Efficient content based image retrieval using 2D dual tree complex discrete wavelet transform

Abstract

Last two decades have seen a rapid increase in the size of digital image collections. Content based image retrieval (CBIR) provides an efficient way to search and retrieve images from these large databases. In this paper, CBIR using 2D complex Dual-tree Discrete Wavelet Transform is developed. Features are extracted from 2D CDT-DWT from YCbCr image as it provides higher spatial localization and lower frequency resolution at higher frequencies, and the lower spatial localization and higher frequency resolution at lower frequencies. The technique is evaluated using the database which includes 1000 images with 10 image classes. Average precision and average recall values calculated by using 30 query images from the database. Experimental result shows improvement in precision and recall over existing methods.