Image Retrieval Based on Content Using Color Feature

Abstract

In various application domains such as education, crime prevention, commerce, and biomedicine, the volume of digital data is increasing rapidly. The problem appears when retrieving the information from the storage media. Content-based image retrieval systems aim to retrieve images from large image databases similar to the query image based on the similarity between image features. In this thesis we present a CBIR system that uses the color feature as a visual feature to represent the images. We use the images from the WANG database that is widely used for CBIR performance evaluation. The database contains color images, so we use the RGB color space to represent the images. We use the Ranklet Transform to make the image invariant to rotation and any image enhancement operations. This is a preprocessing step performed on every image. For the resulting ranklet images we extract the color feature by calculating the color moments. The color moments are invariant to rotation and scaling. This is a benefit of our system. To speed up the retrieval time, images are clustered according to their features using k-means clustering algorithm. Finally, we compared with other existing systems that use the same features to represent the images. We show the outperforming of our system against the other systems.