This paper presents a novel recommender service system that considers the image as a uniform representation for tourists’ expectations, destinations, and local tourism SMEs. Images carried by each stakeholder role is modeled and managed by several system modules, and they also evolve to reflect the real time situations of each entity. In addition, the system is dynamic in terms of its emphasis on the dynamic relationships among these roles and entities. When interactions occur, image mixing will be conducted to derive extra image attributes for the adjustments of the images. Besides, since colors can be mapped onto emotions, this paper adopts colors to operate the image matching and mixing process in order to find good matches of destinations for the recommendations meeting the tourists’ emotional needs. Although this image related approach we proposed is used in tourism domain, we believe our method could also contribute to other areas of either practical applications or academic studies.