• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.472-474
• /
• 2001

본 논문은 wavelet 기반의 watershed를 이용한 효율적인 영상 분할을 기법을 제안한다. 영상 분할을 위해 입력 영상을 wavelet transform을 사용하여 low-resolution 영상을 생성한 후 watershed 알고리즘을 이용해 분할하고, 이를 Inverse wavelet transform함으로써 원 영상으로 복원한다. 복원된 영상을 의미 있는 영역들로 분할하기 위해 wavelet 특징값의 유사성을 두 인접한 영역에 비교하여 병합한다. 실험 결과 제안한 방법은 영상의 잡음에 대한 강인함과 영상의 과분할 문제를 해결할 수 있다.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.609-618
• /
• 2013

This paper proposes a fast image segmentation method that gives high segmentation performance as graph-cut based methods. Graph-cut based image segmentation methods show high segmentation performance, however, the computational complexity is high to solve a computationally-intensive eigen-system. This is because solving eigen-system depends on the size of square matrix obtained from similarities between all pairs of pixels in the input image. Therefore, the proposed method uses the small-size square matrix, which is obtained from all the similarities among regions obtained by segmenting locally an image into several regions by graph-based method. Experimental results show that the proposed multi-scale image segmentation method using the algebraic multi-grid shows higher performance than existing methods.

• Journal of the Korea Computer Graphics Society
• /
• v.2 no.2
• /
• pp.21-28
• /
• 1996

The nature of complexity of medical images makes them difficult to segment using standard techniques. Therefore the usual approaches to segment images continue to predominantly involve manual interaction. But it tediously consumes a good deal of time and efforts of the experts. Hereby a nonmanual parameters estimation which can replace the manual interaction is needed to solve the problem of redundant manual works for an image segmentation. This paper attempts to estimate parameters for an image region segmentation using Scale Space Filtering. This attempt results in estimating the number of regions, their boundary and each representatives to be segmented 2-dimensionally and 3-dimensionally. Using this algorithm, we may diminish the problem of wasted time and efforts for finding prerequisite segmentation parameters, and lead the relatively reasonable result of region segmentation.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1383-1391
• /
• 2011

Following the appearance of the latest medical equipment with improved function, the importance of image analysis which enables effective image processing and analysis consistent with the hardware performance is on the rise. As well as, ongoing study is being done on the 2D medical image processing and 3D reconstruction. This paper segments chest CT images into each stage and finally shows 3D reconstruction of each segmented result. Among various image segmentation methods, Region Growing and apply sharpening and Gamma Controller as for image improvement for effective segmentation, image segmentation in order of bronchus and lung, bronchus, lung. Human organs image of segmented is use VTK(Visualization Toolkit) to make 3D reconstruction, two and three-dimensional medical image processing and analysis for lesions diagnosis are able to utilized.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.191-194
• /
• 2002

영상분할이란 영상 내에 존재하는 객체를 배경에서 분리해내는 것을 말한다. Active Contour 모델은 객체를 영상에서 분리하는 gradient 기반의 영상분할 방식이다. 전통적인 의미의 Active Contour 모델에서 사용한 gradient 함수 기반의 영상분할은 잡영이 많고 객체와 배경간 뚜렷한 경계가 없는 영상에서는 그 한계를 보이고 있다. 이에 본 논문에서는 이러한 Active Contour 모델의 단점을 극복하기 위한 방법으로 영상 내의 진화곡선에 의존하는 에너지 함수인 Mumford-Shah Functional을 이용한 방법을 제안한다. 이 방법은 영상 내의 Active Contour를 진화시켜 Mumford-Shah 함수의 에너지를 최소화시키는 Level Set 함수를 찾고 Level Set 함수에 의해 얻어진 부분영상에서 히스토그램을 이용한 임계치(thresholding) 방식을 사용하는 보다 효과적인 객체추출 모델이다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.143-146
• /
• 2000

본 논문에서는 다수의 실내 영상으로부터 영상을 촬영한 카메라의 속성정보와 실내 환경에 대한 기하정보를 추출하는 방법을 제안한다. BSP-Tree를 이용하여 주어진 실영상을 각각의 부분 영역이 실제로도 평면 영역에 해당되도록 분할하였으며, 특징점 대응을 통해 각 분할된 영역의 영상간 대응을 찾고 이로부터 각 분할 영역의 homography를 계산하였다 또한 간단한 가정을 통해 계산된 homography로부터 각 분할영역에 대응된 평면의 방정식과 각 영상을 촬영한 카메라의 속성을 찾아낼 수 있믐을 보였다. 본 논문에서 제안한 방법은 현재 본 연구팀이 구현 중인 영상기반 모델링 시스템에서 핵심적인 기능을 수행하리라 기대된다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.4
• /
• pp.421-430
• /
• 2010

Image segmentation technique is becoming increasingly important in the field of remote sensing image analysis in areas such as object oriented image classification to extract object regions of interest within images. This paper presents a new method for image segmentation in High Resolution Remote Sensing Image based on Improved Seeded Region Growing (ISRG) and Region merging. Firstly, multi-spectral edge detection was done using an entropy operator in pan-sharpened QuickBird imagery. Then, the initial seeds were automatically selected from the obtained multi-spectral edge map. After automatic selection of significant seeds, an initial segmentation was achieved by applying ISRG to consider spectral and edge information. Finally the region merging process, integrating region texture and spectral information, was carried out to get the final segmentation result. The accuracy assesment was done using the unsupervised objective evaluation method for evaluating the effectiveness of the proposed method. Experimental results demonstrated that the proposed method has good potential for application in the segmentation of high resolution satellite images.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.532-534
• /
• 2003

본 논문에서는 인쇄체 우편주소 영상에서 smearing과 히스토그램 분석을 이용한 고속의 문자열 기울기 보정 및 분할 방법을 제안하였다. 제안한 방법에서는 입력 영상을 가분할 하고, 각각의 가분할 영상에 대한 수평 히스토그램을 분석하여 기울기 측정 및 보정을 수행하였다. 문자열 분할 단계에서는, 기울기가 보정된 영상에 smearing을 수행하고, 영상에 존재하는 잡영 및 각종 바코드를 제거하고, 수평 히스토그램 분석을 통해 최종 문자열 분할 결과를 도출하였다. 제안한 방법을 사용한 실험에서 2,000 장의 테스트 영상 중 1,989장의 영상에서 정확한 문자분할 결과를 얻을 수 있었으며, 제안한 방법이 유효함을 보였다.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.812-819
• /
• 2016

This paper introduces and analyzes the theoretical basis and method of the conventional initial-value assignment problem and feasibility of image segmentation. The paper presents topological evidence and a method of appropriate initial-value assignment based on topology theory. Subsequently, the paper shows minimum conditions for feasibility of image segmentation based on separation axiom theory of topology and a validation method of effectiveness for image modeling. As a summary, this paper shows image segmentation with its mathematical validity based on topological analysis rather than statistical analysis. Finally, the paper applies the theory and methods to conventional Gaussian random field model and examines effectiveness of GRF modeling.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.283-289
• /
• 2006

The present image segmentation is what user want to segment image and has been studied for technology in composition of segment object with other images. In this paper, we propose a method of novel semi-automatic image segmentation using gradual region merging and genetic algorithm. Proposed algorithm is edge detection of object using genetic algorithm after selecting object which user want. We segment region of object which user want to based on detection edge using watershed algorithm. We separated background and object in indefinite region using gradual region merge from Segment object. And, we have applicable value which user want by making interface based on GUI for efficient perform of algorithm development. In the experiments, we analyzed various images for proving superiority of the proposed method.