| 요약2 |
To satisfy the diverse needs of consumers, emotional designs that focus on consumers have emerged. Consumers who consume emotionally have a high score on the happiness index and satisfaction. Among them, consumers pursue a style that suits their lifestyle in the residential space where they live. And in detail, consumers are highly satisfied by changing the color and material of objects placed in the space. Consumers prefer the natural and the modern styles from among the styles of interior design. Furthermore, when consumers plan the color scheme of residential spaces, living rooms are the top priority among residential spaces. Therefore, the purpose of this paper is to develop a model based on machine learning that recommends colors of furniture or objects to be placed in the living room of consumers. The data learned in the developed model is RGB of three colors extracted from natural and modern living room images. The living room space images are collected based on keywords on the I.R.I image scale, which visually measures Koreans' color sensitivity, and in addition, the living room space images are collected through a sharing platform. The collected images are cleaned and integrated using the I.R.I color image scale and CNN model. The color data (RGB) of the cleaned images are learned in XGBoost and LightGBM, which perform machine learning tasks. The color recommendation models in this paper are evaluated using r² and MSE, which are evaluation methods for regression models supported by Scikit-Learn. And the model with the highest evaluation score is selected. Therefore, in this paper, a color scheme model for color harmony in the living room was selected as XGBoost No. 2 “train : value = 8 : 2”. This is effective as a color scheme model, and it will be a model that can satisfy consumers with individuality in the era of emotional design. |