Abstract

The rapid increase in amount of multimedia data on personal computers, institutional computers and Internet necessitates the need to find a particular image or a collection of images of interest. It creates a need for new sophisticated methods to retrieve the information one desires. Especially for the visual content this is still an unsolved problem. The legacy approach within manual annotation alone cannot keep up with the rapid growth of available data anymore. Therefore, content-based image retrieval (CBIR) has attracted many researchers to variety of fields in an effort to automate data analysis and indexing. In this paper, we propose a content-based image retrieval system for real images. This method is using segmented images by Louvain method to create features cooperates with CBIR system based on the Bag-of-Visual-Words (BoVW) model. In order to evaluate the proposed method, we selected the Corel dataset which is composed of 10 classes total of 1000 images in the dataset for the experiment. The experimental results are shown using qualitative and quantitative evaluations.