A method for extracting and analyzing “Kansei” factors from pictures

Upon viewing a picture, its audience gets an impression of that work. In this case, the picture has certain factors that can affect viewers´ impressions, which in Japan are called KANSEI factors. In general, highly attractive regions of a picture have the ability to affect the majority of viewers´ impressions. By extracting and analyzing those attractive regions, it becomes possible to predict viewers´ impressions within a reasonable error. This paper proposes a method for extracting attractive regions of pictures for analyzing KANSEI factors. It also describes a function for evaluating attractive regions segmented from a picture based on the size and color features of those regions