robot system to comply to an environment via the control of tool-environment interaction force is of vital for the successful task accomplishment in many robot application. This paper presents the implementation of external force control for two dimensional contour following task using a commercial robot system. Force accommodation is used since a constraint imposed in our work is not to modify the commercial robot system. A linear, decoupled model of two dimensional contour following system in the discrete time domain is derived first. Then the experimental verification of linear control is obtained using a PUMA 560 manipulator with standard Unimation controller, Astek FS6-120A six axis wrist force sensor attached externally to the arm and LSI-11173 microcomputer. Experimentally obtained data shows that the RMS contact force error is 0.8246 N when following the straight edge and 2.3768 N when following 40 mm radius curved contour.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.3
• /
• pp.157-164
• /
• 2008

While developing physical prototype from CAD model, rapid prototyping mainly focuses on two key points reducing time and material consumption. So, we have to change from a traditional solid model to building a hollowed prototype. In this paper, a new method is presented to hollow out solid objects with uniform wall thickness to increase RP efficiency. To achieve uniform wall thickness, it is necessary to generate internal contour by slicing the offset model of an STL model. Due to many difficulties in this method, this paper proposes a new algorithm that computes internal contours computing offset model which is generated from external contour using wall thickness. Proposed method can easily compute the internal contour by slicing the offset surface defined by the sum of circle swept volumes of external contours without actual offset and the circle wept volumes. Internal contour existences are confirmed by using the external point. Presented algorithm uses the 2D geometric algorithm allowing RP implementation more efficient. Various examples have been tested with implementation of the algorithm, and some examples are presented for illustration.

• Journal of Biomedical Engineering Research
• /
• v.26 no.6
• /
• pp.357-363
• /
• 2005

Active contour models have been extensively used to segment, match, and track objects of interest in computer vision and image processing applications, particularly to locate object boundaries. With conventional methods an object boundary can be extracted by controlling the internal energy and external energy based on energy minimization. However, this still leaves a number of problems, such as initialization and poor convergence in concave regions. In particular, a contour is unable to enter a concave region based on the stretching and bending characteristic of the internal energy. Therefore, this study proposes a method that controls the internal energy by moving the local perpendicular bisector point of each control point on the contour, and determines the object boundary by minimizing the energy relative to the external energy. Convergence at a concave region can then be effectively implemented as regards the feature of interest using the internal energy, plus several objects can be detected using a multi-detection method based on the initial contour. The proposed method is compared with other conventional methods through objective validation and subjective consideration. As a result, it is anticipated that the proposed method can be efficiently applied to the detection of the pulmonary parenchyma region in medical images.

• International Journal of Contents
• /
• v.3 no.4
• /
• pp.15-21
• /
• 2007

Image morphing deals with the metamorphosis of one image into another. The field morphing depends on the manual work for most of the process, where a user has to designate the control lines. It takes time and requires skills to have fine quality results. It is an object of this paper to propose a method capable of realizing the semi-automation of field morphing using adaptive vertex correspondence based on image segmentation. The adaptive vertex correspondence process efficiently generates a pair of control lines by adaptively selecting reference partial contours based on the number of vertices that are included in the partial contour of the source morphing object and in the partial contour of the destination morphing object, in the pair of the partial contour designated by external control points through user input. The proposed method generates visually fluid morphs and warps with an easy-to-use interface. According to the proposed method, a user can shorten the time to set control lines and even an unskilled user can obtain natural morphing results as he or she designates a small number of external control points.

• Journal of KIISE:Software and Applications
• /
• v.33 no.1
• /
• pp.95-104
• /
• 2006

The Gradient Vector Flow (GVF) snake or active contour model offers the best performance for image segmentation. However, there are problems in classical snake models such as the limited capture range and the slow progress into concavity. This paper presents a new method for enhancing the performance of the GVF snake model by extending the external force fields from the neighboring fields and using a modified smoothing method to regularize them. The results on a simulated U-shaped image showed that the proposed method has larger capture range and makes it possible for the contour to progress into concavity more quickly compared with the conventional GVF snake model.

• International Journal of Precision Engineering and Manufacturing
• /
• v.7 no.1
• /
• pp.47-50
• /
• 2006

An active contour model has been used to detect the edges in a still image. In order to apply the active contour model to edge detection, the energy function which consists of internal, external and image energies should be defined. After defining the energy function, the edge of an object is detected through minimization of the value of the energy function. In this paper, the modified internal energy function is proposed to improve the convergence of the energy function when the active contour model is applied to the tracking of deformable objects using the greedy algorithm. In order to show the performance of the proposed energy function, experiments were carried out for the still and animated images.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.844-847
• /
• 1996

This paper describes the servo position control for the 2-axis positioning table the servo controller consists of conventional feedback loops, disturbance observer. To reduce the contour error, which occurs in the multi-dimensions machines, cross-coupled controller(CCC) is suggested. A weak point of the CCC is their low effectiveness in dealing with arbitrary nonlinear contour such as circles and parabolas. This paper introduces a new nonlinear CCC that is based on control gains that vary during the contour movement The gains of CCC and adjusted in real time according to the shape of nonlinear contour. The feedback controller based on the disturbance observer compensated for external disturbance, plant uncertainty and bad effectiveness by friction model. Suggested servo controller which improve the contouring accuracy, apply to the 2-axis system. Simulation results on 2-axis table verify the effectiveness of the proposed servo controller.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2396-2398
• /
• 2001

Active contour로 알려져 있는 snake는 반복적인 계산으로 이미지상에서 찾고자 하는 물체의 외곽선에 수렴하는 contour로 이미지 상의 물체의 외곽선으로부터 발생하는 외부 에너지(external energy)와 contour 자체로부터 기인하는 내부 에너지(internal energy)를 최소화하는 방향으로 움직인다. 그러나 물체의 윤곽선으로부터 발생하는 외부 에너지는 찾고자 하는 물체뿐만 아니라 주위의 다른 물체로부터도 발생하므로 만일 추적하고자 하는 물체의 주변에 다른 물체들이 존재한다면 snake은 올바르게 동작하지 않게 된다. 본 논문에서는 이러한 단점을 극복하기 위하여 물체의 색상정보를 이용하는 방식을 제안하였다. 물체의 색상 정보는 물체의 고유한 특성 중의 하나로 본 논문에서는 색상정보를 이용하여 원래의 이미지를 찾고자 하는 물체의 색상과 얼마나 유사한가를 나타내는 확률 이미지로 변환하였다. 이렇게 변환된 확률 이미지 상에서 snake 알고리즘을 적용함으로써 배경의 다른 물체로부터 발생하는 외부 에너지를 효과적으로 제거할 수 있다. 또한 본 논문에서는 물체가 이동함에 따라 변화하는 색상 정보를 지속적으로 갱신함으로써 물체의 추적이 효과적으로 이루어지도록 하였다.

• The Journal of Korean Society for Radiation Therapy
• /
• v.14 no.1
• /
• pp.35-39
• /
• 2002

Introduction : It is essential to input patients external contour in 3D treatment plan. We would like to see changes in depth and dose when 3D RTP is operating auto contouring when windows value (Width/Level) differs in this process. Material & Methode : We have analyzed the results with 3D RTP after CT Scanning with round CT Phantom. We have compared and analyzed MU values according to depth changes to Isocenter changing external contour and inputting random Window value. We have watched change values according to dose optimization in 4 directions(LAO, LPO, RAO, RPO), We plan 100 case for exact analyzation. We have results changing window value random to each beam in 100 cans. Result : It showed change between minimum and maximum value in 4 beam is Depth 0.26mm, MU $1.2\%$ in LAO. It showed LPO-Depth 0.13mm, MU $0.9\%$, RAO-Depth 0.2mm MU $0.8\%$, RPO-Depth 0.27mm, MU $1.1\%$ Conclusion : Maximum change in depth 0.27 mm, MU error rate is $0.12\%$ according to Window change. As we can see in these results, it seems Window value change doesn't effect in treatment. However, it seems there needs to select appropriate Window value in precise treatment.