Emotion-Based Painting Image Display System
- Authors
- Lee, Taemin; Kang, Dongwann; Yoon, Kyunghyun; Seo, Sanghyun
- Issue Date
- Mar-2020
- Publisher
- TSI PRESS
- Keywords
- Aesthetic analysis; Arousal-Valence; Attributes of Paintings; Emotional care; Emotion of Paintings; Internet of Things
- Citation
- INTELLIGENT AUTOMATION AND SOFT COMPUTING, v.26, no.1, pp 181 - 192
- Pages
- 12
- Journal Title
- INTELLIGENT AUTOMATION AND SOFT COMPUTING
- Volume
- 26
- Number
- 1
- Start Page
- 181
- End Page
- 192
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/44256
- DOI
- 10.31209/2019.100000139
- ISSN
- 1079-8587
2326-005X
- Abstract
- As mobile devices have tremendously developed, people can now get sensor data easily. These data are not only physical data such as temperature, humidity, gravity, acceleration, etc. but also human health data such as blood pressure, heart pulse rate, etc. With this information, Internet of Things (IoT) technology has provided many systems to support human health care. Systems for human health care support physical health care like checking blood pressure, pulse rate, etc. However, the demand for physical health care as well as mental health care is increasing. So, a system, which automatically recommends a painting to users based on their feeling, is proposed in this paper. Using a smartphone application, users take a self-portrait. Then, the application reads the user's facial expression, and obtains an Arousal-Valence (A.V.) emotion value. Also, the application has a database of paintings with A.V. value in advance. To create this database, we extracted many features from various paintings and estimated their A.V. value using regression analysis. When users reach home, the application detects it automatically using GPS information, and shows the painting that best suits the user's emotion, based on the extracted A.V. value. Thereby, users can get a feeling of relaxation by admiring the painting.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Art and Technology > School of Computer Art > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.