• Journal of Information Processing Systems
• /
• 제17권6호
• /
• pp.1138-1156
• /
• 2021

Emotional semantics are the highest level of semantics that can be extracted from an image. Constructing a system that can automatically recognize the emotional semantics from images will be significant for marketing, smart healthcare, and deep human-computer interaction. To understand the direction of image emotion recognition as well as the general research methods, we summarize the current development trends and shed light on potential future research. The primary contributions of this paper are as follows. We investigate the color, texture, shape and contour features used for emotional semantics extraction. We establish two models that map images into emotional space and introduce in detail the various processes in the image emotional semantic recognition framework. We also discuss important datasets and useful applications in the field such as garment image and image retrieval. We conclude with a brief discussion about future research trends.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2008년도 추계학술대회
• /
• pp.74-77
• /
• 2008

Online shoppers are not able to try clothing on. Therefore, the pictures of clothing on the website play a significant role when shoppers make decision on their purchase. There are generally three different ways to show clothing at online shops. The first one is showing only clothing images, and the second one is showing the pictures that have actual fitting models wearing clothing on (In this case, Model's face is mostly not shown in the picture.), and the third is showing the pictures of professional fitting models who wear goods. The shopping malls adopt each of the different ways but little is known about affect on purchasing from these three ways. The aim of this study is to figure out how the online shopper's emotional status is affected by these three ways of presenting pictures of clothing. At first, we developed a set of adjective words of human emotion to set up the evaluation criteria for user's emotional status. Those adjectives are originally from the precedent research on human emotion. To cut 99 adjectives down to a proper number for the criteria, we conducted a preliminary survey, and finally, 5 adjectives are selected as appropriate criteria for evaluating users' emotional status while they are shopping. Those five adjectives are 'possess','sensual', 'unique', 'tasteful', and 'stylish'. Then, we conducted the main survey showing 10 kinds of cloth (each cloth was consist of 3 ways). And in the page of model images, we measured the model's preference for understanding the relation with customer's emotion criteria of the product. As a result of the test there was statistically significant difference between product only images and anonymous images, but there was no significant difference between anonymous images and model images. And the preference of the model and value of the emotion criteria have large correlation except 'unique' criteria. It is expected that the result in this study will help to build new marketing strategy which satisfy customers' emotion.

• 한국의류산업학회지
• /
• 제17권4호
• /
• pp.524-540
• /
• 2015

This study develops textile pattern design ideas created through the visualization of music. Methods of auditory and synesthesia were employed to analyze various attributes of popular music genres and appoint language image, shape image, and color image to obtain their interrelationships. This study provides data that can be used to express emotional images on textile print pattern designs. This research used different genres of popular music as stimuli. The language image was extracted and introduced to the overall color scheme; in addition, the color image was verified. The analysis of the color image was executed by applying it with the color set image scale of I.R.I colors. Then, the color image of the target genre of popular music was examined and analyzed through a color tone system. The preference in shape image was realized through visual images based on basic principles of points, lines, and sides composition; subsequently, an analysis of the emotional image of popular music followed. An examination of the emotional images of different popular music genres have led to the discovery that language image, color image, and shape image all share a common emotional image. There was also a realization that similarity and interrelationship exists in language, color, and shape images experienced by listening to popular music.

• 한국실내디자인학회논문집
• /
• 제16권5호
• /
• pp.115-125
• /
• 2007

As a part of "The method of suitable design for resident," the purpose of this study is to figure out the resident aptitude of client through "Saju-Myungrihak" more effectively and precisely. That is, the study is to find out the relations between individual character and environmental interior tendency through experimentingss to make Images based on one's individual inherent aptitude and character. For all these reasons, we proudly launch to develop the interior design program based on emotional inherent-aptitude technology for our clients with applying Nakamitch Mizuo's emotional technology thesis "the Expert System." However, a critical implication made by Nakamitch Mizuo's emotional technology, elucidates the fact that there was a problem for understanding the system of client's inherent aptitude. 1. Appearance of The inherent-aptitude in Saju-Myungrihak 2. MBTI (Myers Briggs Type Indicator) Form K 3. To strengthen and develop the tools of visual images through understanding clients' character and tendency by the result of his or her DNA (ACE, DRD4, DRD2, G-protein) test.

• 감성과학
• /
• 제13권1호
• /
• pp.259-268
• /
• 2010

현대사회를 감성사회라고 말한다. 감성사회에서 감성(感性)디자인은 상품의 가치를 높여 부가가치를 높여준다. 많은 연구자들이 감성디자인에 대하여 주장을 하고 있지만 감성제품과 일반 제품의 관계에 대해서는 아직까지 판단기준이 무엇인지 명확하게 밝히거나 무엇이 감성제품인지에 대하여 구체적으로 연구된 사례가 많지 않다. 따라서 감성디자인에서, 사용자에게 중요하게 다루어지는 디자인요소가 무엇이며, 감성디자인의 분류와 판단 기준을 제시할 필요가 있다. 이를 위하여 첫 번째로 선행 연구된 디자인 창의성 평가 요소와 감성디자인의 관계, 소비자에게 선호되는 감성디자인은 어떤 창의성평가요소와의 디자인요소가 중요하게 다루어져야 하는지를 제안하고, 두 번째로, 감성디자인유형별로 중요하게 표현되는 이미지와 창의성평가요소와의 관계는 무엇인지를 알아보았다. 이를 위하여 사용자들에게 제품을 보여주고 감성디자인이라고 생각하는 제품을 선정하게하고, 선정된 제품을 디자인유형별로 나누어 창의성평가요소와의 관계를 알아보았다. 또한 선정된 제품에서 느끼고 있는 디자인이미지를 알아보고 이미지와 창의성평가요소와의 관계도 알아보았다. 본 연구를 통하여, 감성디자인은 시대의 변화, 환경, 사용자에 따라 중요한 창의성평가요소가 다르게 나타날 수 있으며, 사용자가 선호하는 디자인은 어떤 이미지를 갖는 디자인이어야 한다는 것을 알 수 있을 것이다.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2011년도 춘계학술대회
• /
• pp.43-44
• /
• 2011

• 제어로봇시스템학회논문지
• /
• 제15권1호
• /
• pp.94-98
• /
• 2009

In this paper, we deal with a face recognition method for the emotional face images. Since the face recognition is one of the most natural and straightforward biometric methods, there have been various research works. However, most of them are focused on the expressionless face images and have had a very difficult problem if we consider the facial expression. In real situations, however, it is required to consider the emotional face images. Here, three basic human emotions such as happiness, sadness, and anger are investigated for the face recognition. And, this situation requires a robust face recognition algorithm then we use a fuzzy Fisher's Linear Discriminant (FLD) algorithm with the wavelet transform. The fuzzy Fisherface is a statistical method that maximizes the ratio of between-scatter matrix and within-scatter matrix and also handles the fuzzy class information. The experimental results obtained for the CBNU face databases reveal that the approach presented in this paper yields better recognition performance in comparison with the results obtained by other recognition methods.

• 한국콘텐츠학회논문지
• /
• 제14권9호
• /
• pp.476-483
• /
• 2014

본 논문은 국내 표정 연구에 적합한 얼굴 표정 이미지를 제작하는 것에 목적을 두었다. 이를 위해서 1980년대 태생의 한국인의 표준 형상에 FACS-Action Unit을 결합하여, KSFI(Korean Standard Facial Image) AU set를 제작하였다. KSFI의 객관성을 확보하기 위해 6가지 기본 감성(슬픔, 행복, 혐오, 공포, 화남, 놀람) 이미지를 제작하여, 감성 별 인식 정확률과 얼굴 요소의 감성인식 기여도를 평가하였다. 실험 결과, 정확률이 높은 행복, 놀람, 슬픔, 분노의 이미지의 경우 주로 눈과 입의 얼굴 요소를 통해 감성을 판단하였다. 이러한 연구 결과를 통해 본 연구에서는 표정 이미지의 AU 변경할 수 있는 KSFI 콘텐츠를 제안하였다. 향후 KSFI가 감성 인식률 향상에 기여할 수 있는 학습 콘텐츠로서의 역할을 할 수 있을 것으로 사료된다.

• International Journal of Costume and Fashion
• /
• 제10권2호
• /
• pp.51-59
• /
• 2010

This study regarded fashion selection criteria as clothing consumption value and desired fashion images, and examined selection differences according to regional subculture groups. Clothing consumption value is a direct value that people seek with clothing products and a perceived value which is divided into emotional, social, price, quality values. Fashion image which is a feeling communicated to others by wearing a certain fashion style is the most superficial value. Multivariate Analysis of Variance (MANOVA) was performed to test the differences between regional subculture groups in clothing consumption values and desired fashion images. We found some differences in clothing consumption value specifically in emotional value and social value. The group differences were remarkably significant in fashion image comparison. 'Kang-nam' group pursued 'lively', 'sophisticated', 'charming', feminine', 'gorgeous' image more than 'Kang-buk' group. While 'Kang-buk' group produced lower scores in ideal fashion images, the group had significant higher seeking in 'sportive' image compared to 'Kangnam' group.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.562-566
• /
• 2009

영상 검색에서 보다 빠르고 정확한 결과를 제공하기 위해 많은 시스템들은 결과내 재검색을 위한 카테고리 내 검색을 제공하고 있다. 이를 위해, 본 논문에서는 감성 카테고리를 사용하여 영상을 분류하는 시스템을 제안한다. 제안된 시스템은 영상에 포함된 컬러와 패턴 정보를 가지고 감성 벡터를 추출하여, 각 영상을 8 개의 감성 카테고리로 분류한다. 이때, 감성 카테고리는 고바야시가 정의한 8 개의 어휘 {romantic, natural, casual, elegant, chic, classic, dandy, modern}를 사용한다. 질의에 대한 결과가 주어지면, 사용자는 선택한 감성 카테고리로 재분류된 영상들을 제공받을 수 있다. 제안된 시스템의 성능을 평가하기 위하여 야후 이미지 검색에서 수집된 풍경 영상 1,000 장으로 사용자 평가를 실시하였으며 이를 통해 제안된 시스템의 성능을 증명하였다.