Integrating contourlet features with texture, color and spatial features for effective image retrieval

Abstract

Over the past few years, Content-based image retrieval (CBIR) has been an active research area. A rapid proliferation has been witnessed in the fields of both theoretical research and development of the CBIR system. The most commonly used transformation techniques in CBIR include wavelet and Fourier transformations; in spite of their widespread utilization, they have not been very effective in representing the image regions that are separated by smooth contours. An effective alternative, Contourlet Transformation performs well in representing the time-frequency localization of the images. In this paper, we propose a CBIR system for effective retrieval of images from a database for a given query image. The proposed CBIR system utilizes CT to extract the content of the image in terms of directional contours, horizontal and vertical edges of the image. In addition, the system extracts texture, color and spatial features from the images. In image retrieval, the system measures the similarity between the features of the query image and the images in the database using Squared Euclidean distance. Eventually, the images similar to the query image are effectively retrieved, chiefly based on the contourlet features.