• Title, Summary, Keyword: 실루엣

Search Result 207, Processing Time 0.049 seconds

Pattern Making Method and Design of Power Shoulder Jackets (파워 숄더 재킷의 디자인 및 패턴전개 방법)

  • Park, Sanghee;Lee, Eunhae
    • The Journal of the Korea Contents Association
    • /
    • v.13 no.7
    • /
    • pp.131-140
    • /
    • 2013
  • Power shoulder look is most noticeable trend in women's wear in the 09/10 season. Specially jackets with sharper angle and wider shoulder became the best item since then, and were chosen for must-have item by fashion directors. Jacket occupied 50% in power shoulder items. Its shoulder angle was from 0 to 30 degree but items with 15 degree stood out among them. There are three methods to make power shoulder look jackets; shoulder extension method with moving shoulder tip up and sleeve cap height, method of extension and cutting sleeve cap with shorten shoulder length, and method of extension and moving shoulder tip up in the sleeve with shoulder line like raglan sleeve. As a result, shoulder angle is higher, starting point of shoulder line is closer to side neck point and shoulder point is extender to outside for appearance and fit. In shoulder extension method, the arm hole line was drawn with care by matching joining shoulder seam and setting the sleeve into the arm hole. In sleeve cap transformation, it is desired that starting point shoulder angle is moved closely to side neck point. In case of the sleeve with shoulder line, it needs to consider enough ease of shoulder and upper arm. For making patterns of power shoulder look jacket, it need to consider arm hole line, shoulder length, shoulder point position, sleeve cap height and sleeve width with interpretation design facts. In this study, through the analysis clothing construction method of power shoulder jacket, it is of help to pattern making for various power shoulder design items.

Markerless Motion Capture Algorithm for Lizard Biomimetics (소형 도마뱀 운동 분석을 위한 마커리스 모션 캡쳐 알고리즘)

  • Kim, Chang Hoi;Kim, Tae Won;Shin, Ho Cheol;Lee, Heung Ho
    • 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.

High-resolution 3D Object Reconstruction using Multiple Cameras (다수의 카메라를 활용한 고해상도 3차원 객체 복원 시스템)

  • Hwang, Sung Soo;Yoo, Jisung;Kim, Hee-Dong;Kim, Sujung;Paeng, Kyunghyun;Kim, Seong Dae
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.50 no.10
    • /
    • pp.150-161
    • /
    • 2013
  • This paper presents a new system which produces high resolution 3D contents by capturing multiview images of an object using multiple cameras, and estimating geometric and texture information of the object from the captured images. Even though a variety of multiview image-based 3D reconstruction systems have been proposed, it was difficult to generate high resolution 3D contents because multiview image-based 3D reconstruction requires a large amount of memory and computation. In order to reduce computational complexity and memory size for 3D reconstruction, the proposed system predetermines the regions in input images where an object can exist to extract object boundaries fast. And for fast computation of a visual hull, the system represents silhouettes and 3D-2D projection/back-projection relations by chain codes and 1D homographies, respectively. The geometric data of the reconstructed object is compactly represented by a 3D segment-based data format which is called DoCube, and the 3D object is finally reconstructed after 3D mesh generation and texture mapping are performed. Experimental results show that the proposed system produces 3D object contents of $800{\times}800{\times}800$ resolution with a rate of 2.2 seconds per frame.

High-Quality Depth Map Generation of Humans in Monocular Videos (단안 영상에서 인간 오브젝트의 고품질 깊이 정보 생성 방법)

  • Lee, Jungjin;Lee, Sangwoo;Park, Jongjin;Noh, Junyong
    • Journal of The Korea Computer Graphics Society
    • /
    • v.20 no.2
    • /
    • pp.1-11
    • /
    • 2014
  • The quality of 2D-to-3D conversion depends on the accuracy of the assigned depth to scene objects. Manual depth painting for given objects is labor intensive as each frame is painted. Specifically, a human is one of the most challenging objects for a high-quality conversion, as a human body is an articulated figure and has many degrees of freedom (DOF). In addition, various styles of clothes, accessories, and hair create a very complex silhouette around the 2D human object. We propose an efficient method to estimate visually pleasing depths of a human at every frame in a monocular video. First, a 3D template model is matched to a person in a monocular video with a small number of specified user correspondences. Our pose estimation with sequential joint angular constraints reproduces a various range of human motions (i.e., spine bending) by allowing the utilization of a fully skinned 3D model with a large number of joints and DOFs. The initial depth of the 2D object in the video is assigned from the matched results, and then propagated toward areas where the depth is missing to produce a complete depth map. For the effective handling of the complex silhouettes and appearances, we introduce a partial depth propagation method based on color segmentation to ensure the detail of the results. We compared the result and depth maps painted by experienced artists. The comparison shows that our method produces viable depth maps of humans in monocular videos efficiently.

A Study on Desirable Breast Type of Women in Their Twenties Based on the Ratio of Breast in Works of Art and Cup Design According to Breast Type (미술작품의 유방 실루엣 비율에 근거한 20대 여성의 바람직한 유방형태와 유형별 컵 설계에 관한 연구)

  • Sohn, Boo Hyun;Kweon, Soo Ae
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.37 no.3
    • /
    • pp.280-291
    • /
    • 2013
  • This paper analyzes desirable breast types using measurements from 31 selected female subjects based on the ratio of breast in works of art and to design a brassiere cup design according to the breast type of 182 female subjects in their 20s. The subjects selected for this paper are somewhat larger than a previous study on aesthetically perfect breasts of foreigners according to chest breadth, center neck point to breast point, breast circumference, and breast volume. However, the aesthetic breasts of foreigners are larger than the subjects selected for this study according to chest depth, under-bust circumference, and bust point to bust point. Comparing various breasts types and aesthetic breasts, padding is necessary to complement the form of flat breasts to increase the volume and diameter. Brassiere cups for cone-shaped breasts should be designed to increase breast volume through an increase in nipple height. Hemisphere breasts should be designed to increase the overall volume-leaving diameter. Protrusion breasts should enhance the functions of aggregating and supporting without any increase or decrease of the breast volume. Drooping breasts require the ability to support a large volume to stabilize the breast. Subjects were selected depending on the ratio of breast silhouette as works of art and who have large breasts in disproportional to a slender trunk. Three items, the circumferential length of breast, height of the nipple, and the depth of inner breast using the anthropomorphic measurements of 182 subjects were measured through regression equations for breast volume. Breast volume = -394.86 + 27.52 ${\times}$ (the circumferential length of breast) + 18.73 ${\times}$ (height of the nipple) + 12.85 ${\times}$ (the depth of inner breast). Regression equations to extract the aesthetic breast volume in measurements irrelevant to breasts using the anthropomorphic measurements of 31 subjects were as follows. Aesthetic breast volume = -611.30 + 17.67 ${\times}$ (bust circumference) -24.29 ${\times}$ (under-bust circumference) + 16.31 ${\times}$ (neck point to breast point to waistline) + 22.83 ${\times}$ (bust breadth) + 12.22 ${\times}$ (waist depth) -8.34 ${\times}$ (interscye- front). This prediction equation is useful to develop a breast type brassiere pattern, complement breast enhancement surgery, or minimize the effect a mastectomy.

A Study on the Reflective Property of Trends in Fashion Shows - Focused on Three Designing Factor of the Silhouette, the Detail, the Color and the Fashion Image - (패션쇼의 트렌드 반영성(反映性)에 관(關)한 연구(硏究) - 실루엣, 디테일, 색상(色相), 패션 이미지 등(等) 4가지 디자인 요소(要素)를 중심(中心)으로 -)

  • Lee, Myung-Hee
    • Journal of Fashion Business
    • /
    • v.3 no.4
    • /
    • pp.147-160
    • /
    • 1999
  • This paper is intended to compare and analyze the fashion trends that were introduced in the recent shows, held abroad and in Korea, so as to investigate how well the designers in Taegu and Kyungbuk (TK) area are keeping up with the international vogue. The research has done, analyzing Pret-a-Porter in Paris and the three events held in the TK area in 1997 -The Taegu Collection, Kyungbuk Fashion Festival and Textile & Apparel Fair and using reference pictures and documentary records. In order to investigate the trends the research is divided by four groups which are the silhouette, the detail, the color and the Fashion image and has done with the help of three postgraduate students. The results are as follows. 1. The Silhouette The slim-line has the greatest importance in the silhouette analysis of the recent collections. Like Elongated and Fit & Flare, tight-fitting and female-line were also appeared quite a lot. Compared with foreign collection, Korean collections put the bigger importance on the slim-line. 2. The Detail The printings, using paintings and plant-logos had the large portion of the accessories in both foreign and Korean collections. Draw string and wrap style were also presented a lot. Especially, at the Korean collections, layerd, corsage, and craft accent were emphasized, too. As for the necklines the similarity was found over the four events considering. Camisole neckline and halter neck were presented the most, and bared top, Vneckline, boat and low-neck which can highlight the feminity were often appeared as well. Considering collars, tailored and peaked collars which are frequently used for the jackets, were usually shown at the collections. Like convertable, shirts, wing and Italian collar, the collars that can be applied for the sports wears were presented a lot. Virtually no variation of design was found in the sleeve analysis. While set-in-sleeve and sleeveless were found commonly, not so many ornaments were added to the sleeves. The ankle and knee length for the pants and skirts were common. Furthermore, including the micro-mini, showing extremely feminine style the mini-style had the 20% portion of the skirt-length. Unbalanced lengths, using bias-cut were presented quite a lot on the runways. Deep slit skirts, wide pants and irregular hem skirts were in vogue. On the runways of Paris, more than 21% of the design was the burmuda pants. 3. The Color Red and Blue were in vogue in the four collections considering. Sometimes, yellowish was combined in Korean collections. Black and pale tone were appeared to be in fashion also with light grayish, moderate and deep tone. 4. The Fashion image As for the fashion image, feminine-decorative trend amounted to the large percentage in korean collections. At the foreign collection feminine-decorative trend and feminine trend were predominant, then mannish trend and simple trend were apeared equally. The research shows that TK area and foreign collections are fairy similar, which means that the designers in TK area have been making their efforts to satisfy the clients who have the international minds. However, compared with foreign collections, TK collections were apprered to be strongly inclined to only a few trends. Consequently the season trends are not as diverse as the foreign trends, which cannot satisfy the fashion taste of the clients in TK area. The local designers should know the tendency and the taste of the clients and make the more efforts to read local clients' mind.

  • PDF

The Effect of Meta-Features of Multiclass Datasets on the Performance of Classification Algorithms (다중 클래스 데이터셋의 메타특징이 판별 알고리즘의 성능에 미치는 영향 연구)

  • Kim, Jeonghun;Kim, Min Yong;Kwon, Ohbyung
    • 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.