Abstract
In this paper, we propose clothing image retrieval system considering user's Kansei . Recently, various goods have been dealt on the Internet shopping and we can obtain goods information easily on the Internet. However, when a user searches fashion goods, the computer shows the user a large number of goods. Therefore, the user needs to check and choose a number of goods. The user's load is large. Then, using a clothing image retrieval system, the load can be reduced greatly. The system searches clothing images considering the user's Kansei . However, the system needs to learn the user's Knasei. The system learns the user's Kansei gradually by repeating interactive with the user. The system which learned the user's Kansei can search clothing images considering the user's Kansei . In our previous study, numerical simulations were conducted in order to analyze the optimized performance of the proposed system. In simulations, the practicality of the proposed system was confirmed. However, the practicality of the proposed system to real users was not confirmed. In this study, we conducted evaluation experiments by real users to verify the effectiveness of the clothing image retrieval system. As a result, we confirmed that the proposal system searches clothing images considering the user's Kansei.
