This paper describes an attractiveness evaluation model based on the physical features of image regions. The word “attractiveness” here means salient, which is to get attention of viewers. This model uses the heterogeneity of regions in color, texture, shape, and size, as well as the potential attractiveness of color, spatial frequency, and size as the evaluation parameters. These parameters significantly contribute to the attractiveness in our subjective experiments. The model calculates the level of attractiveness by first merging the parameters through weighted linear combination, and then by providing the merged value to the Beta function, i.e., one of the S curve functions.