• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.47-55
• /
• 2024

We spend a lot of time in indoor space, and the space has a huge impact on our lives. Interior design plays a significant role to make an indoor space attractive and functional. However, it should consider a lot of complex elements such as color, pattern, and material etc. With the increasing demand for interior design, there is a growing need for technologies that analyze these design elements accurately and efficiently. To address this need, this study suggests a deep learning-based design analysis system. The proposed system consists of a semantic segmentation model that classifies spatial components and an image classification model that classifies attributes such as color, pattern, and material from the segmented components. Semantic segmentation model was trained using a dataset of 30000 personal indoor interior images collected for research, and during inference, the model separate the input image pixel into 34 categories. And experiments were conducted with various backbones in order to obtain the optimal performance of the deep learning model for the collected interior dataset. Finally, the model achieved good performance of 89.05% and 0.5768 in terms of accuracy and mean intersection over union (mIoU). In classification part convolutional neural network (CNN) model which has recorded high performance in other image recognition tasks was used. To improve the performance of the classification model we suggests an approach that how to handle data that has data imbalance and vulnerable to light intensity. Using our methods, we achieve satisfactory results in classifying interior design component attributes. In this paper, we propose indoor space design analysis system that automatically analyzes and classifies the attributes of indoor images using a deep learning-based model. This analysis system, used as a core module in the A.I interior recommendation service, can help users pursuing self-interior design to complete their designs more easily and efficiently.

• 한국실내디자인학회논문집
• /
• 제37호
• /
• pp.3-11
• /
• 2003

The study Is Intended to investigate and analyze the system and practice that have been applied to Interior Architecture, comparing with a number of similar foreign cases, in an attempt to seek the way toward its development as well as to come up with the solution for enhancing the competitiveness, thereby making a recommendation on how to create the desirable work environment of Interior Architecture down the road. The conclusion and recommendation we have made is highlighted as follow. Among the practical or procedural challenges in the process of improving work environment of Interior Architecture, development of current national technical qualification system in a way of further detailing the categories of Ki-sul-sa(highest engineer grade) or Ki-neung-jang(highest technician grade) as part of measures aimed at gradual approaching for improvement of design fees and rates or supervision fees will be very crucial, that calls for close coordination with the Ministry of Labor and Human Resources Development Service of Korea. In a bid to upgrade the Interior Architecture to become the part of knowledge-based industry, amendment to Korean Standard Industrial Classification along with Standard Classification of Occupations and Academic Classification will be essential, and moreover with the attitude of reflection and self-improvement, the endeavors to be able to deal with the revision of existing laws and regulations in a consistent way and manner, by forming a joint committee among the three Interior Architecture-related organizations(KOSID, ICC, KlID), will be more than important.

• Asia Pacific Journal of Business Review
• /
• 제5권1호
• /
• pp.21-36
• /
• 2020

This paper examines the effect of the choice properties of food carving decoration lectures on the recommendation and revisiting intention. As the culinary industry grows, consumers seek not only the value of satiety through food but also the value of aesthetics. They perceived satisfaction from the taste and appearance of the food as well as the interior of the restaurant and the service. Food carving is an important means of fulfilling consumer satisfaction value which is ever-changing. This study attempts to analyze the relationship between the choice properties of food carving lectures and the course recommendation and revisiting intention. This study hypothesis was formulated and the survey was conducted on 125 respondents who had experienced food carving lectures. The reliability and validity of measurement items were verified through Cronbach's Alpha and factor analysis. As a result, all measurement items showed no abnormality. The results of the analyses are as follows. The education satisfaction, education commitment, and brand image, the choice properties of food carving decoration lecture, were found to have a positive effect on the recommendation intention. The results also showed that the education commitment and brand image of food carving decoration lectures were positively associated with revisiting intention. Lastly, the implications of these findings were suggested and for future research were discussed.

• 산경연구논집
• /
• 제10권4호
• /
• pp.43-56
• /
• 2019

Purpose - The purpose of this study is to classify the quality factors of chicken restaurant customers with the service quality based on the SERVQUAL, the quality factors based on the selection attributes and service qualities of chicken restaurants used in the previous studies. Research design, data, and methodology - This survey was carried out on the students of Kangwon University in Samchuk City, Kangwon Province from November 20 - November 30, 2017, and a total of 260 questionnaires were distributed, with 222 collected. Of them, effective questionnaires applied in the final study were a total of 193 except 29 that couldn't be used. Results - The findings of this study are as follows: Firstly, chicken restaurants' quality factors were divided into seven categories like cleanliness, service encounter quality, product quality, aesthetics, overall interior, purchase quality, and convenience. Secondly, it showed that service encounter quality, purchase quality, and cleanliness had a positive impact on customer satisfaction, respectively. Thirdly, it showed that service encounter quality, purchase quality, and cleanliness had a positive impact on trust, respectively. Fourthly, it showed that customer satisfaction had a positive impact on behavioral intention. Additionally, it suggested that customer satisfaction of chicken restaurant consumers had a positive impact on behavioral intention and thereby, higher customer satisfaction leads to higher levels of reuse and recommendation intention. Lastly, after checking the effect relations of trust between customer satisfaction about chicken restaurant and behavioral intention, it was analyzed that customer satisfaction has a positive impact on trust and trust has a positive impact on behavioral intention. On the other hand, it showed that trust have a partially mediating effect in the relations between customer satisfaction and behavioral intention. But, it showed that product quality, aesthetics, overall interior, purchase quality, and convenience did not have a positive impact on customer satisfaction. Conclusions - Chicken restaurant consumers put more priority on friendly and good services of chicken restaurant staff in service encounter and delivery order, rather than on reasonable price and discount systems. Thereby, chicken restaurant marketers need to take factors like service encounter quality, cleanliness into more consideration.

• 마케팅과학연구
• /
• 제18권2호
• /
• pp.19-45
• /
• 2008

본 연구는 인터넷쇼핑몰 비주얼 머천다이징의 주요차원을 고객이 쇼핑몰에 진입한 후 정보탐색과 대안평가를 거치는 등의 쇼핑과정을 토대로 AIDA모형 관점에서 점포, 제품, 촉진에 초점을 맞추었다. VMD의 주요차원(primary dimensions)으로는 점포디자인, 머천다이징, 그리고 머천다이징단서로 구분하였다. 선행연구 결과를 토대로 점포다자인의 하위차원으로는 차별성, 간결성, 위치확인성을, 머천다이즈의 하위차원으로는 제품구색, 명성, 정보성을, 그리고 머천다이징단서의 하위차원으로는 제품추천 및 링크를 설정하여 VMD태도와의 관계를 탐색적으로 조사하였다. 연구결과 이들 세 차원은 종속변수에 유의한 정의 영향을 미치는 것으로 나타났다.