• Journal of the Korean housing association
• /
• v.20 no.1
• /
• pp.37-44
• /
• 2009

Sleep has big influence on our life, for example productivity, character formation of babies, mortality and the people who suffered from sleep problem are also diverse. Therefore, indoor environmental supports for good sleep, might be different with the situation and need of respective person. The objectives of this study are: 1) to investigate the current bedroom condition, sleep problem, and life pattern of Korean. 2) to classify Korean into several groups and explain their characteristics relevant to sleep, in order to understand Korean's need for good sleep. The questionnaire was sent out to Seoul and its environs in Jan.$\sim$Feb. 2008, and total of 702 questionnaires were collected. The research on the bedroom condition was conducted around perceived influence of environmental factors, opening and closing of the door, cooling and heating strategy, clo value during sleep, bedding type, lighting, sharing bedroom. People are divided into 6 groups by 8 factors, and 5 groups could be seen that they need some management for good sleep because of their sleep problem.

• Annual Conference on Human and Language Technology
• /
• 1994.11a
• /
• pp.201-206
• /
• 1994

문서 인식 시스템의 성능을 저하시키는 가장 큰 원인 중의 하나로 문자 분할 오류를 들 수 있는데 보다 우수한 성능의 문서 인식 시스템 개발을 위해서는 정확한 문자 분할 방법이 절실히 요구된다. 기존의 문자 분할에 관한 연구들은 이진 영상을 대상으로 함으로써 접촉되거나 겹치는 문자의 경계 부분에서 문자 분할에 유용한 정보들을 잃어 문자 분할 오류를 초래할 수 있다. 하지만 명도 영상을 분석해 보면 문자의 접촉 부분에서 주로 나타나는 지형적 특징이 있으며, 문자 경계에서 명도값이 변하는 것을 관찰할 수 있는데 이와같은 명도 영상의 정보를 사용하면 보다 효과적으로 문자를 분할할 수 있을 것으로 판단된다. 본 연구에서는 이러한 점에 착안하여 명도 영상으로부터 지형적 특징을 추출하고 다단계 그래프 탐색 방법을 이용하여 명도값을 추적함으로써 비선형 문자 경계를 찾는 새로운 문자 분할 방법을 제안한다. 제안된 방법은 명도 문자열 영상을 입력으로 받아 명도 영상의 투영값과 명도 영상으로부터 추출된 지형적 특성을 이용하여 문자 분할 영역을 결정하고 문자 분할 영역내에서 다단계 그래프 탐색에 의한 비선형 문자 분할 경로를 찾는다. 그리고 문자 인식기와 결항하여 최종 문자 분할 위치를 확정하는 인식 결과를 이용한 문자 분할을 수행함으로써 문자 분할 위치 및 문자 인식 결과를 확정한다. 다양한 문서에 대한 실험 결과 제안된 방법이 이진 정보만을 사용하는 방법보다 접촉 혹은 겹친 문자 분할에 매우 효과적임을 알 수 있었다.

• Journal of the Korean Society of Costume
• /
• v.13
• /
• pp.123-134
• /
• 1989

The purpose of this study was to identify the predictable variables of criteria on clothing selection. Relationships among criteria on clothing selection, psychological variable, lifestyle variable, and demographic variable were tested by Pearsons' correlation coefficients and One-way ANOVA. The predictors of criteria on clothing selection were identified by Regression. The consumers were classified into several benefit-segments by criteria on clothing selection, and then, the character of each segment were identified by Multiple Discriminant Analysis. Data was obtained from 593 women living in Pusan by self-administered questionnaires. The results of the study were as follows; 1. Relationship between criteria on clothing selection and relative variables. 1) The important variables to criteria on clothing selection were "down-to-earth-sophisticated", "traditional-morden", "conventional-different", "conscientious-expendient", need for exhibitionism, need for sex, fashion / appearance. 2) The important factor of clothing selection criteria was comfort and it has significant difference among ages. 3) The higher of social-economic status have the more appearance-oriented selection. 2. Predictors of criteria on clothing selection. There were several important predictors of criteria on clothing selection like lifestyle, need, and self-image. Especially, fashion / appearance in lifestyle variable was very important. 3. Segmentation by the criteria on clothing selection. There are four groups Classified by the criteria on clothing selection, that is practical-oriented group, appearance-oriented group, practical and appearance-oriented group, and indifference group. The significant discriminative variables were Fashion / appearance factor, need for exhibitionism, and need for sex. The result of this study can be used for a enterprise to analysis the consumer and to build the strategy of advertisement clothing.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.357-364
• /
• 2005

In this paper, we propose an accurate and fast keyword spotting system for searching user-specified keyword in Hangul document images by using two-level image-to-image matching. The system is composed of character segmentation, creating a query image, feature extraction, and matching procedure. Two different feature vectors are used in the matching procedure. An experiment using 1600 Hangul word images from 8 document images, downloaded from the website of Korea Information Science Society, demonstrates that the proposed system is superior to conventional image-based document retrieval systems.

• Journal of Satellite, Information and Communications
• /
• v.11 no.2
• /
• pp.14-17
• /
• 2016

This paper describes the implementation of automatic number-braille converter based on image processing for the blind people. The algorithm is consists of four main steps. First step is binary image conversion of the input image obtained by the camera. the second step is segmentation operation by means of dilation and labelling of the character. Next step is calculation of cross-correlation between segmented text image and pre-defined text-pattern image. The final step is generation of brail output which is relevant to input image. The computer simulation result was showing 91.8% correct conversion rate for arabian numbers which is printed in A4-sheet and practical possibility was also confirmed by using implemented automatic number-braille converter based on DSP image processing board.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.792-795
• /
• 2006

In this paper, we propose a method of vehicle license plate recognition on PDA for illegal parking car regulation. we classified three kinds of vehicle license plates being used down to date since the introduction of each vehicle license Plate using features of each one. And we recognized vehicle license plates segmentation the AreaName, the AreaCode, the TypeCharacter and the Numbers. A 88.7% recognition accuracy was obtained through the experiment of the proposed vehicle license plate recognition system using the obtained images of PDA.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.5
• /
• pp.887-894
• /
• 2006

This paper proposes a new method that detects the intersection points of handwritten Hangul strokes using run-length. The method firstly finds the strokes' width of handwritten Hangul characters using both horizontal and vertical run-lengths, secondly extracts horizontal and vertical strokes of a character utilizing the strokes' width, and finally detects the intersection points of the strokes exploiting horizontal and vertical strokes. The analysis of both the horizontal and the vertical strokes doesn't use the strokes' angles but both the strokes' width and the changes of the run-lengths. The intersection points of the strokes become the candidated parts for phoneme segmentation, which is one of main techniques for off-line handwritten Hangul recognition. The segmented strokes represent the feature for handwritten Hangul recognition.

• The Research Journal of the Costume Culture
• /
• v.9 no.3
• /
• pp.357-374
• /
• 2001

This study analyzed the trends of fashion market in 15 branch stores of 3 major department stores in Seoul. The purposes of this study were to classify fashion zone and brands in each floor of the department stores, and to analyze the rate which a fashion brand was located department store. The results were as follows : 1. There were sundry goods on main floor, women\`s clothings on 2-4th floor, sports & golf wears and infants & children\`s clothings from 6th floor to the top in most department stores. 2. Lotte Chamshil branch had the largest number of fashion brands in it, the nest was Lotte Main store and followed by Hyundai Chunhoe branch, Shinsegae Gangnam branch, Hunndai Shinchun branch, Lotte Gangnam branch, Hyundai Main store, Hyundai Muyeuk-Center branch, and Lotte Youngdeungpo branch, etc. 3. The fashion categories of the Lotte Department stores were segmented as the Casuals (character, young, young basic, career, town, jean, city), Young worlds, Imported beautique, Madams, Designers(beautique), Intelligences, Unisex, Ladies formal wears, the Seasonables, and the Formals, Missy Careers. This was the most various fashion market segments among 3 major department stores. This store had 667 Women\`s fashion and Casual brands. The Chamshil branch and Main store were intensified the Casual & sundry goods on 5th floor. 4. The fashion categories of the Hundai Department stores were segmented as Women\`s wears, Women\`s casuals, Young-Adult, Young live, Women\`s former wears, Royal beautique and Young characters. It was less segmented than other Department stores. Total number of Women\`s fashion and casual brands were 471 brands. The market segmentation of fashion zone was well done at Chunho branch and Shinchun branch. It was intensified that Fashion sundry goods at Muyeuk-Center branch and The Women and Young fashion zone at Chunho branch. 5. The fashion categories of the Shinsaegae Department stores were segmented as Casuals (young, young character, X-, missy, career, character), Imported beautique, Designer\`s characters, Young basics, Elegance, Missy, Young weave, Original brands. This store had 304 Women\`s fashion and Casual brands. Shinsaegae has also developed it\`s own brand(PB items) and classified as the Original zone which differentiated it from other Departments. 6. The Deco was the most popular brand in the department stores, the next were Micha/Botticelli, and followed by Darks/System/lzzat Baba, Givy/Obzee/Lee won jae/Kim yeon Joo, and so on. The target of 6 out of 10 brands which were included in here were career women of age 20 to 30 ages. The price rate were from 200,000 won to 300,000 won.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.5 s.311
• /
• pp.89-100
• /
• 2006

The carotid intima-media thickness (IMT) is very important, because the severity of it is an independent predictor of transient cerebral ischemia, stroke, and coronary events such as myocardial infarction. The conventional image processing to measure the IMT has not been satisfactory, because the methods have relied on the manual section drawing and a regional segmentation by differential estimation. We propose a new image processing technology effective to extract features from the carotid artery image whose pixels have the directional vector properties with composed color distribution. The technique we presented here is not by differential variation but by verification of the layer properties of carotid artery image. Iterated vertical and horizontal analysis and segmentation of the IMT image show the vector characteristics. This new technique makes it possible to cluster the layers statistically, and to classify mathematical correlation between regions and resulting in correct measurements of thickness and its variation. The advantages and effectiveness of this approach are applicable to region process and character extraction of such a vector image.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.