• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.32 no.4
• /
• pp.61-72
• /
• 2014

Throughout analyzing and construing the words, contexts, and expressive languages used for depicting the pine tree in the novel "Honbul" written by Choi, Myung-Hee the symbolism of the pine and folksy languages used for scenery can be condensed as written below: First, it is explicit that the scenery-words for illustrating the pine tree in "Honbul" are emerged through diverse means methods and expressions. Namely, the reference forms of the pine tree and the expressive means of utilizing words portrays the use of the pine are various and subdivided. Second, the scenery-words found in vocabularies and the contexts of "Honbul" imply various symbolic representation. They not only perform to describe inherent image and symbolism of the pine, but they work for reifying the image of "Honbul" in the narrative structure in "Honbul" as being intrinsic scenery-word. Third, the scenery-words used for expressing aesthetics emerge as synesthetic expressions through the linear beauty and the texture of the pine as well as through five-senses. Forth, on the basis of the inherent symbolism and the image of the pine, the landscape of the background described in "Honbul" deems as a symbolic backdrop. As with then narrative structure of the novel, the pine tree performs as a mediation of the heaven and the earth, god and man, as well as the sacred and the secular. Fifth, scenery-words used for depicting the pine tree are a symbol that represents the spirit and emotion of the character in the novel. Moreover, it is a tool for pursuing the personification of the nature, the deification of the object, and the cosmos of the space. It is also utilized as a device that definitize the ideational image applied to express the landscape of the background of the novel. As mentioned above, the expressions, vocabularies and textures about pine tree represented from "Honbul" are expected to be the beginning of understanding the landscape-images and landscape-languages of pine in not only the setting for this novels, Namwon but also the entire districts of Korea.

• The Journal of Asian Finance, Economics and Business
• /
• v.6 no.3
• /
• pp.259-268
• /
• 2019

This study examines the color image of uniform of airline cabin crew according to the demographic characteristics of the customer and demonstrates how it affects the cognitive image of airlines. Adjective adjectives were derived for uniform color images of all eight airlines in Korea and analyzed the image of airline brand color. Based on the analysis of color images, the difference in perception according to the demographic characteristics of passengers was analyzed. When the colors of airline uniforms are mainly blue, sky blue, white and ivory, they have a lot of trust, neat and elegant images. Uniforms with primary colors such as red, orange and green beans are found to have a lot of cheerful, developmental and enterprising images. In addition, the empirical analysis of the impact of the customer's cognitive perception and favoritism on the uniform color image of the airline crew showed that the more positive the airline's positive perception of the uniform color image, the more positive the cognitive image is. In other words, the empirical analysis revealed that the airline's uniform color image, its cognitive image of the airline, and its popularity have significant positive relationships.

• Journal of the Korean Society of Costume
• /
• v.52 no.6
• /
• pp.41-50
• /
• 2002

The purpose of this study is to classify korean clothing image using brainstorming method. Brainstorming theme is selected 'The Land of Morning Calm 'which famed to foreigner about Korea. Brainstorming members were 10 persons for 1st. 9 persons for End. The 119 words of association from 'morning calm'were to extracted at 1st brainstorming. The group of senses image were to classified at End brainstorming. The results of this study were as follows : 1. The clothing image type of tactual sense implied feeling of that downy bedding in a soft spring and grandmother's hands as warm. rough. 2. The clothing image type of smelling sense associated smells of pleasant. mild. and fresh. 3. The clothing image type of auditive sense consisted mainly sense of indirect. resonance. small, and clear sounds. 4. The clothing image type of visual sense associated pure, passive, gentle, and lasting life-force as weeds and wild flowers. Korean line is pointless and rounded curve. Korean form is soft silhouette as streamy, not exaggerate and wavy detail of slim and short. Korean color is not dyed, just natural color and pastel tone. Korean textile is a natural material as linen, ramie. and coarse silk.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.84-93
• /
• 2014

Comics uses words to convey its content and meaning, while the comic image conveys the content as a narrative function to represent how language is combined with the text. This paper makes a comparison and analysis of the comics of Japan and South Korea, in terms of words and image expression, narrative techniques, and the way of communication, to study the characteristics of image narrative. The comic image of Jing ke is the other as a flow of narrative and getting rid of the current screen, to resonate with the readers. Go U-yeong's comics and Sumeragi Natsuki's set up a virtual narrative time and space through the line, surface, space and shade, to realize the reproduction of unhistorical facts and the significance of narrative with the artist's imagination. Sumeragi Natsuki's comics uses historical facts to represent exquisite narrative like still-life paintings. She focuses on the description of the objective facts of history, to seek the sensitive comic image beyond reality. The image narration of Go U-yeong's comics is a clash between his historical narrative among the subjective romantic image and the readers' awareness narrative flow that they insist inside. Therefore, he tries to keep balance. The instant image in his comics is not a reproduction of the historical real moment, but a reproduction image of the reality reconstructed by his own pursuit of narrative.

• Journal of Distribution Science
• /
• v.14 no.9
• /
• pp.65-72
• /
• 2016

Purpose - This study is to examine the effect of Korean Wave (Hallyu) towards consumer purchase intention of Korean Product in Indonesia. In addition, this study also investigates the image of Korea whether it can give an impact on Indonesian consumers' intention to purchase Korean Products. Research design, data, and methodology - A total of 227 respondents from Indonesian consumers were collected using online surveys. The results from this survey were analyzed using principal component analysis (PCA) to identify each of the factors. Multiple regression and process analysis (designed by Andrew F. Hayes) were conducted to test the hypotheses. Results - This research found that 'Korean Wave', 'Ethnocentrism', and 'Country-of-Origin Image' significantly affected consumer purchase intention towards Korean Products in Indonesia, while 'Country Image' on the purchase intention was not significant affected the purchase intention. Conclusions - Study findings provide useful information for business practitioners and government to develop and maintain the use of Korean Wave in the business and marketing fields. By only referring to the image of country, it will be difficult for the consumers to decide whether they want to purchase the products or not. In other words, the favorable image of Korea, usually represented by high level of industrialization and economy, is more likely to be enhanced by favorable image of product and Korean cultural wave.

• The Research Journal of the Costume Culture
• /
• v.29 no.1
• /
• pp.121-133
• /
• 2021

The purpose of this study was to investigate brand slognas that are effective in explaining how brand identity affects consumers. The effect of congruity between brand slogan and self-image (low and high) on attitude to slogans and brands were anaylzed. The moderating effect of self-monitoring (low and high) was also investigated. Survey data from 177 people in their 20s-30s were analyzed through descriptive statistics, exploratory factor analysis, and two-way ANOVA. First, congruity between slogan and self-image had a positive effect on both slogan and brand attitude. In other words, the higher the congruity between slogan and self-image, the more positive the attitude toward the slogan and brand. Second, no interactive effect was found in congruity between slogan and self-image and self-monitoring on slogan attitude; however it was identified for brand attitude. Again, in a group with high congruity between slogan and self-image, attitude toward the brand was more positive when self-monitoring was higher than when it was low. In conclusion, brand slogans that can represent the self-image of highly self-monitoring consumers are effective. In particular, this is meaningful as it has revealed its relationship with the impact of identity self-image congruity and self-monitoring on brand attitudes in fashion brands. These results offer meaningful guidance in determining brand slogans according to consumers' personal characteristics.

• Journal of the Korean Society of Food Culture
• /
• v.24 no.3
• /
• pp.286-294
• /
• 2009

The purpose of this study was to determine whether foodservice brand language localization affects consumer attitudes in terms of similar brand image recognition with an original brand. Many global foodservice companies have tried to modify their own brand identity according to local situations in order to attract more consumers. According to this study's results, consumers who similarly recognized both the original brand image and localization brand image tended to have greater purchase intention than those who did not recognize them similarly. In addition, when the original brand identity was changed to the local language, consumers more similarly conceived the original brand image and localization. And for local store marketing, foodservice companies should have a thorough marketing research plan since there can be difference results according to brand name recognition gaps or demographic characteristics. Original brand image similarity recognition by consumers affected their attitudes. In other words, the group that similarly recognized both the original brand company image and the localization brand company image tended to have greater purchase intention. Because brand language plays an important role in consumer attitudes with respect to recognizing a brand and distinguishing another brand, this study suggests that franchise foodservice companies have a local store marketing plan.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1998.10a
• /
• pp.413-414
• /
• 1998

This paper presents a real-time Spatial Decision Support System(SDSS) for security camera image monitoring. Other SDSSs are not real-time systems, i.e., they show the images that are already transformed into data format such as virtual reality. In our system, the image is broadcasted in real-time since the purpose of the security camera needs to do it in real-time. With these real-time images, other systems do not add up anything more; the screen just shows the images from the camera. However in our system, we created a motion detection system so that the supervisor(Judge) of a sec.urity monitoring system does not have to pay attention to it constantly. In other words, we created a judge advising system for the supervisor of the security monitoring system. Most of small objects do not need the supervisor's attention since they could be birds, cats, dogs, etc. if they show up in the screen image. In this new system the system only report the unusual change to the supervisor by calculating the motion and size of objects in the screen. Thus the supervisor can be liberated from the 24-hour concentration duty; instead he/she can be only alerted when the real security threat such as a big moving object like an human intruder appears. Thus this system can be called a real-time Spatial DSS. The utility of this system is proved mathematically by using the concept of entropy. In other words, big objects like human intruders increase the entropy of the screen images significantly therefore the supervisor must be alerted. Thus by proving its utility of the system theoretically, we can claim that our new real-time SDSS is superior to others which do not use our technique.hnique.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.5
• /
• pp.225-230
• /
• 2015

In this paper, we propose an effective real-time visual loop closure detector, VILODE, which makes use of key frames and bag of visual words (BoW) based on SURF feature points. In order to determine whether the camera has re-visited one of the previously visited places, a loop closure detector has to compare an incoming new image with all previous images collected at every visited place. As the camera passes through new places or locations, the amount of images to be compared continues growing. For this reason, it is difficult for a visual loop closure detector to meet both real-time constraint and high detection accuracy. To address the problem, the proposed system adopts an effective key frame selection strategy which selects and compares only distinct meaningful ones from continuously incoming images during navigation, and so it can reduce greatly image comparisons for loop detection. Moreover, in order to improve detection accuracy and efficiency, the system represents each key frame image as a bag of visual words, and maintains indexes for them using DBoW database system. The experiments with TUM benchmark datasets demonstrates high performance of the proposed visual loop closure detector.