An important research issue in multimedia databases is the retrieval of similar objects. Most of the Content-Based Image Retrieval (CBIR) system uses the low-level features such as color, texture and shape to extract the features from the images. In Recent years the Interest points are used to extract the most similar images with different view point and different transformations. SURF is fast and robust interest points detector/descriptor which is used in many computer vision applications. In the state-of-the-art the SURF is combined with Color Moments to improve the performance of the system. In this paper, we propose one presentation (LOWE 2004) to improving image search based on the color and shape descriptors. The representation is obtained by the quantification of the SURF (Herbert and all 2008) combined with the color moments (Stricker and all 1995), and so called Bag-of- Features and Colors (BOFC). Experiments show that our descriptor BOFC provides better results than a standard Bag of Visual Words approach based on SURF (BOF).
Keywords: Bag of Features, Bag of Words, CBIR, Color Moments, Local Features, SURF
