Content-Based Image Retrieval using moments of wavelet transform

With the rapid production of huge amount of digital images, it has become extremely essential to develop efficient systems to organize and index images for easy access. Content-Based Image Retrieval (CBIR) is one such system which solves this problem. This paper proposes an image retrieval technique based on moments of wavelet transform. Discrete wavelet transform (DWT) coefficients of grayscale images are computed which are then normalized using z-score normalization. Geometric moments of these normalized coefficients are computed to construct feature vectors. These feature vectors are used to retrieve visually similar images from large database. Performance of the proposed method is tested on Corel-1000 database and measured using precision and recall parameters. The experimental results show that the proposed method outperforms some of the other state-of-the-art methods in terms of precision and recall.