Kansei retrieval method using visual pattern image coding for virtual reality space presentation

We propose a Kansei retrieval method based on the design pattern of a traditional Japanese craft object to provide a user with the desired presentation space in the digital traditional Japanese craft system. Visual quantitative feature values are extracted using visual pattern image coding (VPIC). These values include the total number, the frequency, the dispersion rate and the deviation rate of different edges. The quantitative feature values for traditional Japanese craft objects are registered in a multimedia database and the relation between Kansei words and the visual features of traditional Japanese craft objects are analyzed using a questionnaire. Then, the visual features are compared with the quantitative feature values. Through the above process, we want to find the relation between the design pattern components and edge types using VPIC. By finding this relation, the Kansei retrieval method can be realized.