• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.293-294
• /
• 2016

스마트폰, 블랙박스, CCTV 등을 통해 다양하고 방대한 영상 데이터가 발생하고 있다. 그중에서 사람의 얼굴 영상을 통해 개인을 인식 및 식별하고 감정 상태를 분석하려는 다양한 연구가 진행되고 있다. 본 논문에서는 디지털영상처리 분야에서 널리 사용되고 있는 SIFT알고리즘을 이용하여, 얼굴영상에 대한 특징점을 추출하고 이를 기반으로 성별, 나이 및 기초적인 감정 상태를 분류할 수 있는 시스템을 제안한다.

• Journal of Korea Multimedia Society
• /
• v.19 no.6
• /
• pp.1014-1023
• /
• 2016

In this study, we presented a method for non-square Differential LBP operation that can well describe the micro pattern in the horizontal and vertical component. We proposed a way to represent a LBP operation with various direction components as well as the diagonal component. In order to verify the validity of the proposed operation, Differential LBP was investigated with respect to accuracy, sensitivity, and specificity for the classification of facial expression. In accuracy comparison proposed LBP operation obtains better results than Square LBP and LBP-CS operations. Also, Proposed Differential LBP gets better results than previous two methods in the sensitivity and specificity indicators 'Neutral', 'Happiness', 'Surprise', and 'Anger' and excellence Differential LBP was confirmed.

• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.403-411
• /
• 2022

Appearance management is evolving as a means of self-expression or as a way of expressing one's individuality. In particular, hairstyle is the most important part of a person's appearance and accounts for 70% of the appearance. Improving people's appearance by changing their hairstyle gives them confidence. Among them, the fringe hair style plays an important role in determining the first impression and reflects the trend. Fringe is shorter and simpler than general hair treatment, but even these small treatments have the effect of changing the impression, so women are trying to transform into a fringe hair style. A previous study was conducted on four lines classified: round, heart, square, and triangular. In this study, we added them to define 5 hairlines and created them by combining each hairline. that have been produced 5 fringe hair styles that suit the shape of the face. It is expected that the results of this study will be used as educational materials for hair line and fringe hair styles in the field, contributing to the beauty industry.

• Smart Media Journal
• /
• v.11 no.6
• /
• pp.18-29
• /
• 2022

This study proposes an evaluation item model for the avatar expression process, satisfaction and self-identification for each expression element in order to investigate the expression attributes on the influence on the user in setting the avatar. The evaluation of avatar expression method was composed of self-identification and satisfaction by ease of expression and expression elements on the avatar production and expression process. To evaluate the proposed evaluation model, 17 people participated in the experiment. As a result, it was found that most of the participants had a high level of understanding of the production process, and the more diverse the expression elements, the higher the satisfaction with the avatar expression process. Hair shape and face shape were the most important expression factors, and clothes and overall harmony was the most concerned facotrs. Most of them tried to express themselves as realistically as possible. However, in self-identification, there was no significant correlation between expression and production process. In this study identify the decision-making factors that appear in the avatar expression process, the direction in which satisfaction can be formed, and the factors that affect self-identification. In addition, it will be a basic study on how avatars have a lasting influence on users in the future.

• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1478-1484
• /
• 2004

This paper presents a method that controls facial expression in realtime of 3D avatar by having the user select a sequence of facial expressions in the space of facial expressions. The space of expression is created from about 2400 frames of facial expressions. To represent the state of each expression, we use the distance matrix that represents the distances between pairs of feature points on the face. The set of distance matrices is used as the space of expressions. Facial expression of 3D avatar is controled in real time as the user navigates the space. To help this process, we visualized the space of expressions in 2D space by using the Principal Component Analysis(PCA) projection. To see how effective this system is, we had users control facial expressions of 3D avatar by using the system. This paper evaluates the results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.77-84
• /
• 2012

Face classification has wide applications in intelligent video surveillance, content retrieval, robot vision, and human-machine interface. Pose and expression changes, and arbitrary illumination are typical problems for face recognition. When the face is captured at a distance, the image quality is often degraded by blurring and noise corruption. This paper investigates the efficacy of multi-classifier decision level fusion for face classification based on the photon-counting linear discriminant analysis with two different cost functions: Euclidean distance and negative normalized correlation. Decision level fusion comprises three stages: cost normalization, cost validation, and fusion rules. First, the costs are normalized into the uniform range and then, candidate costs are selected during validation. Three fusion rules are employed: minimum, average, and majority-voting rules. In the experiments, unfocusing and motion blurs are rendered to simulate the effects of the long distance environments. It will be shown that the decision-level fusion scheme provides better results than the single classifier.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.14 no.3
• /
• pp.37-49
• /
• 2012

The purpose of this study is to provide basic data of dress design by researching three-dimensional decorative techniques representing flowers, a popular motif in dress design. This study analyzed 44 dresses that were presented in Valentino collection. The result of this study is as follows: First, the detailing expression method can show various patterns and colors through embroidery technique, sub-materials, and bonding techniques in embroidery, beads flower, and ribbon flowers. Second, the fabric flower technique expressed flower image in three-dimension in more various images than do either the ribbon or beads flower technique. Fabric flowers are mostly made from the same material as dresses. The expression technique of fabric flower is classified into the following three classifications: 1) A technique underlying a flower image with one, two and three large flowers, 2) a technique decorating a large area with a number of an identical motif, and 3) a technique highlighting a part of the body or design line by attracting eyes to one point, creating a corsage decorated where a designer wants to emphasize. Third, a silhouette technique realizes a flower image with a silhouette of a dress like sculpted structure and it is thus used less than a detailing expression technique. A flower image is expressed by making use of body lines or emphasizing the face. Finally, flower images on a dress were realized as a full blossomed flower, through visually streamlined shapes and curved lines.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.117-122
• /
• 2005

This paper proposes an algorithm for Facial Characteristic Point(FCP) extraction. The FCP plays an important role in expression representation for face animation, avatar mimic or facial expression recognition. Conventional algorithms extract the FCP with an expensive motion capture device or by using markers, which give an inconvenience or a psychological load to experimental person. However, the proposed algorithm solves the problems by using only image processing. For the efficient FCP extraction, we analyze and improve the conventional algorithms detecting facial components, which are basis of the FCP extraction.

• Journal of the Korean Society of Costume
• /
• v.55 no.4 s.94
• /
• pp.29-37
• /
• 2005

Beauty Art is an act which makes a face beautiful using various methods such as permanent, manicure and make-up. Recently, Beauty Art is recognized as the personal culture expressing the value of beauty and spirit. Therefore, there are growing interests in the comprehensive study of Beauty Art nor only from the beauty industries but also from academia, because Beauty Art is the high value-added field and Is recognized as a style of the dress. The purpose of this study is to open a new view to understand the Nail Art as a fold of experimental plastic art. The arctic expression is added to Beauty Art to develop it from the routine technique of the make-up and hairstyling to creative art. Assemblage is adopted to provide Beauty Art with fine harmonious expression which develop Nail Art into interesting and unique art area. Assemblage meaning compounding or collection is a technique through which three-dimension is added to two-dimension paintings, and which is an expression of an art work by recollection of miscellaneous articles or waste materials. Assemblage is a term which Jean Dubuffet coioned first in order to differentiate collage used by Picaso or Braque. Here, I present Nail Art Designs which applied Jean Dubuffet's works focusing on Automaticity and Happenstantial phenomena of materials, Materialization, and Directness. These features are characteristics of Assemblage which basic frameworks are fantastic collection, accumulation, constructive collection, and object collection.

• The Research Journal of the Costume Culture
• /
• v.9 no.3
• /
• pp.375-388
• /
• 2001

This study looks into the appearances and contents of undercloths advertisements by analyzing them appeared in women\`s magazines of Korea, which are , and published between 1965 and 1999 mainly targeting the women at the age of 20s through 40s. This study leads to the following conclusions : 1. Most of advertisements use 1 or 2 pages of the magazines with colored pictures. 2. The most frequently advertised underclothes is brassieres and white and pastel are dominant colors. Also, spandex and cotton are the most frequently appeared fabrics in the advertisement. 3. Professional Korean female models in twenties are the most favored choice for those underclothes advertisements and those models dominantly face their fore part with showing the body parts higher than their knees. Solo model appear in most of the advertisements and independent appearance is dominant. 4. In the visual expression of the advertisements explicitly show the products for visual expression, whereas verbal expressions mostly emphasize the benefits to be obtained from the underclothes advertised. 5. Advertisement appeals are mainly base on readers\` reason rather than sensibility.