An Efficient DCT-Based Image Retrieval Approach Using Distance Threshold Pruning

Abstract

Content-based image retrieval (CBIR) techniques would allow indexing and retrieving images based on their low-level contents, which involves a large number of image pixels and thus becomes an inherently and essentially computational intensive task. This paper proposes a distance threshold pruning (DTP) method to alleviate computational burden of CBIR without sacrificing its accuracy. In our approach, the images are converted into the YUV color space, and then transformed into discrete cosine transform (DCT) coefficients. Benefited from the energy compacting property of DCT, Only the low-frequency DCT coefficients of Y, U, and V components are stored. On querying an image, at the first stage, the DTP serves as a filter to remove those candidates with widely distinct features. At the second stage, the detailed similarity comparison (DSC) is performed on those remaining candidates passing through the first stage. The experimental results show that both high efficacy and high data reduction rate can be achieved simultaneously by using the proposed approach.