Yukuo Isomoto

Color, shape and impression keyword as attributes of paintings for information retrieval

The composition of a painting consists of colors and shapes, and is explained with impression words and location of objects. These cause our impression or feeling. Especially from the viewpoint of KANSEI information retrieval, the data structure should be designed to be consistent with the attributes of color, shape, and impression words. Also, in the information retrieval of paintings, bibliographic data are important factors, as well as color and shape. The authors discuss the design and structure of keywords and key images as attributes of paintings for information retrieval. Each attribute of a painting is described as a fuzzy set and its membership function that represents the grade of the keywords or key images. We propose an estimation method for retrieved objects with the membership function. Furthermore, the information retrieval of paintings is formulated based on fuzzy set theory as an extension of the traditional crisp model.