|
Prediction of Human Emotions toward Abstract Images by Image Features and Eye Tracking Device |
|---|---|
| รหัสดีโอไอ | |
| Creator | กิติ์สุชาต พสุภา |
| Title | Prediction of Human Emotions toward Abstract Images by Image Features and Eye Tracking Device |
| Contributor | ภาณวี ฉัตรค้ำจุนเจริญ, โชติรส วุฒิเลิศเดชา |
| Publisher | Faculty of Information Science and Technology, Mahanakorn University of Technology |
| Publication Year | 2558 |
| Journal Title | Journal of Information Science and Technology |
| Journal Vol. | 5 |
| Journal No. | 2 |
| Page no. | 1-8 |
| Keyword | Eye Movements, Implicit Feedback, Emotion, Image Retrieval |
| URL Website | https://tci-thaijo.org/index.php/JIST |
| Website title | Journal of Information Science and Technology |
| ISSN | 2651-1053 |
| Abstract | Currently, emotion semantic search technology can support users to access data in the database. This can cover user's desirable which focuses on emotion concept. Given an image to different users, users' emotion stimulated by the image might be different due to different areas of interest. This paper presents a novel approach to increase the accuracy of emotion based image classification by combining eye movement data with basic image feature. The results show that combining eye movement data together with color feature can yield better classification performance than using color feature alone. |
