• 정보처리학회논문지B
• /
• 제17B권5호
• /
• pp.363-374
• /
• 2010

본 논문에서는 영상의 동질성 영역 분할을 위한 동질성 문턱 값(Homogeneity Threshold: $H_T$)의 자동 추출과 USRG(Unseeded Region Growing) 기반의 동질성 영역 자동 분할 방법을 제안한다. $H_T$는 인접한 화소들 간에 동질성을 구분하는 기준이 되며, 제안한 방법에 의하여 원본영상으로부터 자동 계산된다. 제안한 방법의 이론적 배경은 Otsu의 단일수준 문턱 값(single level threshold) 방법인데, 이것은 원본 영상의 작은 국소영역을 두 클래스로 분할하기 위하여 사용되고, 두 클래스가 서로 다른 영역으로 구별되는 조건을 만족할 때의 각 클래스의 표준편차의 합($\sigma_c$)을 $H_T$를 계산하기 위한 요소로 사용한다. 제안한 방법의 타당성을 보이기 위해 분할된 동질성 영역들만을 가지고 새롭게 생성한 영상과 원본 영상과의 비교를 통해 시각적으로 차이가 없음을 보이고, 분할된 동질성 영역의 크기순과 화소수가 많은 명암도 순으로 분할된 영역들을 결합한 영상들과 자동 추출된 문턱 값($H_T$)에 범위조정계수 ${\alpha}$을 적용한 값($H^*_T$)를 가지고 분할한 결과 영상들의 제시를 통해 제안한 방법에 대한 타당성을 보였다. 제안한 방법은 해부학이나 생물학의 연구 및 자연 영상의 시각화와 애니메이션 등 다양한 분야에서 활용될 수 있으리라 기대한다.

• 한국환경과학회지
• /
• 제10권1호
• /
• pp.35-39
• /
• 2001

The mutagenicity of the river water of Nakdong river estuary was determined by Ames test using the blue rayon suspension method. Samples were collected from 10 sites in the estuary once in each season of 1998. The samples collected from the sites where industrial waste discharge on May were mutagenic, but the other samples were not mutagenic. The sample collected from the site 1 located near the industrial area (Hadan-dong) were highly mutagenic in the TA98 with (+S9) and without (-S9) mix as well as in the TA100 with (+S9) and without (-S9) S9 mix, suggesting that the river water of this site is polluted by direct and indirect mutagens of frame-shift type as well as direct and indirect mutagens of base-replacement type. The positive mutagenicity, although relatively low, was also detected in TA98 with (+S9) and without (-S9) S9 mix in the extract of the site 4 near the industrial area(Jangrim-dong), suggesting that the primary mutation type is frame-shift. The negative mutagenicity from July to December at the sites (1-4) near the industrial area seems to be affected by the low economic growth rate in 1998 in Korea. On the other hand, the negative mutagenicity in all extracts collected from the sites 5-10 near the residential area where living sewage discharge, suggests that the river water was not polluted by mutagens.

• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.101-110
• /
• 1996

Color image quantization is a process of selecting a set of colors to display an image with some representative colors without noticeable perceived difference. It is very important in many applications to display a true color image in a low cost color monitor or printer. the basic problem is how to display 224 colors with 256 or less colors, called color palette. In this paper, we propose an algorithm to design the 256 or less size color palette by using spatial maskin geffect of HVS and subjective distortion measure weighted by color palette by using spatial masking effect of HVS and subjective distortion measure weighted by color activity in 4*4 local region in any color image. The proposed algorithm consists of octal prequantization and subdivision quantization processing step using the distortion measure and modified Otsu's between class variance maximization method. The experimental results show that the proposed algorithm has higher visual quality and needs less consuming time than conventional algorithms.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.290-293
• /
• 2005

This paper proposes and evaluates a new approach to detect ships as targets from Radarslit-l SAR (Synthetic Aperture Radar) imagery in the vicinity of Korean peninsula. To be more specific, a labeling technique and morphological filtering in conjunction with some other methods are employed to automatically detect the ships. From the test, the ships are revealed to be detected. For ground truth data, information from a radar system is used, which allows assessing accuracy of the approach. The results showed that the proposed approach has the high potential in automatically detecting the ships

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2003년도 The 8th Asian Symposium on Precision Forging ASPF
• /
• pp.158-161
• /
• 2003

Extrusion of forward-gear and backward-rod by combined extrusion with controlling the extrusion velocity using a counter tool is studied. In the combined forward-backward extrusion with controlling extrusion velocity, only parts with short gear can be formed. To obtain longer gear parts, extrusion with reverse ram motion is carried out after the combined forward-backward extrusion process. In this method, combined forward-backward extrusion is carried out until excessive extrusion length is attained and then, the motion of the punch is stopped and the counter tool is moved in the inverse direction and returned to the position for obtaining the desired extrusion length. The experiment is carried out by using lead for billets as a model material. With reverse ram motion, longer gear teeth without under-filling defect can be formed than that by only combined extrusion with controlling extrusion velocity.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2005년도 춘계학술대회 논문집
• /
• pp.147-152
• /
• 2005

This paper proposes an evaluates a new approach to detect ships as targets from Radarsat-1 SAR (Synthetic Aperture Radar) imagery in the vicinity of Korean peninsula. To be more specific, a labeling technique and morphological filtering in conjunction with some other methods are employed to automatically detect the ships. From the test, the ships are revealed to be detected. For ground truth data, information from a radar system is used, which allows assessing accuracy of the approach. The results showed that the proposed approach has the high potential in automatically detecting the ships.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권2호
• /
• pp.61-66
• /
• 2019

증강현실은 카메라로 촬영하고 있는 영상에 가상의 객체를 실시간으로 합성하여 가상의 객체가 현실에 존재하는 것처럼 보이게 하는 기술이다. 증강현실에서 현실에 존재하는 물체에 가상의 물체를 증강하기 위해서는 현실에 존재하는 물체의 위치와 방향을 정확하게 추정해야 하는데, 이 때 활용되는 기술이 영상의 호모그래피(Homography) 이다. 이러한 호모그래피는 영상의 특징점 좌표에 RANSAC 알고리즘을 적용하여 추정할 수 있는데, RANSAC 알고리즘을 이용한 호모그래피 추정 방식은 호모그래피를 추정하고자하는 물체 이외의 배경에 특징점이 많을 경우 정확한 호모그래피를 추정할 수 없다는 문제점이 존재했다. 본 논문에서는 호모그래피를 추정하고자하는 물체가 가까이에 있고 배경이 상대적으로 멀리 위치해있을 때 영상 각 픽셀의 거리 값을 알 수 있는 깊이 영상을 활용하면 물체와 배경을 쉽게 분리할 수 있다는 점을 이용하여 배경의 특징점을 필터링하는 방법을 제안한다. 이를 위하여 본 논문에서는 흑백조 영상인 깊이 영상을 Otsu 알고리즘을 이용하여 사용자와 거리가 가까운 영역과 거리가 먼 영역으로 이진화하고, RGB 영상에서 추출된 특징점 중에서 거리가 먼 영역에 위치한 특징점을 제거함으로써 특징점을 활용한 호모그래피 추정 결과를 향상시킨다. 이러한 방법을 기존의 호모그래피 추정 방법에 적용한 결과 수행시간이 71.7% 단축되었으며, RANSAC 알고리즘의 반복 횟수가 69.4% 줄어들었고, 참정보 비율이 16.9% 증가하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.321-325
• /
• 2004

Retinopathy of Prematurity (ROP) is a common retinal neovascular disorder of premature infants. It can be characterized by inappropriate and disorganized vessel. This paper present a method for blood vessel detection on infant retinal images. The algorithm is designed to detect the retinal vessels. The proposed method applies a Lapalacian of Gaussian as a step-edge detector based on the second-order directional derivative to identify locations of the edge of vessels with zero crossings. The procedure allows parameters computation in a fixed number of operations independent of kernel size. This method is composed of four steps : grayscale conversion, edge detection based on LOG, noise removal by adaptive Wiener filter & median filter, and Otsu's global thresholding. The algorithm has been tested on twenty infant retinal images. In cooperation with the Digital Imaging Research Centre, Kingston University, London and Department of Opthalmology, Imperial College London who supplied all the images used in this project. The algorithm has done well to detect small thin vessels, which are of interest in clinical practice.

• 한국멀티미디어학회논문지
• /
• 제10권12호
• /
• pp.1559-1565
• /
• 2007

The many target-detection methods that use forward-looking infrared (FUR) images can deal with large targets measuring $70{\times}40$ pixels, utilizing their shape features. However, detection small targets is difficult because they are more obscure and there are many target-like objects. Therefore, few studies have examined how to detect small targets consisting of fewer than $30{\times}10$ pixels. This paper presents a small target detection method using clutter rejection with stochastic hypothesis testing for FLIR imagery. The proposed algorithm consists of two stages; detection and clutter rejection. In the detection stage, the mean of the input FLIR image is first removed and then the image is segmented using Otsu's method. A closing operation is also applied during the detection stage in order to merge any single targets detected separately. Then, the residual of the clutters is eliminated using statistical hypothesis testing based on the t-test. Several FLIR images are used to prove the performance of the proposed algorithm. The experimental results show that the proposed algorithm accurately detects small targets (Jess than $30{\times}10$ pixels) with a low false alarm rate compared to the center-surround difference method using the receiver operating characteristics (ROC) curve.

• 한국컴퓨터정보학회논문지
• /
• 제22권5호
• /
• pp.57-63
• /
• 2017

In the paper, we propose a new reliable technique for measuring food intake based on image automatically without user intervention. First, food and bowl image before and after meal is obtained by user. The food and the bowl are divided into each region by the K-means clustering, Otsu algorithm, Morphology, etc. And the volume of food is measured by a proportional expression based on the information of the container such as it's entrance diameter, depth, and bottom diameter. Finally, our method calculates the volume of the consumed food by the difference between before and after meal. The proposed technique has higher accuracy than existing method for measuring food intake automatically. The experiment result shows that the average error rate is up to 7% for three types of containers. Computer simulation results indicate that the proposed algorithm is a convenient and accurate method of measuring the food intake.