빛간섭단층촬영 영상의 분석 알고리즘에 따른 당뇨황반부종 측정치의 신뢰도 비교

계효정(Hyo Jung Gye),배정훈(Jeong Hun Bae),송수정(Su Jeong Song) 대한안과학회 2016 대한안과학회지 Vol.57 No.5

목적: 당뇨황반부종에서 자동망막경계설정 소프트웨어(automatic segmentation software)인 CirrusTM High definition optical coherence tomography (HD-OCT) segmentation algorithm과 Iowa reference algorithm을 이용하여 망막층의 경계설정 신뢰도를 비교하고자 하였다. 대상과 방법: Cirrus algorithm과 Iowa algorithm을 이용하여 당뇨황반부종 환자 23명(30안)의 중심와두께를 측정하고 망막층을 세분화하여 신뢰도를 비교하였다. 두 알고리즘의 일치도, 상관관계 및 신경절세포층과 망막신경섬유층의 경계설정 오류빈도를 평가하였다. 결과: Cirrus software로 측정한 중심와두께는 평균 512.07 ± 182.35 μm로 Iowa algorithm 측정치인 476.53 ± 32.36 μm에 비해 유의하게 높았다(p〈0.05). 두 알고리즘 측정치의 급내상관계수는 0.929였고 유의한 상관관계를 보였다(β=0.868, p〈0.001). 신경절세포층과 망막신경섬유층의 경계설정 오류빈도는 중심와두께가 400 μm 미만인 경우 Cirrus algorithm과 Iowa algorithm에서 각각 45%, 9%였고 400 μm 이상인 경우 95%, 42%였다. 결론: 당뇨황반부종에서 중심와두께는 Cirrus algorithm과 Iowa algorithm 사이에 비교적 높은 일치도와 유의한 상관관계를 보였으나, 신경절세포층과 망막신경섬유층 측정에 있어서는 두 알고리즘이 차이를 보였고, 특히 중심와두께가 400 μm 이상인 경우 망막층의 경계설정 신뢰도는 Iowa algorithm에서 더 높았다. Purpose: To evaluate segmentation reliability in diabetic macular edema (DME) estimates between a CirrusTM HD-OCT image analysis algorithm and an Iowa reference algorithm, which are an automatic segmentation software. Methods: Thirty eyes from 23 patients diagnosed with DME were included and underwent spectral-domain optical coherence scans (CirrusTM HD-OCT). Central foveal thickness (CFT) and ganglion cell layer-inner plexiform layer segmentation data were compared with those produced by the CirrusTM HD-OCT segmentation algorithm and Iowa reference algorithm. Measurement agreement was assessed using intraclass correlation (ICC) and segmentation errors were confirmed by 2 ophthalmologists. Results: The mean CFT in the 1-mm central area determined by the manufacturer-supplied Cirrus software and Iowa reference algorithm was 512.07 ± 182.35 μm and 476.53 ± 32.36 μm, respectively (p 〈 0.05). The mean paired difference was 35.53 ± 92.46 μm (ICC, 0.929). Segmentation errors were demonstrated in eyes with a CFT less than 400 μm, specifically for 45% of scans obtained by the Cirrus algorithm and 9% from the Iowa algorithm, in eyes with a CFT equal to or higher than 400 μm, the error rates were 95% and 42%, respectively. Conclusions: CFT measurement in eyes with diabetic macular edema using the Cirrus algorithm and Iowa algorithm showed relatively high degrees of agreement and significant correlation. In eyes with a CFT equal to or higher than 400 μm, the Iowa algorithm showed higher reliability in retinal segmentation than the Cirrus algorithm.

Medical Image Segmentation Based on Morphology Algorithm and FCM Algorithm

Shigang Wang,Zhinan Rong,Xueshan Gao 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.10

Fuzzy c-means algorithm is an unsupervised clustering algorithm, its clustering process can reduce the human intervention, and it is suitable for processing medical images of uncertainty and ambiguity. When simply using FCM algorithm in brain image segmentation will leads to the condition of low accuracy. On the basis of FCM algorithm, this paper proposes a new method which combines FCM algorithm and morphology algorithm. The result of simulation shows that this method can accurately and efficiently segment the brain image. The new algorithm is an effective method for image segmentation.

유전자 알고리즘을 이용한 반자동 영상분할 시스템 개발

임혁순(Hyuk-Soon Im),박상성(Sang-Sung Park),장동식(Dong-Sik Jang) 한국컴퓨터정보학회 2006 韓國컴퓨터情報學會論文誌 Vol.11 No.4

현재 영상분할은 사용자가 원하는 영상을 분할하고, 분할된 객체에 다른 영상을 합성하는 기술에 대해 많은 연구가 진행되어왔다. 본 논문에서는 점진적 영역병합과 유전자 알고리즘을 이용하여 새로운 반자동 영상 분할 방법을 제안하였다. 제안된 알고리즘은 사용자가 원하는 객체를 선정한 후, 유전자 알고리즘을 이용해 객체의 경계를 검색한다. 검색된 경계를 기반으로 분수령 알고리즘을 이용하여 사용자가 원하는 객체의 영역을 분할하였다. 분할된 객체에서 불명확한 영역들을 점진적 영역 병합으로 배경과 객체를 분리하였다. 그리고, 알고리즘 개발을 효과적으로 수행하기 위해 GUI기반의 인터페이스를 만들어 사용자가 원하는 값을 적용할 수 있게 하였다. 실험에서는 제한된 방법의 우수성 입증을 위하여 다양한 영상을 분석하였다. 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.

클러스터링 알고리즘의 후처리 방안과 분할된 영역들의 분류에 대한 연구

오준택,김보람,김욱현 한국정보처리학회 2009 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.16 No.1

Some clustering algorithms have a problem that an image is over-segmented since both the spatial information between the segmented regions is not considered and the number of the clusters is defined in advance. Therefore, they are difficult to be applied to the applicable fields. This paper proposes the new post-processing methods, a reclassification of the inhomogeneous clusters and a region merging using Baysian algorithm, that improve the segmentation results of the clustering algorithms. The inhomogeneous cluster is firstly selected based on variance and between-class distance and it is then reclassified into the other clusters in the reclassification step. This reclassification is repeated until the optimal number determined by the minimum average within-class distance. And the similar regions are merged using Baysian algorithm based on Kullbeck-Leibler distance between the adjacent regions. So we can effectively solve the over-segmentation problem and the result can be applied to the applicable fields. Finally, we design a classification system for the segmented regions to validate the proposed method. The segmented regions are classified by SVM(Support Vector Machine) using the principal colors and the texture information of the segmented regions. In experiment, the proposed method showed the validity for various real-images and was effectively applied to the designed classification system. 클러스터링 알고리즘은 영역들간의 공간정보를 고려하지 않고 사전에 정의된 수만큼의 군집들로 분할하기 때문에 영상의 과분할을 유발하며, 이에 실제적인 응용분야에 적용하기에는 어려움이 존재한다. 본 논문에서는 클러스터링 알고리즘에 의해 획득한 군집들을 대상으로 보다 나은 분할결과를 획득하기 위한 후처리 방안으로, 비동질적인 군집의 재분류와 베이시안 알고리즘에 의한 유사영역의 합병알고리즘을 제안한다. 먼저, 클러스터링 알고리즘에 의해 분할된 영상의 군집들에 대해서 가장 비동질적인 군집을 선택하여 이를 나머지 군집들 중 하나로 재분류하며, 최소평균내부거리값에 의해 결정된 군집수만큼 반복적으로 수행된다. 그리고 여전히 존재하는 유사한 인접영역들을 제거하기 위해서 영역간의 Kullbeck-Leibler 거리값을 기반으로 베이시안 알고리즘을 이용한 영역 합병을 수행한다. 마지막으로, 제안한 방법의 유효함을 검증하기 위한 목적으로, 분할된 영역들의 우세컬러와 텍스처 정보를 기반으로 하는 SVM(support vector machine) 기반 영역분류시스템을 설계한다. 실험결과, 제안한 방법은 다양한 실험영상들에 대해서 단계별 더 나은 성능을 보였으며, 분할된 영역들의 분류에서도 효과적인 결과를 보여 제안방법의 유효함을 확인하였다.

Development of Region-based Crop Segmentation Algorithm for Sharp-leaf Crops using UAV-RGB imagery

( Dong-wook Kim ),( Hak-jin Kim ),( Sang-jin Jeong ),( Won Suk Lee ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.1

Crop segmentation is fundamental and important in agricultural information automation. Many issues, such as crop growth stage prediction, crop line detection, crop density estimation, cover crop identication, leaf disease detection, and crop biomass monitoring, are highly dependent on the performance of crop segmentation algorithms. Under field conditions, crop segmentation for UAV-imagery should be more sophisticated considering low resolution of image, atmospheric interference, varying illumination on each day, and complex backgrounds. Especially, in the cultivation of Korea, a plastic mulch which has been used for restricting weeds and preventing damages from cold weather, makes the backgrounds more complex. In our previous study, ExG-Otsu’s threshold algorithm, which has been very commonly used in RGB images, was used for segmentation of Chinese cabbage and White radish. However, ExG-Otsu’s threshold algorithm showed low accuracy for sharp-leaf crops such as Garlic and Onion because of the complex shape of crops and shadow effect under various illumination conditions. In this study, crop segmentation algorithm that perform for sharp-leaf crops were developed by applying region-based segmentation algorithm with CIE L*a*b* color space. Combining region-based segmentation algorithm based on local density estimation and CIE L*a*b* color space improves the segmentation accuracy when compared with the previous method because the algorithm could removes texture and irregularity. The results showed the potential of using UAV-based RGB imagery for crop segmentation of sharp-leaf crops over the whole growing season in a quantitative manner.

A Review on Image Segmentation with its Clustering Techniques

Priyansh Sharma,Jenkin Suji 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.5

Segmentation refers to a technique in which an image in digital form is partitioned into multiple segments (basically groups of pixels, also termed as Super pixels). This paper is a survey on Image Segmentation with its clustering techniques. Image Segmentation is the procedure of apportioning a picture into numerous segments, to change the exemplification of a picture into another which is more useful and easy to segment. A few universally useful calculations and approaches have been developed for picture division. It separates a digital picture into numerous locales to investigate them. It is likewise used to recognize segment items in the picture. A few picture segmentation procedures have been developed by the specialists with a specific end goal to make pictures smooth and simple to access. This paper describes segmentation techniques, advantages and disadvantages of the clustering methods and a comparison of the techniques.

유전자알고리즘을 이용한 영상분할 문턱값의 자동선정에 관한 연구

이병룡(Byung-Ryong Lee),Quoc Bao Truong,Van Huy Pham,김형석(Hyoung-Seok Kim) 제어로봇시스템학회 2011 제어·로봇·시스템학회 논문지 Vol.17 No.6

In this paper, we focus on the issue of automatic selection for multi-level threshold, and we greatly improve the efficiency of Otsu’s method for image segmentation based on genetic algorithm. We have investigated and evaluated the performance of the Otsu and Valley-emphasis threshold methods. Based on this observation we propose a method for automatic threshold method that segments an image into more than two regions with high performance and processing in real-time. Our paper introduced new peak detection, combines with evolution algorithm using MAGA (Modified Adaptive Genetic Algorithm) and HCA (Hill Climbing Algorithm), to find the best threshold automatically, accurately, and quickly. The experimental results show that the proposed evolutionary algorithm achieves a satisfactory segmentation effect and that the processing time can be greatly reduced when the number of thresholds increases.

GA-Based Adaptive Window Length Estimation for Highly Accurate Audio Segmentation

Myeongsu Kang,Jong-Myon Kim 보안공학연구지원센터 2015 International Journal of Multimedia and Ubiquitous Vol.10 No.1

Accurate audio segmentation has recently received increasing attention for its applications in automatic indexing, content analysis and information retrieval. Hence, this paper proposes a highly accurate audio segmentation methodology using a genetic algorithm-based approach to adapting and optimizing segmentation window lengths. Specifically, this paper analyzes the parameter sequence of the root-mean-square values of an input audio stream with optimal sliding window (or segmentation window) lengths found and adapted by a genetic algorithm. In addition, this paper determines whether an audio-cut occurs or not by utilizing the parameter sequences as inputs of a support vector machine. Experimental results indicate that the proposed approach achieves 100.00% and 98.69% in the average precision and recall rates of segmentation performance, respectively.

Image 3d Adaptive Algorithm Based on Graph Cut

Fengxian Tang,Yunfeng Yang 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.8

As a key step in the visual inspection, image to appear particularly important. Compared with the traditional algorithm, graph cut algorithm overall high precision and faster convergence speed in discontinuous area. Based on adaptive algorithm on the basis of in-depth study, this paper proposes a three-dimensional adaptation algorithm based on graph cut theory in order to realize the image matching. Experimental results show that this algorithm can well meet the requirements of high precision and high real time capability, solve the problems such as large amount of calculation in the traditional algorithm.

Design and Implementation of the Compound Noun Segmentation Algorithm Based on Statistical Information

Chang-Geun Kim,Han-Ho Tack 한국지능시스템학회 2004 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.4 No.3

This paper suggests a reverse segmentation algorithm using affix information and some preference pattern information of Korean compound nouns. The structure of Korean compound nouns is mostly derived from Chinese characters, and it includes some preference patterns utilized as a segmentation rule in this paper. To evaluate the accuracy of the proposed algorithm, an experiment was performed with 36,061 compound nouns. The experiment resulted in getting 99.3% of correct segmentation and showed excellent satisfactory results from the comparative experimentation with other algorithms. Especially, most of the four-syllable or five-syllable compound nouns were successfully segmented without fail.