On-line knowledge embedding for an interactive EC-based montage system

Proposes an online knowledge embedding method for interactive evolutionary computation (EC) to reduce human fatigue. Online knowledge embedding is a method in which a user explicitly uses search hints that he obtains during an interactive EC operation for the next search. To evaluate this method, we developed two interactive EC-based montage systems. Our montage systems generate images of a face by combining six different part-images. The first system embeds the user´s intention in an EC search and the second does not. The results of subjective tests and other evaluation measurements have shown that the proposed method realizes a faster convergence than ordinary interactive EC searches do