A Personalized Recommender System Model Using Colour-impression-based Image Retrieval and Ranking Method

This paper points out that achievements in the field of multimedia analysis and retrieval represent an important opportunity for improvement of recommender system mechanisms. Online shopping systems use various recommender systems; however a study of different approaches has shown that they do not exploit the potential of information carried by multimedia product data for product recommendations. We demonstrate how this can be accomplished by a personalized recommender system model that is based on analysis of colour features of product images. We present an approach for extraction of colour-properties of images in order to represent impressions related to the human perception of images. Colour-properties are based on image colour histograms, psychological properties of colours and a learning mechanism. Based on the extracted colour-properties, the method retrieves and ranks the images corresponding to the desired impressions. The architectural framework of the model is based on service-oriented architecture in order to promote its flexibility and reuse, which is important when applying the model to existing recommender system environments. An experimental study was performed for decorative photography domain. Keywordsproduct recommendation; image retrieval; Ebusiness; service-oriented architecture.