In this paper, a recommendation system based on a mobile and web application is proposed for indoor decoration. The main contribution of this work is to apply two-stage filtering using linear matching and collaborative filtering to make recommendations. In the mobile application part, the image of the medium captured by a mobile phone is analyzed using color quantization methods, and these color analysis results along with other user-defined parameters such as height, width, and type of the product are sent to the web server. In the web application part, a large data set is first filtered via linear matching in which the color content of the medium and user-defined parameters received from the mobile application are matched to those for the products stored in the database. We then apply second-stage filtering, namely collaborative filtering, on the reduced data set. Performance evaluations of various color quantization methods and collaborative filtering methods used in the system are made. Results show the feasibility of using scalar quantization as a color quantization method and the K-nearest neighbor in the collaborative filtering method for our recommendation system. Overall evaluation of the system shows that our recommendation system provides around 90% accuracy.