Improvement of Automatic Pattern Generation System Based on User Impression

Abstract

It has been known that computers are not good at handling qualitative information, such as human impressions and sensitivities, while being good at quantitative mathematical calculations and handling large volume of information. However, in recent years, soft computing methods and sensitivity engineering are systematized. Then it is becoming possible to simulatively handle ambiguous information, such as human impressions and sensitivities with computers. Using these methods, in recent years, many researches have been conducted to relate media, such as images, and sensitivity information. A technique of classifying similar images using sensitivity information, such as impression words, and a technique of selecting sensitive characteristics from an image have been proposed. We, too, have created a system that automatically generates an image of pattern based on impression information input by the user. In this research, we would like to improve the former automatic pattern image generation system that we created, and aim to design a system, which can generate a pattern image that reflects the user's sensitivity better with a few elements.