• Title/Summary/Keyword: Active contour model

Search Result 163, Processing Time 0.025 seconds

The preprocessing effect using K-means clustering and merging algorithms in cardiac left ventricle segmentation

  • Cho, Ik-Hwan;Do, Ki-Bum;Oh, Jung-Su;Song, In-Chan;Chang, Kee-Hyun;Jeong, Dong-Seok
    • Proceedings of the KSMRM Conference
    • /
    • 2002.11a
    • /
    • pp.126-126
    • /
    • 2002
  • Purpose: For quantitative analysis of the cardiac diseases, it is necessary to segment the left-ventricle(LV) in MR cardiac images. Snake or active contour model has been used to segment LV boundary. In using these models, however, the contour of the LV may not converge to the desirable one because the contour may fall into local minimum value due to image artifact in inner region of the LV Therefore, in this paper, we propose the new preprocessing method using K-means clustering and merging algorithms that can improve the performance of the active contour model.

  • PDF

A Boundary Extraction Method Based on Active Contour Model and Dynamic Programming (능동 윤곽선 모델을 이용한 경계선 추출과 다이나믹 프로그래밍)

  • 김령주;김영철;최흥국
    • Proceedings of the Korea Multimedia Society Conference
    • /
    • 2002.05c
    • /
    • pp.282-285
    • /
    • 2002
  • 의료영상에서 윤곽선의 추출은 관심영역 대한 객관적인 수치 즉 면적, 부피, 장단축의 길이 등을 분석하고 3차원 재구성을 위해 선행되어야 하는 중요한 과정이다. 현재 윤곽선 추출에 대한 않은 방법들이 개발 중에 있으나 이 방법들은 한계를 지니고 있어 더 높은 수준의 처리가 요구된다. 본 논문에서는 active contour model(snake)을 이용하여 MR뇌 영상에서 종양을 추출하였다. Snake의 에너지 최적화 문제를 dynamic programming을 사용하여 개선하였으며 canny edge detection을 이용하여 잡음에 덜 민감하도록 하였다.

  • PDF

Active Contour Based Edge Detection Using Evolutionary Computation (진화 연산을 이용한 능동외곽기반의 윤곽선검출에 관한 연구)

  • Kang, Hyeon-Tae;Cho, Deok-Hwan;Hwang, Gi-Hyun;Mun, Kyeong-Jun;Park, June-Ho;Lee, Hwa-Seok
    • Proceedings of the KIEE Conference
    • /
    • 2001.07d
    • /
    • pp.2405-2407
    • /
    • 2001
  • In this paper, we apply and evolutionary computation(EC), probabilistic optimization algorithm, to active contour. A number of problems exist associated with such as algorithm initialization, existence of local minima, non-convex search space, and the selection of model parameters in conventional models. We propose an adequate fitness function for these problems. The determination of fitness function adequate to active contour using EC is important in search capability. As a result of applying the proposed method to non-convex object shape, we improve the unstability and contraction phenomena, in nature, of snake generated in deformable contour optimization.

  • PDF

A Study on Applying the Adaptive Window to Detect Objects Contour (물체의 윤곽선 검출을 위한 Adaptive Window적용에 관한 연구)

  • 양환석;서요한;강창원;박찬란;이웅기
    • Journal of the Korea Society of Computer and Information
    • /
    • v.3 no.2
    • /
    • pp.57-67
    • /
    • 1998
  • In order to extract the contour of interesting object in the image, Kass suggested the Active Contour Model called "Snakes" The speed of this model is slow and this model is sensitive of initialization. In order to improve these problems, Gunn extracted the accurate contour by using two initializations, and operated to less sensitive of initialization. This method could extract more accurate contour than the existing method, but it had no effect in the speed and it was sensitive of noise. This paper applied to the Energy Minimization Algorithm about only the pixel within the window applying the window of $8{\times}8$ size at each contour point consisting Snakes in order to solve these problems. In order to less sensitive of noise which exists within image, it suggests a method that moves the window to vertical direction for the gradient of each contour point.our point.

  • PDF

Arbitrary Object Contour Extraction using Active Contour Model (Active Contour Model을 이용한 임의의 물체 윤곽선 추출)

  • 문창수;유봉길;오승재;정종필;전희정
    • Journal of the Korea Society of Computer and Information
    • /
    • v.4 no.4
    • /
    • pp.77-85
    • /
    • 1999
  • In this paper. improved the formula of Kass. First of all, improved initial guess inside and outside of an object. So, prevent the of shrink, find more easily and faster the contour of object. Secondly, proposed the algorithm which moved to local minimum with the improvement of formula of the internal energy and $3{times}3$ matrix. Process the noise of local minimum with use of medial filtering. In third, process the phenomenon which edge points gather one point with imposing energy to the energy term. Improve the algorithm to find the contour precisely with the use of threshold. The result of these improvements, make an initial guess easily and find the contour of objects which have higher curvature. Improve the speed of process by reducing the repetition of feedback system.

  • PDF

Automatic Face Tracking based on Active Contour Model using Two-Level Composite Gradient Map (두 단계 합성 기울기 맵을 이용한 활성 외곽선 모델 기반 자동 얼굴 추적)

  • Kim, Soo-Kyung;Jang, Yo-Jin;Hong, Helen
    • Journal of KIISE:Software and Applications
    • /
    • v.36 no.11
    • /
    • pp.901-911
    • /
    • 2009
  • In this paper, we propose a construction technique of two-level composite gradient map to automatically track a face with large movement in successive frames. Our method is composed of three main steps. First, the gradient maps with two-level resolution are generated for fast convergence of active contour. Second, to recognize the variations of face between successive frames and remove the neighbor background, weighted composite gradient map is generated by combining the composite gradient map and difference mask of previous and current frames. Third, to prevent active contour from converging local minima, the energy slope is generated by using closing operation. In addition, the fast closing operation is proposed to accelerate the processing time of closing operation. For performance evaluation, we compare our method with previous active contour model-based face tracking methods using a visual inspection, robustness test and processing time. Experimental results show that our method can effectively track the face with large movement and robustly converge to the optimal position even in frames with complicated background.

Face Detection Using Active Contours (Active Contours를 사용한 얼굴 검출)

  • 정도준;장재식;박세현;김항준
    • Proceedings of the Korea Multimedia Society Conference
    • /
    • 2002.05c
    • /
    • pp.195-199
    • /
    • 2002
  • 본 논문에서는 주어진 입력 이미지에서 얼굴 영역을 검출하기 위한 액티브 컨투어 모델(active contour models)을 제안한다. 제안한 모델은 스킨 칼라 모델(skin color model)에 의해 표현되는 사람 얼굴의 칼라 정보를 이용한다. 본 논문에서는 첨점(cusps), 모서리 (corners), 그리고 자동 위상 변화(automatic topological changes)를 고려한 레벨 셋 메소드(level set method)를 사용하여 액티브 컨투어를 진화시킨다. 실험 결과는 제안한 방법이 얼굴 영역 검출에 효과가 있음을 보여준다.

  • PDF

A New Snakes Algorithm Combined with Disparity Information in the Stereo Images (스테레오 영상에서 변이 정보를 결합한 새로운 스네이크 알고리즘)

  • 김신형;전병태;장종환
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.28 no.11C
    • /
    • pp.1088-1097
    • /
    • 2003
  • In this paper, we propose a method that improves the snakes algorithm well known as previously active contour model. Generally, the previous snakes algorithm applied to the 2-D images doesn't get the good results due to the influences about other objects adjacent to contour of object to be extracted. Users directly set the initial snakes points near to the contour of the object to get better results. In this paper, using the disparity information of the stereo images, a new algorithm of the object segmentation is proposed to reduce the influences adjacent to the contour of object. Users can establish initial snakes points automatically from the setting of the interested regions.

Segmentation of Brain Ventricle Using Geodesic Active Contour Model Based on Region Mean (영역평균 기반의 지오데식 동적 윤곽선 모델에 의한 뇌실 분할)

  • Won Chul-Ho;Kim Dong-Hun;Lee Jung-Hyun;Woo Sang-Hyo;Cho Jin-Ho
    • Journal of Korea Multimedia Society
    • /
    • v.9 no.9
    • /
    • pp.1150-1159
    • /
    • 2006
  • This paper proposed a curve progress control function of the area base instead of the existing edge indication function, in order to detect the brain ventricle area by utilizing a geodesic active contour model. The proposed curve progress control function is very effective in detecting the brain ventricle area and this function is based on the average brightness of the brain ventricle area which appears brighter in MRI images. Compared numerically by using various measures, the proposed method in this paper can detect brain ventricle areas better than the existing method. By examining images of normal and diseased brain's images by brain tumor, we compared the several brain ventricle detection algorithms with proposed method visually and verified the effectiveness of the proposed method.

  • PDF

Image Segmentation of Special Area Using the Level Set (레벨셋을 이용한 특정 영역의 영상 세그먼테이션)

  • Joo, Ki-See;Choi, Deog-Sang
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.14 no.4
    • /
    • pp.967-975
    • /
    • 2010
  • Image segmentation is one of the first steps leading to image analysis and interpretation, which is to distinguish objects from background. However, the active contour model can't exactly extract the desired objects because the phase only is 2. In this paper, we propose the method which can find the desired contours by composing the initial curve near the objects which have intensities of special range. The initial curve is calculated by the histogram equalization, the Gaussian equalization, and the threshold. The proposed method reduce the calculation speed and exactly detect the wanted objects because the initial curve set near by interested area. The proposed method also shows more efficient than the active contour model in the results applied the CT and MR images.