Authors : Hun-Woo Yoo , Dong-Sik Jang , Dae-Ki Kim and Dong-Won Park
Abstract: We propose a new emotion-based image retrieval method in this study. Our method was motivated by Soen’s evaluation of human sensibility on color patterns. Thirteen adjective words expressing emotions such as “like”, “beautiful”, “natural”, “dynamic”, “warm”, “gay”, “cheerful”, “unstable”, “light”, “strong”, “gaudy”, “hard”, and “heavy” are modeled by 19-dimensional color array and 4 x 3 gray matrix. Once the query is presented in text format, emotion model-based query formulation produces the associated color array and gray matrix. Then, images related to the query are retrieved from the database based on the multiplication of color array and gray matrix, each of which is extracted from a database image. For experiments over 440 images, we obtained an average retrieval rate of 0.61 for the use of color array and an average retrieval rate of 0.47 for the use of gray matrix.
Hun-Woo Yoo , Dong-Sik Jang , Dae-Ki Kim and Dong-Won Park , 2004. Design of Human Sensibility Model via Color and Gray Information and Its Application to Content-based Image Retrieval . Asian Journal of Information Technology, 3: 1173-1183.