• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.1
• /
• pp.53-73
• /
• 2014

Given that emotion-based computing environment has grown recently, it is necessary to focus on emotional access and use of multimedia resources including images. The purpose of this study aims to identify the visual cues for emotion in images. In order to achieve it, this study selected five basic emotions such as love, happiness, sadness, fear, and anger and interviewed twenty participants to demonstrate the visual cues for emotions. A total of 620 visual cues mentioned by participants were collected from the interview results and coded according to five categories and 18 sub-categories for visual cues. Findings of this study showed that facial expressions, actions / behaviors, and syntactic features were found to be significant in terms of perceiving a specific emotion of the image. An individual emotion from visual cues demonstrated distinctive characteristics. The emotion of love showed a higher relation with visual cues such as actions and behaviors, and the happy emotion is substantially related to facial expressions. In addition, the sad emotion was found to be perceived primarily through actions and behaviors and the fear emotion is perceived considerably through facial expressions. The anger emotion is highly related to syntactic features such as lines, shapes, and sizes. Findings of this study implicated that emotional indexing could be effective when content-based features were considered in combination with concept-based features.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• Journal of the Korean Society of Fashion and Beauty
• /
• v.1 no.1 s.1
• /
• pp.65-78
• /
• 2003

This research is to provide practical help in learning hair and makeup illustration skills by presenting techniques for hair and makeup drawing; to serve efficient illustration education; and to enhance the status of beauty and contribute to artistic development. Hair style and makeup techniques include graphical one, pattern-centered one, one using pattern paper, simplifying one and mood one expressing image. Of them, this research made the illustrations to use cosmetics, color pencils and pastel based on the graphical technique. for each design of the illustrations, ethnic, sexy, natural, romantic and gorgeous images, which were considered to be appropriate to the graphical technique, were chosen by the researcher out of hair and makeup styles that appeared in the fashion magazines including Vogue, Gap, Mode et Mode from 2000 through 2001. In particular, they were chosen with focusing on basic styles. The summaries below were found with the experience of making illustrations. Various techniques and skills are required to express the ideas of hair and makeup styles. Of them, the graphical technique is very useful as the primary step to learn various techniques and improve drawing skills. First, the graphical technique may enable not only expressing what is desired to draw as is, but also accurately representing hair and makeup designs so as to convey objective expression. In this regard, it is a proper way to achieve its inherent purpose as conveyance of messages. Second, more accurate styling of hair and makeup is available through graphical expression, which helps understand related practical techniques. In addition, makeup illustration, which is expressed through direct makeup products and instruments, may serve skill improvement since such direct use provides the feeling of real makeup. Third, the graphical technique as a basic drawing skill may unrestrictedly show the artist's expression ability. Fourth, although artistic merits implying individuality and creativity should be shared through illustrations that express the artist's ideas or emotions, the graphical technique is the easiest method to beginners who just started learning of illustration, in that it enables expression without highly advanced skills.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.29 no.3
• /
• pp.297-320
• /
• 2018

This study aims to improve the access and retrieval of images and to find a way to effectively generate tags as a tool for providing explanation of images. To do this, this study investigated the features of human tagging and machine tagging, and compare and analyze them. Machine tags had the highest general attributes, some specific attributes and visual elements, and few abstract attributes. The general attribute of the human tag was the highest, but the specific attribute was high for the object and scene where the human tag constructor can recognize the name. In addition, sentiments and emotions, as well as subjects of abstract concepts, events, places, time, and relationships are represented by various tags. The tag set generated through this study can be used as basic data for constructing training data set to improve the machine learning algorithm.

• Journal of the Korean Society of Costume
• /
• v.59 no.9
• /
• pp.55-70
• /
• 2009

This study aims at analyzing the formativeness of women fashion shoes shown in the high fashion since 2000 along with the necessity of study for such purposes. Fashion shoes designed for the perfection of high fashion have been positioned as an important item to increase the value of fashion. Subsequently, three formative images through the research method under the literature study could be analyzed as follows. First, the Fetishism image appeared from 18th century and the shoe heel has the erotic internal beauty while attracting the erotic nature from the perspective of 'feet confinement'. The high heel came to have an absolute relationship with the feminine beauty, and the feet and shoes are accepted for the erotic symbol regardless of anyone in the East or West. Second, the fashion shoes in the Maximalism image to pursue for the dream and excitement at the same time have been shown at the same time by using various ornaments in an exaggerated manner for the use of ornaments to clothes through designs by shoe designers. Third, the Aristocratism image in the fashion shoes was remarkably highlighted with the use of materials from processing natural materials with the best quality, which was expressed in an exotic manner with roughness and comfort despite the nature of refinement balanced with the simple reactionary tendency and technical senses of handicrafts. It can be perceived that the inner emotions of human beings are expressed by intentionally dismantling the functions of shoes in terms of functionality even in the fashion shoes in completing the ideal images after which are pursued by people.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.6
• /
• pp.87-94
• /
• 2019

South Korean films narrate exquisitely, express emotions implicitly and employ magnificent images, exemplifying unique oriental aesthetics. This paper takes Along with the Gods: The Two Worlds (2017) as an example to analyze the meaning of oriental aesthetics in South Korean films using the Film Narrative Theory. It is a fantasy blockbuster depicting family kinship stories. It structures with the familiar karma and reincarnation of Asian Buddhism with the core of family kinship. Perfectly interpreting the fantasy world of hell with stunning movie effects, it shows the family kinship of families under the main plot line of a horror film.

• Korean Institute of Interior Design Journal
• /
• v.17 no.6
• /
• pp.63-70
• /
• 2008

The service sector is growing and service is complicated with various customer needs in the competitive markets. Bill Hollins urges that services must be designed. I believe that service experiences must be designed with servicescape as an environment surrounding services. Servicescape is the physical and social environments of service. Service experiences do not depend only on the aesthetic impression of physical servicescape. One of the main characteristics of services is that the most value of services are accomplished from interaction between customer and service encounters. The design of physical servicescape affects the interaction between customer and service encounters and the behavior of both customer and service suppliers' including social factors such as display emotions and the interpersonal distance between customers. Servicescape design should control tangible and intangible area of service events. In addition servicescape design creates customer's good experiences in the servicescape. This research proposes the possibilities and proper design process of servicescape design. Servicescape Design should control the activities including interrelations of participants, efficient service delivery process, and the united images of services for creating the satisfied service experience values.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.5
• /
• pp.1019-1035
• /
• 2020

This study examines the millennial generation, who express themselves and share information on social media after experiencing constantly changing 'hot places' (places of interest) in contemporary cities, with the goal of analyzing space consumption behaviors. Data were collected via an Instagram crawler application developed with Python 3.4 administered to 19,262 posts using the term 'hot places' from November 1 and December 15, 2019. Issues were derived from a text mining technique using Textom 2.0; in addition, semantic network analysis using Ucinet6 and the NetDraw program were also conducted. The results are as follows. First, a frequency analysis of keywords for hot places indicated words frequently found in nouns were related to food, local names, SNS and timing. Words related to positive emotions felt in experience, and words related to behavior in hot places appeared in predicate. Based on importance, communication is the most important keyword and influenced all issues. Second, the results of visualization of semantic network analysis revealed four categories in the scope of the definition of "hot place": (1) culinary exploration, (2) atmosphere of cafés, (3) happy daily life of 'me' expressed in images, (4) emotional photos.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.45 no.5
• /
• pp.825-839
• /
• 2021

This study aims to develop jacquard fashion masks using traditional patterns and investigates the preference and emotions of consumers for them. Nine patterns were designed with the motifs of plum flower, turtle, and geometric patterns using an Adobe Illustrator program. After that, 20 kinds of jacquard fabrics were developed using those patterns, and prototype masks were made. Furthermore, data were collected using a survey of 231 adult consumers to understand the emotional images evoked by jacquard fashion masks with traditional patterns. The results of the research show that the emotional dimension derived from jacquard fashion masks with traditional patterns consists of seven factors: luxurious image, frugal image, feminine image, oriental image, sporty image, geometrical image, generous image. We found that consumers preferred the M6 with the plum flower pattern as the motif as the most preferred design, while M13 with the geometric pattern as the motif was the lowest preferred.

• The Research Journal of the Costume Culture
• /
• v.14 no.3 s.62
• /
• pp.443-456
• /
• 2006

The purpose of this study is to present inner wear design making use of domestic characters that can represent the emotions of those kidults, to develop differentiated products as a result of recent revitalization of inner wear industry and to propose the possibility of total marketing in domestic character industry. Three characters of Barunson, which leads the way in developing domestic character products for inner wear design to satisfy the needs of the emotional generation were selected and work began on the designs based on the selected characters' images and themes. The result of this study was as follows. First, adding new designs using characters to inner wear fits the trend. Second, it was able to expand a range of characters' marketability by developing inner wear designs using domestic stationary and fancy characters as motives, and to seek the possibility of developing 'total marketing' plans in domestic character industry. Third, we were able to recognize the possibility of domestic character development and the importance of design development by developing products making use of domestic characters rather than foreign characters.