• Journal of KIISE:Software and Applications
• /
• v.33 no.4
• /
• pp.418-426
• /
• 2006

This paper proposes a robust and efficient segmentation method for a cardiac ultrasound image taken from a probe inserted into the heart in surgery. The method consists of three steps: initial boundary extraction, whole boundary modification using confidence competition, and local boundary modification using the rolling spoke method. Firstly, the initial boundary is extracted with threshold regions along the global spokes emitted from the center of an ultrasound probe. Secondly, high confidence boundary edges are detected along the global spokes by competing among initial boundary candidate and new candidates achieved by edge and appearance information. finally, the boundary is modified by rolling local spokes along concave regions that are difficult to extract using the global spokes. The proposed method produces promising segmentation results for the ultrasound cardiac images acquired during surgery.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1B
• /
• pp.156-166
• /
• 2000

A rate-distortion based segmentation using recursive merging is presented, which considers texture as a homogeneity by adopting the procedure of a generalized texture approximation. The texture in a region is approximated by SA-DCT and a set of two uniform quantizers with fixed step sizes, one for DC and another for AC. Using the approximated texture, we calculated the rate-distortion based cost. The segmentation using recursive merging is performed by using the rate-distortion based cost. Experimental results for 256$\times$256 Lena show that the region-based coding using the proposed segmentation yields the PSNR improvements of 0.8~ 1.0 dB and 1.2~1.5 dB over that using the rate-distortion based segmentation with DC approximation only and JPEG, respectively.

• Journal of KIISE:Software and Applications
• /
• v.27 no.12
• /
• pp.1219-1226
• /
• 2000

본 논문에서는 유전자 알고리즘과 피라미드(다단계 또는 다 해상도)를 결합한 새로운 영상분할 방법을 제안하다. 먼저, 영상을 피라미드의 해상도가 낮은 상위 단계로 분할하고 좋은 적합도를 가진 염색체의 개체군을 얻는다. 둘째, 해상도를 높인 다음 단계의 입력으로 앞 단계에서 얻은 염색체들을 사용하며, 더욱 세분화된 분할이 이루어지도록 염색체를 진화시키다. 유전자 알고리즘의 적합함수는 각 영역의 규질성과 peakiness를 이용하여 정의하였다. 교차는 교차점을 중심으로 영상을 2분하여 서로 교환하는 1점 교환법을 사용하였으며, 돌연변이는 병합과 분할이 이루어지도록 설계하였다. 본 논문은 저 해상도에서 가능성(적합성)이 큰 유전자를 신속히 구한 훙 단계적으로고 해상도에서 적합한 유전자로 진화시켜 나가는 방법으로 처음부터 최고 해상도에 유전자 알고리즘을 적용하는 종전의 방법보다 훨씬 더 효율적이며 유전자 알고리즘과 다단계 기법의 이상적인 결합이라 할 수 있다. 분할 결과에서도 타 알고리즘에 비하여 우수하거나 비슷한 결과를 얻었다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.3
• /
• pp.105-112
• /
• 1989

A new simple edge-based segmentation method composed of edge tracing, region filling, and post processing is proposed. Solving so called the small gap problem common to most of edge-based methods, this method segments images so completely as to be suitable for image coding. Experimental results show that our methods has much less (1/3) computation time than Perkins' one, and its reconstructed images is good on visual perception.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5A
• /
• pp.861-872
• /
• 2006

The element free Galerkin method is extended by the local partition of unity method to model the cohesive cracks in two dimensional continuum. The shape function of a particle whose domain of influence is completely cut by a crack is enriched by the step enrichment function. If the domain of influence contains a crack tip inside, it is enriched by a branch enrichment function which does not have the LEFM stress singularity. The discrete equations are obtained directly from the standard Galerkin method since the enrichment is only for the displacement field, which satisfies the local partition of unity. Because only particles whose domains of influence are influenced by a crack are enriched, the system matrix is still sparse so that the increase of the computational cost is minimized. The condition for crack growth in dynamic problems is obtained from the material instability; when the acoustic tensor loses the positive definiteness, a cohesive crack is inserted to the point so as to change the continuum to a discontiuum. The crack speed is naturally obtained from the criterion. It is found that this method is more accurate and converges faster than the classical meshless methods which are based on the visibility concept. In this paper, several well-known static and dynamic problems were solved to verify the method.

• Journal of KIISE:Software and Applications
• /
• v.27 no.8
• /
• pp.846-854
• /
• 2000

In this paper, we propose effecient methods to extract the femoral head region in MR images. The femoral head area in MRI is approximated using Hough transform and the anatomical features of the femoral heads. Then, modified region growing method is applied to extract the femoral head region. We measured the parameters for the diagnosis of the avascular necrosis of the femoral heads from the segmented femoral head region. The proposed methods are proved very effective to extract the femoral head of healthy volunteer and of the patient having heavy avascular necrosis. The measured parameters can be used very efficiently for the quantitative analysis and the diagnosis of the avascular necrosis of the femoral heads.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.123-131
• /
• 2019

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.2
• /
• pp.596-605
• /
• 1997

The synamic systrm emplohing the self-squared function, , $f(Z)=z^2+c$, provides the Mandelbrot set which classifies constants c using the divergence of the sequence starting from the origin.To speed-up the generation of Mandelbrot set images, two approaches , called as the divide-and-conquer technique and the triangular boundary tracing technique, have been developed.However , the divede-and-conquer technique genrates sequences of some pixels that so not affect graphical representations of the Mandelbrot set.The triangular boundary tracing tech-mique does noot represent some 8-connected components of the Mandelbrost set.In this paper, we prorose a new ;method which solves the 8-connectivity problem of triangular boundary tracing technique.This algorithm considers the divergence for only pixels which are essential to the graphical repressentation of the Mandelbrot set.It also foves good representations for 8-connected components like hairly structures.

• Journal of radiological science and technology
• /
• v.27 no.3
• /
• pp.19-24
• /
• 2004

MRI imaging is one of the imaging techniques showing anatomical structures of human body for medical diagnosis, and has been researched in order to provide better quality of anatomical information. In this study, we propose a very useful method to extract an interest areas and how to diagnose necrolysis of femoral neck disease automatically. Regions of femoral neck is set using anatomical features and Hough transform and advantages of both region extension and histogram-based region segmentation method are combined for better region segmentation. As a result of the proposed method, good imaging quality was obtained for femoral neck with both normal and severe necrosis as well as for femoral neck in early stage of necrolysis.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.10
• /
• pp.1069-1074
• /
• 2009

A sub-domain method for free vibration analysis of arbitrarily shaped, concave membranes with a deep groove is proposed in the paper. The proposed method divides the concave membrane of interest into two convex regions. The vibration displacement(approximate solution) of each convex region is assumed by linearly superposing plane waves generated at edges of the region. A sub-system matrix for each convex region is extracted by applying a provisional boundary condition to the approximate solution. Finally, a system matrix, which of the determinant gives eigenvalues of the concave membrane, is made by considering the fixed boundary condition(displacement zero condition) at edges and the compatibility condition(the condition of continuity in displacement and slope) at the interface between the two regions. Case studies show that the proposed method is valid and accurate when the eigenvalues by the proposed are compared to those by NDIF method, FEM, or the exact method.