| Title |
Implementation and Application of Interior Design Style Training Model using Deep Learning |
| Authors |
김진성(Kim, Jin-Sung) ; 이진국(Lee, Jin-Kook) |
| DOI |
http://doi.org/10.14774/JKIID.2020.29.5.096 |
| Keywords |
Design Reference Images; Deep Learning; Interior Design Style; Style Recognition |
| Abstract |
This paper describes an implementation and application of interior design style training model using a deep learning. In fields of interior design, a design style is a useful concept and has played an important role in helping people understand interior and communicate with each other. Previous research on interior design style have focused what is the interior design styles. On the other hands, this research aims to propose a method for stochastically recognizing design style of interior images using deep learning and a convolutional neural network and an approach to applying the style recognition model to the interior design. The research focuses on training and evaluating a interior design style recognition model and its application for interior design. A target is living room and its four popular styles (casual, classic, modern and natural style). The research method and process can be summarized as follows: 1) collecting interior design reference images according to design style, 2) building an interior design style training model using a pre-trained VGG16 model, 3) training and evaluating the model, and 4) demonstration of usage of the model. The result of research shows that the style training model automatically recognizes styles of reference images with probability values. This model and recognized style information contribute to facilitating manage and utilize interior design references. |