• 한국방재학회 논문집
• /
• 제8권5호
• /
• pp.77-83
• /
• 2008

본 연구에서는 정부차원에서 충남 연기군 일대에 추진되고 있는 행정중심복합도시 대상지역($132\;km^2$)에 대하여 재해대책을 위한 토지피복 분류 및 식생활력도(NDVI) 평가를 시도하였다. 활용한 영상은 아리랑 2호, LANDSAT, Aster 영상이며 해상도에 따른 분류의 한계를 비교, 평가하였다. 대상지역은 주로 산지와 논과 밭 등의 경작지이므로 특히 논과 밭의 분류에 주의를 기울였다. 아리랑2호 영상의 분류에 있어서는 고해상영상 분류를 위한 세그먼테이션 기법을 적용하였다. 분류의 정확도를 평가하기 위해 표본적으로 현장조사를 실시하여 검사하였으며 국가 토지이용도 및 토지대장의 지목과 비교하였다. 얻어진 결과는 shape file의 형태로 주제도를 완성하였으며 이는 행정중심복합도시의 미래지향적 개발계획을 위한 정책결정에 많은 도움이 될 것이다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.204-206
• /
• 2003

In order to utilize remote sensed images effectively, a lot of image classification methods are suggested for many years. But, the accuracy of traditional methods based on pixel-based classification is not high in general. In this study, object oriented classification based on image segmentation is used to classify Landsat images. A necessary prerequisite for object oriented image classification is successful image segmentation. Object oriented image classification, which is based on fuzzy logic, allows the integration of a broad spectrum of different object features, such as spectral values , shape and texture. Landsat images are divided into urban, agriculture, forest, grassland, wetland, barren and water in sochon-gun, Chungcheongnam-do using object oriented classification algorithms in this paper. Preliminary results will help to perform an automatic image classification in the future.

• 한국컴퓨터정보학회논문지
• /
• 제25권5호
• /
• pp.137-146
• /
• 2020

20대 미혼 여성 182명의 직접 계측치를 이용한 유방유형 분류에 유방전체 형상 요인, 유방상부내측형상 요인, 유방볼륨 요인, 유방하부외측형상 요인 등 4가지 요인이 추출되었다. 군집분석을 통해 '상부발달 유방', '밋밋한 유방', '하부 발달 유방', '돌출한 유방' 등 4유형의 유방유형으로 분류하였다. 유방유형은 목앞점~젖꼭지점길이, 목옆점~젖꼭지점길이, 유방안쪽점 사이간격, 젖꼭지 간격, 유방아래직경, 유방내측깊이, 유방바깥쪽길이, 유방아래길이, 젖가슴가쪽점~젖가슴위쪽점길이, 젖가슴 밑 윤곽선길이 등 10개 항목으로 판별 가능하다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 1999년도 추계학술대회-지능형 정보기술과 미래조직 Information Technology and Future Organization
• /
• pp.313-320
• /
• 1999

In this paper, a translation, rotation and scale invariant system for the classification of closed 2D images using the bispectrum of a contour sequence and the weighted fuzzy mean method is derived and compared with the classification process using one of the competitive neural algorithm, called a LVQ(Learning Vector Quantization). The bispectrun based on third order cumulants is applied to the contour sequences of the images to extract fifteen feature vectors for each planar image. These bispectral feature vectors, which are invariant to shape translation, rotation and scale transformation, can be used to represent two-dimensional planar images and are fed into an classifier using weighted fuzzy mean method. The experimental processes with eight different shapes of aircraft images are presented to illustrate the high performance of the proposed classifier.

• 패션비즈니스
• /
• 제11권5호
• /
• pp.124-135
• /
• 2007

To understand tendency of body shapes of Chinese women who reside in Beijing and Shanghai for improving the match of exported clothes to China, this categorizes the bodies by extracting the elements of the objects and understanding body promotion. To categorize the subject by not size factor but form factor, data were compared and analyzed mainly with index based on measurement of the body. This selected specimen as 1381 of Chinese women from 19 to 50 selected in random sampling in Shanghai and Beijing from 23th, June to 7th August in 2004. 1. Chinese women is generally separated in 7.09 parts and upper body including waist shapes round. 2. The elements indicating the women's physical properties are obesity, the size of upper part, front shape, side shape, shoulder and back shape, perpendicular size and lower part length, body shape. 3. The Chinese are categorized by three factors. Normal shape which is not both fat and skinny, records the highest in the ranking.

• 한국의류학회지
• /
• 제45권1호
• /
• pp.1-16
• /
• 2021

This study classified short adult male body types and identified characteristics by body type according to Size Korea's 7th human system measurement data for men in their 20s to 60s. There were four body types for short adult males. Type 1 was a 'short bird legs-normal body shape' with an average body size, low body height, short torso length, thin legs, and no sagging shoulders. Type 2 was a 'short torso thin body' with a small body size, a slim body, a high body height, a short torso length and no sagging shoulders. Type 3 was a 'thick leg-overweight body shape' with a large body size, thick legs, low body height, small shoulder length and obesity. Type 4 was a 'long bird legs-normal body' with a normal body size, high body height, thin legs, long torso and sagging shoulders. The development of clothing design and pattern reflecting the body shape characteristics of short adult males should be improved to fit clothing and suitability. It is necessary to increase the satisfaction of ready-to-wear for consumers with various body types by adding the size for shorter men through a subdivision of the ready-made size system.

• 건축역사연구
• /
• 제24권6호
• /
• pp.57-66
• /
• 2015

As Sri Lanka Stupa had been affected by Indian stupa directly, understanding Sri Lanka Stupa is important to know about the flow of Buddhist Art History, which is showing the variation of Initial Buddhist stupa. Due to invasions and disasters, all Sri Lanka's Stupa collapsed and became random mound. After restoration works, Stupa shape changed dramatically from the Initial shape to Existing shape. Since it is hard to find out how Initial stupas were like, Sanchi Stupa needed to be an example for the comparative study as an Initial shape. Sri Lanka Stupa have Square foundation and 3 Basal rings that are supporting the Main Dome. Entrances are on all 4 sides, Railing and Torana(gate) has never found in Sri Lanka stupa. Sri Lanka stupa has been classified with the shape of Dome into 6~8 types according to "Vijayanta Potha", the Ancient Buddhist Description, and described by several researchers confusingly. With the inconvenience of using unfamiliar words and irrational gap between the Initial Sri Lanka stupa and Existing Sri Lanka stupa, proposing new classification of Sri Lanka Stupa is necessary. Existing Sri Lanka Stupa can be classified into 4 types : which is (1)Bell type, (2)Pot type, (3)Mound type, (4)Bubble type. This suggestion is for further studies to use Easier and shorter words to describe the types and make it reasonable to use, since the current classification includes 3 stupa types even there is no case for any of them. Restrict Stupa Classifications within existing Sri Lanka Stupa is needed because the current classification had been continued for hundreds of years without any adjustments. Bell type is mainly located in Anuradhapura. Pot type and Mound type is only found in limited area, and Bubble type is located in most area of Sri Lanka.

• 응용통계연구
• /
• 제37권1호
• /
• pp.73-86
• /
• 2024

평가지표와 같은 수치형 자료의 경우 수치 형태보다 엑셀(Excel)의 방사형 차트 형태로 나타내 시각적으로 표현하면 정보 전달에 더욱 효과적일 것이다. 그러나 개체가 많은 경우 시각적으로 판별하거나 분류하는 것이 쉽지 않다. 이럴 경우 각 개체에 대해 방사형 차트를 이용하여 형상화 시킨 후, 형상의 정보를 대표할 수 있는 형상점을 찾고 형상좌표로 변환해 형상분석을 적용하여 분류 및 판별하는 방법을 알아보고자 한다. 형상분석을 이용하기 위해 주로 분석자의 주관으로 형상점을 얻고 임의의 좌표공간을 생성시켜 좌표를 얻곤 했다. 방사형 차트는 해당 개체의 특징을 나타내는 변수의 개수만큼 형상점이 생기게 되고 이를 선으로 이은 것은 하나의 형상으로 여겨진다. 따라서 중심을 원점으로 두고 2차원 공간으로 정의를 내린 후, X축과 각 특징을 나타내는 축이 이루는 각에 대해 삼각함수를 적용해 형상좌표를 추출해낸다. 변수의 개수가 많아 형상의 모양이 복잡해질 경우 방사형 차트를 이용해 시각화하더라도 쉽게 파악하기 어렵다. 독립성을 보장할 수 없는 변수들에 대해 주성분 분석(PCA)을 실시하여 시각적으로 효과적인 형상을 만든다. PCA를 실시하기 전과 후의 형상에 대해 전통적 판별분석, 서포트벡터머신(support vector machine; SVM), 인공신경망(artificial neural network; ANN)의 기법을 적용시켜 분류표와 분류율을 확인한다. 또한 GPA (generalized procrustes analysis) 적합좌표, 북스테인좌표 2가지 좌표에 대한 판별의 차이를 비교한다. 북스테인좌표의 경우 기저 형상점을 중심으로 형상의 위치와 회전, 척도를 변환한 좌표로써, 분류율에 대해 GPA 형상좌표보다 더 높은 결과를 보이고 있다. 북스테인좌표의 경우 여러 군집 간의 형상을 비교하는데 유용하게 활용된다.

• Transactions on Control, Automation and Systems Engineering
• /
• 제2권3호
• /
• pp.182-188
• /
• 2000

High-frequency electric resistance welding (HERW) technique is one of the most productive manufacturing method currently available for pipe and tube production because of its high welding speed. In this process, a heat input is controlled by skilled operators observing color and shape of bead but such a manual control can not provide reliability and stability required for manufacturing pipes of high grade quality because of a variety of bead shapes and noisy environment. In this paper, in an effort to provide reliable quality inspection, we propose a neural network-based method for classification of bead shape. The proposed method utilizes the structure of Kohonen network and is designed to learn the skill of the expert operators and to provide a good solution to classify bead shapes according to their welding conditions. This proposed method is implemented on the real pipe manufacturing process, and a series of experiments are performed to show its effectiveness.

• 한국멀티미디어학회논문지
• /
• 제22권8호
• /
• pp.852-859
• /
• 2019

With the development of IT technology and smart devices, various applications utilizing image information are being developed. In order to provide an intuitive interface for pronunciation recognition, there is a growing need for research on pronunciation recognition using mouth feature values. In this paper, we propose a system to distinguish Korean vowel pronunciations by detecting feature points of lips region in images and applying Bayesian based learning model. The proposed system implements the recognition system based on Bayes' theorem, so that it is possible to improve the accuracy of speech recognition by accumulating input data regardless of whether it is speaker independent or dependent on small amount of learning data. Experimental results show that it is possible to effectively distinguish Korean vowels as a result of applying probability based Bayesian classification using only visual information such as mouth shape features.