• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.507-511
• /
• 2007

기존의 얼굴 인식 기술은 얼굴 검출과 얼굴 인식이라는 두 분야로 나뉘며, 얼굴 검출 기술은 주로 얼굴 인식을 위한 전처리 단계로 이용되었다. 이러한 얼굴 검출 기술은 방대한 양의 사진 콘텐츠를 분류하는 것에도 이용될 수 있다. 얼굴 검출 기술을 통해 사람이 있는 경우 인물 사진, 없는 경우 풍경 사진으로 분류한다. 그러나 기존의 얼굴 검출 기술만으로는 정확성이 떨어진다. 이를 보완하기 위해 본 논문에서는 사진의 구조 단순도 알고리즘을 제안 한다. 구조 단순도는 사진의 색상 구도의 단순비율을 의미하며, 일반적으로 인물 사진일 때 작은 값을 풍경 사진일 때 큰 값을 갖는다. 제안 방법의 유용성을 검증하기 위해 인물 사진 250장, 풍경 사진 250장을 이용하여 분류 실험을 하였다. 얼굴 검출 기술만을 이용한 실험은 66%의 정확성을 나타낸 반면 얼굴 검출 기술과 구조 단순도를 이용한 실험은 74.6%를 나타내었다. 따라서 얼굴 검출 기술과 구조 단순도를 이용하면 효과적인 사진 분류를 할 수 있다.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• pp.397-408
• /
• 2003

The information about land use presents future development and vision being the basis of nation development; therefore, it is necessary to more active research that can detect wide land use and changes for the information and efficient management about land use. In this study, we wished to analyze effectively land use changes to Ansan city that is fast changing land use by the latest national land development and urbanization. this study executed land-cover classification using 4 year's Landsat TM images including Ansan city, and efficiently could manage the result of land-cover changes through Arc/Info GRID analysis. Especially, by using change detection system that is developed in this research, we could variously detect land-cover changes, and query and search easily past land-cover changes of pixels that correspond to specific region.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.11 no.2
• /
• pp.49-57
• /
• 2007

In fingerprints, singular regions including core or delta points have different directional characteristics from non-singular regions. Generally, the ridges of singular regions change more abruptly than those of nonsingular areas, thus in order to effectively enhance fingerprint images regardless of region, local ridge curvature information needs to be used. In this paper, we present an improved Directional Filter Bank (DFB)-based fingerprint image enhancement method that effectively takes advantage of such ridge curvature information. The proposed method first decomposes a fingerprint image into 8 directional subbands using the DFB and then classifies the image into background, low curvature, and high curvature regions using the directional energy estimates calculated from the subbands. Thereafter, the weight values for directional subband processing are determined using classification information and directional energy estimates. Finally, the enhanced image is obtained by synthesizing the processed subbands. The experimental results show that the proposed approach is effective in enhancing both singular and non-singular regions.

• Imaging Science in Dentistry
• /
• v.37 no.1
• /
• pp.1-7
• /
• 2007

Fibro-osseous lesions are composed of connective tissue and varying amount of mineralized substances, which may be bony or cementum-like structures. It is necessary for oral radiologist to differentiate due to the tendency of these fibro-osseous lesions to show similar histopathologic appearances, while the management of each lesion is different. However we often encounter a little difficulty in judgement because there are some overlaps between concept of each lesions. So recently I suggest, we face a need to review basic concept and classification of several fibro-osseous jaw lesions. In this article, several fibre-osseous lesions, such as fibrous dysplasia, cemento-ossifying fibroma and cemento-osseous dysplasia, will be discussed basing on the review of literature. particular emphasis will be made on the nomenclature revision of WHO's classification in 1992.

• The Journal of Korean Medicine
• /
• v.33 no.4
• /
• pp.37-41
• /
• 2012

Objectives: This study was aimed to establish the clinical features of the patients suffering from hyperhidrosis, who are willing to visit Oriental clinics. Methods: Forty-six patients with primary hyperhidrosis were enrolled in this study classification, body part of perspiration and its severity, and constitutional differentiation were analyzed. Results: 85.1% of patients were 10 to 39 years old. The body part most complained of hyperhidrosis was the hands and feet at 50%. The portion of Teaeumin, Soumin, and Soyangin was 56.6% 21.1%, and 21.7% respectively. Soumin specifically showed a higher frequency of palmar and plantar hyperhidrosis as 90%. The average score of symptoms was $5.1{\pm}1.7$ by a 10-point self- reporting numeric rating scale (NRS). No statistical difference of NRS score was observed regarding gender, Sasang classification, or hyperhidrosis region. Conclusions: This study provides an overview of hyperhidrosis patients visiting an Oriental clinic, and will be helpful in establishing a strategy for the Korean medicine (KM)-based therapeutic development.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.34 no.2
• /
• pp.30-34
• /
• 2011

Variable precision rough set models have been successfully applied to problems whose domains are discrete values. However, there are many situations where discrete data is not available. When it comes to the problems with interval values, no variable precision rough set model has been proposed. In this paper, we propose a variable precision rough set model for interval values in which classification errors are allowed in determining if two intervals are same. To build the model, we define equivalence class, upper approximation, lower approximation, and boundary region. Then, we check if each of 11 characteristics on approximation that works in Pawlak's rough set model is valid for the proposed model or not.

• Journal of Korean Port Research
• /
• v.14 no.2
• /
• pp.143-154
• /
• 2000

In port management, the scale of facilities and port layouts are major factors characterizing the port, which influence port economics and productivities continuously through the port operation. Grouping ports in certain region by their characteristics could be used as the principal informations to establish national policy for port development or investment and also to analyze the competitiveness between ports. Currently Korean ports are divided into two groups such as the local port and the designated port containing foreign trade port and coastal port under the Korean port law. These divisions seem to be used for port administration as the matter of convenience but some qualitative grouping is needed for research of port problems. In this paper, 20 major Korean ports were clustered by the similar characteristics using Fuzzy C-Means and found to be classified 8 qualitative groups.

• Journal of the Korean Institute of Navigation
• /
• v.24 no.4
• /
• pp.247-254
• /
• 2000

Grouping ports in certain region by their characteristics could be used as the principal informations to establish national policy for port development or investment and also to analyze the competitiveness among ports. Currently Korean ports are divided into two groups such as the local port and the designated Port containing foreign trade port and coastal port under the Korean Port Act. This classification seems to be used for port administration as the matter of convenience but some qualitative grouping is needed for research of port-related matters. The aim of this paper is to cluster 28 foreign trade ports as per the similar characteristics by Hard C-Means and to analyze the results of this clustering.

• Journal of Korea Multimedia Society
• /
• v.22 no.8
• /
• 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.

• Journal of KIBIM
• /
• v.10 no.1
• /
• pp.23-29
• /
• 2020

The vacant houses commonly observed in urban aging are considered to be representative signs of urban decline. Vacant houses are themselves vulnerable to security, and in particular, they are exposed to disasters due to poor management, which can accelerate the decline of the area. This study is to classify the area and analyze the causes and characteristics of the occurrence of vacant houses by type based on the data through the survey on the vacant houses in Incheon. This research analyze vacant house data survey so to characterized and categorized types of vacant houses. The criteria of vacant houses analysis are population density, population growth, aging extent. In conclusion there are four types of region in Incheon area according to housing types, hazard classes, building age and building areas. Type A is inner city, type B is mixed, type C is expandable and type D is unsular types.