• Journal of Korean Home Economics Education Association
• /
• v.18 no.1 s.39
• /
• pp.113-125
• /
• 2006

The purpose of this study was to examine the effects of perception of body size on actual clothing style in middle school girls. To achieve this, this study analyzed self-perception of body size, aspired clothing style, and actual clothing style. By classifying groups into thin and thick, the difference in clothing style according to groups was also analyzed. Subjects of this study were middle school girls in Gwangju and 219 responses were collected from real body measurement and questionnaires. WIN SPSS+10.0 package was used to obtain results. Results are as follows: 1. For the self-perception of body size, middle school girls perceived much thicker in the lower body than the upper body. And they were unsatisfactory about the lower body which was perceived thick. 2. In the correlation of actual and aspired clothing style of middle school girls, they wore a aspired clothing style actually. Their actual or aspired upper clothing style was to cover the skin, exposing or covering a body silhouette. Their lower clothing style was a slacks type that covers a body silhouette and the skin. 3. In selecting actual clothing styles, middle school girls were somewhat affected by self-perceived body size. But they did not prefer the clothing styles perceived thick in girth or big in width in exposing the skin or a body silhouette. On the other hand, as it was perceived long, wearing was increased. frequently wore the upper and lower clothing styles of exposing the skin or a body silhouette than the thick group. But both groups wore the clothing styles of covering the skin or a body silhouette regardless of their thinness and thickness. And when wearing the clothing style of exposing neck and shoulder, middle school girls considered actual body size more than self-perceived size. On the other hand, when wearing the clothing style of exposing arms and silhouette by fitted legs, they considered self-perceived body size more.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.960-966
• /
• 2009

A manifold is used to represent a relationship between high-dimensional data samples in low-dimensional space. In human pose estimation, it is created in low-dimensional space for processing image and 3D body configuration data. Manifold learning is to build a manifold. But it is vulnerable to silhouette variations. Such silhouette variations are occurred due to view-change, person-change, distance-change, and noises. Representing silhouette variations in a single manifold is impossible. In this paper, we focus a silhouette variation problem occurred by view-change. In previous view invariant pose estimation methods based on manifold learning, there were two ways. One is modeling manifolds for all view points. The other is to extract view factors from mapping functions. But these methods do not support one by one mapping for silhouettes and corresponding body configurations because of unsupervised learning. Modeling manifold and extracting view factors are very complex. So we propose a method based on triple manifolds. These are view manifold, pose manifold, and body configuration manifold. In order to build manifolds, we employ biased manifold learning. After building manifolds, we learn mapping functions among spaces (2D image space, pose manifold space, view manifold space, body configuration manifold space, 3D body configuration space). In our experiments, we could estimate various body poses from 24 view points.

• Journal of the Korea Computer Graphics Society
• /
• v.8 no.2
• /
• pp.1-7
• /
• 2002

The fast extraction of the silhouettes of a model is very useful for many applications in computer graphics and animation. In this paper, we present an efficient algorithm to compute a sequence of perspective silhouettes for a polyhedral model from a moving viewpoint. The viewpoint is assumed to move along a trajectory q(t), which is a space curve of a time parameter t. Then, we can compute the time-intervals for each edge of the model to be contained in the silhouette by two major computations: (i) intersecting q(t) with two planes and (ii) a number of dot products. If q(t) is a curve of degree n, then there are at most of n + 1 time-intervals for an edge to be in a silhouette. For each time point $t_i$ we can extract silhouette edges by searching the intervals containing $t_i$ among the computed intervals. For the efficient search, we propose two kinds of data structures for storing the intervals: an interval tree and an array. Our algorithm can be easily extended to compute the parallel silhouettes with minor modifications.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.28 no.11
• /
• pp.1426-1437
• /
• 2004

The study has an objective of providing the basic data for the bodice basic pattern that is highly appropriate after classifying the torso shapes of women in 60s. In order to classify the torso shape, 200 women in 60s that reside in Seoul were investigated for 52 tests. The factor analysis produced total of 6 factors. Factor 1 tended to be posture of upper part of torso and shape of shoulder. Factor 2 was an element of silhouette and Factor 3 was vertical size of lower part of torso and side silhouette. Factor 4 showed to be width and thickness of torso, Factor 5 was shape of neck, and Factor 6 appeared to be sagging of belly and buttocks. Therefore, it can be known that posture, silhouette, shape of neck and shoulder, sagging of belly and buttocks, and etc. are important factors for classification of the torso shape of women in 60s. Through a cluster analysis, each torso shape was classified into 4 types and each type showed information on size, shape, and posture clearly. Type 1 showed percentage of 24.2%, and values of height and weight showed to be average. Also, the body shape hardly had any curve with high shoulder at the Posture of upper body, and they had saggy stomach and buttocks. 43.5% of them were involved in Type 2 and they were short and overweighted. They were comparatively large in width compared to the height with no curves. Type 2 had the largest percentage and this can be said to be the special shape of women in 60s. People of Type 3 were short and overweighted just like Type 2 and all the sizes were similar to those of Type 2 or bigger. The posture is right posture and 21.7％ fall into this type and there is no body curve. This type is the shortest and most overweighted type, and it is a torso shape with right posture just like Type 4. Type 4 is a torso shape with tallest height and least weight. The percentage was the smallest(10.6％) and the width was smaller than any other type but the height was the tallest. The body curve is very clear and they have thin body but big buttocks so it can be said that the people of this type have the best silhouette. Type 2 that had the highest percentile is short and overweighted so it can be said that Type 2 is the representative torso shape of women in 60s.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.9
• /
• pp.136-143
• /
• 2013

In this paper, a algorithm to find joints of a small animal like a lizard from the multiple-view silhouette images is presented. The proposed algorithm is able to calculate the 3D coordinates so that the locomotion of the lizard is markerlessly reconstructed. The silhouette images of the lizard was obtained by a adaptive threshold algorithm. The skeleton image of the silhouette image was obtained by Zhang-Suen method. The back-bone line, head and tail point were detected with the A* search algorithm and the elimination of the ortho-diagonal connection algorithm. Shoulder joints and hip joints of a lizard were found by $3{\times}3$ masking of the thicked back-bone line. Foot points were obtained by morphology calculation. Finally elbow and knee joint were calculated by the ortho distance from the lines of foot points and shoulder/hip joint. The performance of the suggested algorithm was evaluated through the experiment of detecting joints of a small lizard.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.7 no.3
• /
• pp.181-188
• /
• 2005

This study attempted to investigate the plastic characteristics of cyber punk fashion with a focus on fashion in the cyber punk movies in order to inquire into how the influence of the cyber punk taking the lead in the spiritual culture and way of life of the humankind in the 21th century would be expressed in fashion. For this purpose, it sought to analyze the beauty of new fashion creating the cyber environment and identify its contemporary meaning. An attempt was made to investigate the image of cyber punk fashion with a focus on fashion expressed in the cyber punk movies. As a result, the following findings were obtained: First, the image of cyber punk fashion expressed in the cyber punk movies was simplicity, which was to express the modest silhouette and details exclusive of decoration. In addition to clean and smooth gloss, it contained the modest image of resistance', not 'revolt' by borrowing the partial motive and image from existing punk fashion. The change of cyber punk fashion into the characteristic of concise, smooth external appearance brought about the restraint of its image and symbolism as well as its plastic characteristic. Second, it was characterized by the Eroticism nature of emphasizing the body line while expressing the future and modest image or exposing the body. Cyber punk fashion expressed the avant-garde image by using materials that gave a mysterious and future feelings, as well as unsymmetrical silhouette, the slit of body-conscious line, coarse cutting, the method of do-constructing and reconstructing the silhouette, the method of applying diverse underwears such as corset, brassiere and the like. Third, cyber punk fashion was marked by the nature of mined sex. It had the masculine image by using the black color containing the image of masculinity and resistance in female clothing and expressing the suit, coat and military looks giving an masculine impression. And it expressed the image of mixed sexes with the masculine image in male clothing by borrowing feminine images such as body-conscious line, widely cut neckline, floral decoration, leggings and the like. Fourth, cyber punk fashion was marked by naturalness. It was expressed as clothing made from silhouette, knit, cotton and the like in the atmosphere expressing love, comfortableness and truth. This contained the image of naturalness, a return to the primitive, that human being wanted to return to their original figure in the future element. The cyber punk movie may contain a dismal, gloomy future image on the whole, which can be overcome, and shows the possibility that it may grow into the alternative culture, not the revolting culture. The movie of 'The Fifth Element' demonstrates the meaning and role that shows the bright future image. It is thought that designers should make efforts for cyber punk fashion to perform its role in changing the gloomy future image into the bright image of society

• The Research Journal of the Costume Culture
• /
• v.4 no.2
• /
• pp.247-263
• /
• 1996

This study focuses on a comparative study of 1960s'retro look mode in terms of the past and present in order to find out in detail how it in the past is readjusted after it was appeared in the present. For such a study, in the first place the contents of the dress and its ornament of a retro-look fashion was refined through some literature, and then, some works of the dress and its ornament of a retro-look fashion was refinded through some literature, and then, some works of eh dress and its ornament revived in 1960's mode were analysed, based on some fashion magazines at home and abroad like Bazaar, Fashion etc News in 1990s. After 1960s'retro-look mode which reappeared in 1990s was researched in terms of silhouette, detail, texture, color, and pattern, differences between those tow periods of 1960s and 1990s and their causes are summarized as follows: 1. In the aspect of silhouette, it appears that the silhouette in 1960s is that of somewhat stiff, charming image in which Body is excluded and the silhouette in 1990s is that of an soft, feminie image in which Body is emphasized. It was understood that the cause of such a delicate difference comes from the influences of the change in aesthetic senses or awareness, naturalism and neo-feminism. 2. In the aspect of detail, it appears that the detail in 1990s is of an attempt to express in diverse images, compared to that in 1960s, and new images are created new image in 1990s by means of presenting entirely ill-matched images. The major cause of that is because of Antistandard fashion. 3. In the aspect of textures, it appears that a great feature is that the texture in 1990s is of that introduced, being changed in natural and high-class looks, compared to that of 1960s. It was reviewed that the major cause of this is because of a result from the influence of naturalism and the technical growth in various fields which has brought the development of dress material. 4. In the aspect of color, it appears that the color in 1990s is of an image of primary color which is far more sensual and feminie than that of 1960s. It was studied that the major cause of ti comes from the influence of neo-feminism, etc. 5. In the aspect of pattern, it appears that the pattern in 1990s is of that of symbolism, transposition, and the ecletic feature of various modes which appear more deeply than that of 1960s. It was studied that the major cause of such changes is because of a trend of postmodernism which has brought the change of the spiritual structure different from that in the age of modernism. In conclusion, it was understood that the retro-look fashion is of an expression technic of dress and its ornament in that o dress in the pst is simply imitate, but new reconstitution is done by using the elements in the past. at the same time, ti was clarified that even though the elements in the past are revived as they were, dress and its ornament is governed by the social and cultural environments of he day, and with this proof it can be said that the fashion in each age is of a reflection of social phenomena of that age.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.93-94
• /
• 2013

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.460-463
• /
• 2003

본 논문은 프리미티브 모델을 바탕으로 윤곽선 추출하여 효율적으로 홀 채워서 결과 영상의 질과 속도를 향상시키는 알고리즘을 제시한다. 이 알고리즘은 입력 영상에서 뷰의 위치와 방향이 바뀌어 홀이 발생하면 그 홀을 동일 프리미티브의 윤곽선을 이용하여 프리미티브 내의 영상 정보만을 이용하므로 이질감이 작고 홀 주위의 모든 점들의 영상 정보를 이용하여 결과 영상의 질을 향상 시켰다.