Building a Digitized Taiwanese Color Image Database System to Define Color Identity Using a Case-Based Retrieval Mechanism

Abstract

The purpose of this study is to develop a digitized Taiwanese color image database system for various designed artifacts to define their color identities using the color images associated with a set of colors of the artifact. The paper uses the term color image as the adjectival description for a group of colors which correspond to the same feeling. The system uses the color difference formula from the CIEDE2000 method, which calculates the difference between two color perceptions represented by two given points. Using the Group Nearest Neighbor algorithm, the retrieval mechanism yields a similarity measure to retrieve the closest color images. This approach can help designers to interpret the meaning of colors and their associated color images, which will help in developing an artifact’s image. This paper also describes the implementation of a system prototype to prove our concepts and perform the user test.