In this paper, we design a Costume Expert Recommendation System (CERS) based on customers’ physical features. First, we obtain images of customers, and use a multi-classifier model based on Support Vector Machine (SVM) to extract physical features of customers. The physical features include four features: skin-color, face-shape, shoulder-shape and body-shape. Second, CERS stores the specific physical feature of customers into the Fact Base of the Expert System. It then stores expert knowledge on costume matching into the rule base in the manner of production rules. Finally, the CERS adopts inference engine, namely, blackboard model algorithms to obtain the recommended costume that suits the physical features of the customer. Therefore, the proposed system provides customers an intelligent costume recommendation strategy in accordance with SVM and Expert System.
CITATION STYLE
Dong, A., Li, Q., Mao, Q., & Tang, Y. (2019). Costume expert recommendation system based on physical features. In Advances in Intelligent Systems and Computing (Vol. 849, pp. 77–85). Springer Verlag. https://doi.org/10.1007/978-3-319-99695-0_10
Mendeley helps you to discover research relevant for your work.