A Novel Method for Content Base Image Retrieval Using Combination of Local and Global Features

Content-based image retrieval (CBIR) has been an active research topic in the last decade. In this paper we proposed an image retrieval method using global and local features. Firstly, for local features extraction, SURF algorithm produces a set of interest points for each image and a set of 64-dimensional descriptors for each interest points and then to use Bag of Visual Words model, a clustering algorithm is used to obtain the visual vocabulary and each resulted centroid represent a visual word. Then, images are viewed as BoVW represented as histogram. In order to improve retrieval performance, global feature is extracted by HSV color feature. Finally, this approach uses the combined local and global features as feature vectors to provide image retrieval. The COREL image database have been used for our experimental results. The experimental results show that the performance of the combination of both local and global features is much higher than each of them, which is applied separately.

Keywords:

SURF , K-means , Bag-of-Visual Word , Color Features , CBIR