• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.71-75
• /
• 2005

We can easily recognize the voices already known to us. But what about unknown voices? Is there any relationship between voices and the images triggered by the voices? Actually, this question has been partly addressed by Moon(2000, 2002). The current study aims at shedding some more lights on the topic by investigating the relationship between unknown foreign voices and the images triggered by them. Speech samples from 16 American males and females (8 each) were recorded and 180 Korean subjects without any knowledge of the American Speakers were asked to match the voices with the corresponding photos. And the number of corrects matches between voices and pictures of the current study was less than that of Korean-speakers and Korean-listeners case. But in terms of the majority matches, regardless of correctness, the present study showed a similar trend: that is, there is more than a chance relationship between voices and the images triggered by the voices.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.9-17
• /
• 2024

Due to the recent pandemic and the development of ICT technology, the use of non-face-to-face and unmanned systems is expanding, and it is very important to understand emotions in communication in non-face-to-face situations. As emotion recognition methods for various facial expressions are required to understand emotions, artificial intelligence-based research is being conducted to improve facial expression emotion recognition in image data. However, existing research on facial expression emotion recognition requires high computing power and a lot of learning time because it utilizes a large amount of data to improve accuracy. To improve these limitations, this paper proposes a method of recognizing facial expressions using age and gender, which are image meta information, as a method of recognizing facial expressions with even a small amount of data. For facial expression emotion recognition, a face was detected using the Yolo Face model from the original image data, and age and gender were classified through the VGG model based on image meta information, and then seven emotions were recognized using the EfficientNet model. The accuracy of the proposed data classification learning model was higher as a result of comparing the meta-information-based data classification model with the model trained with all data.

• Journal of the Economic Geographical Society of Korea
• /
• v.12 no.4
• /
• pp.364-387
• /
• 2009

Female marriage immigrants have increased since the mid-1990s in Korea. Thus, their adaptation to Korean society has been a big social issue in Korea. There are a lot of academic researches on their adaptation to Korean society so far. We cannot sufficiently understand general main factors of their adaptation to Korean society because of methodological problems in the studies on the female marriage immigrants. Particularly, there are very few studies on female marriage immigrants' adaptation to their communities. This study analyzes determinants of female marriage immigrants' adaptation to their communities, using stepwise multi-regression. Data are collected from questionary survey on female marriage immigrants in Seoul, Gyeong-gi, Daegu, Gyeong-buk, Gwangju, Jeon-nam. Dependent variables are community life, spatial cognition and activities, and neighborhood relationship. Each dependent variable is analyzed with 30 independent variables through stepwise multi-regression. As a result, 16 positive determinants and 2 negative ones are selected. Positive determinants are resident identity, age, adaptation to home, number of Korean friends and same nationals' friends in Korea and so on. But, Korean language fluence is not selected as a significant factor. This is different from a general recognition. As exiting researches, the importance of social network and adaptation variables is also identified in this study.

• Radiation Oncology Journal
• /
• v.17 no.2
• /
• pp.166-171
• /
• 1999

Purpose : To get the data for public information and education of medical students about radiation therapy (RT). Materials and Methods : We evaluated the knowledge and attitudes towards the RT and cancer in the third grade medical students who did not receive a lecture before starting the poly-clinic education about radiation oncology in our medical school, We obtained a total of 142 answers from the students that completed the questionnaire. Results : More than half of the third grade medical students answered 1 question correctly and 5 questions incorrectly among 6 questions about knowledge of RT. Incorrect answers were done about the frequency of RT, hair loss, the period of RT, re-RT, cost of RT, Fifty-six percent of students didn't wish to prolong the survival time from 1 year to 3 years with long courses of chemotherapy and RT. They had bad images about cancer of colorectum, lung, esophagus, liver, breast, cervix which consist of 56.3$\%$ of patients receiving RT. Conclusions : Public information about the basic points of RT should be considered. Also the students showed the pessimism about the anticancer treatments such as chemotherapy and RT, so the exact results and positive aspects of anticancer treatment should be educated more. Especially it is needed to inform the students and the public the positive aspects of RT in some cancers (colorectal, lung, esophageal, hepatic, breast, cervix cancers) which the students had bad images about.

• CRM연구
• /
• v.4 no.1
• /
• pp.1-18
• /
• 2011

The consumer's expectation of companies' social responsibilities has been continuously getting higher as the consumerism has been matured. So, the company has faced the shift to move forward to the positive social activity such as charity, donation, and sponsorship. In addition, the company which does make a success needs to reach goals not only to maximize profits but also to make justices of social and cultural boundaries. Thus, success of an enterprise aims at the maximization of profits as the economic objective and the creation of competitive, powerful brands. Accordingly, as enterprises consider social responsibility as the concept of effective investment to enhance the asset value of corporation, they seek to extend their brands in order to pursue cause-related marketing, which accomplishes and complements two objectives each other the performance of social responsibility and the pursuit of powerful brand assets. In Korea, there are traditional ritual ceremonies such as ceremonies of coming-of-age, marriage, funeral, and ancestor worship and they consider those ceremony occasions as very important. Moreover, social positional grade of rank like the two upper classes of old Korea made people pretend to be noble and sensitive to other people around themselves. This old custom could influence Korean people's way of life, especially, consumer-action. This deep rooted custom also could influence consumption life considerably. Through this study, we can understand the consumer behaviors of Korean who consider ritual ceremonies and saving face as essential and are influenced by this culture. on another hand, we intend to check the effects on buying luxury brands.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.6
• /
• pp.2477-2488
• /
• 2011

The study of the Korean World Cup soccer event sports what is the character's preference factors were analyzed inductively. For this purpose the following research methods were used. First, the target for the study of the D City 10, 20, 30, 40 respectively 30 patients were sampled. World Cup soccer event of the 12 sports chosen for frequency analysis of characters, the final four characters for the analysis of qualitative data were collected from questionnaires 'What aspect of your character do you like this?' that consists of an open survey conducted by Was. As a result, about World Cup chukguk character of the sports people have a preference factors were altered by age, by comprehensively, the Korean people in terms of the five characters and related factors that have in common, which prefer oehyeongseong, internality, Meaningfulness, diversity, and specificity was. Specifically, the 'oehyeongseong' the cute look or exercise (soccer) would be good to see such a varied and colorful, with friendly materials, including a preference factor, and 'internality' and the friendly and patriotic images, meaning Star 'in football and that implies a special meaning was preferred. Finally, the specificity due to the food culture in Korea prefer rooting factors were analyzed.

• Cartoon and Animation Studies
• /
• s.32
• /
• pp.335-361
• /
• 2013

This study examines the ethnoscape of TV dramas on three Korean nationwide television channels from 2005 to 2012 by breaking down how many non-Koreans appear and how they are represented. Among all TV dramas, 6.4% show non-Korean characters of which are generally supportive or small roles. These characters are categorized into four groups: adoration, sympathy, proximity, and other. The adoration group consists mostly of white males from USA or Europe that have professional careers such as medical doctors or lawyers and are positively represented with attractive appearance and nice character. On the other hand, the sympathy group is made up of Southeast, Central Asians and blacks. They are mainly represented as an underprivileged group: females and low-paid workers. In the proximity group are the Japanese and Chinese characters. The Japanese are often represented as rich people that are highly competent or are able to easily cooperate with Koreans. This result shows that Korean TV dramas provide racial and ethnic stereotypes. Though rarely, some dramas represent various lives of foreigners and racial others in Korea. This study contributes to the establishment of sound multiculturalism by analyzing representation of racial others in TV dramas and internalized stereotypes of foreigners in the diverse and multicultural Korean society.

• The Journal of the Korea Contents Association
• /
• v.12 no.10
• /
• pp.148-158
• /
• 2012

In the world, the flow of globalization are causing that many cities in the world are trying to enhance city awareness and city image through the establishment of their identity. Seoul has also preceded various studies in order to establish its identity of the urban landscape in this flow. But, most of studies have only considered some of the problems of the urban landscape and its improvement. Therefore, a study to understand the current built urban landscape and its own identity has not been studied yet. In this study, we propose an analyzing and visualizing framework of the urban landscape through an internet survey using the compare contents based on the differences in Cognition and recognition. The core of the framework which analyses the differences in Cognitions and recognition about the urban landscape was performed by the correct and clear rate. In addition, it was extracted from the answers of the survey and the visualization, was performed by diagrams of accuracy rate that was derived from the correlation between the correct rate and the clear rate.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.13-26
• /
• 2024

Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.

• The Research Journal of the Costume Culture
• /
• v.7 no.3
• /
• pp.134-141
• /
• 1999

The purpose of this study is to provide new style for fashion illustration fo different image of Korean middle aged women. The research method is as follows. First, we make basic style base on The Korea Industrial Advancement Administration\`s Korean standard stomatype. Second, it give variety to body\`s rate and make each different 8 style. The subject are 144 college students who majoring clothing, fashion design and they have responded to the questionnaires. Questionnaires were taken from April, 1998 to Jan. 1999. Data were analyzes by analysis of variance, ANOVA test, Dunkun test, SPSS. PC/sup +/. As a result of this study, we found this following conclusions, 1. Well-proportion style have the exaggerated shoulder and the extended body at the same rate below waist line than basic style. 2. Reduction and extension need stability and well balanced. 3. Fashion illustration of middle aged women\`s clothing expression is not proper too narrow width, too long length of legs. 4. To making length, it is award well-proportion have too long hand or too long arm.