| Abstract: | Content Based Image Retrieval (CBIR) is an important research area for manipulating large amount of image databases and archives. In a broad sense, features include visual features like color, texture, shape etc. In order to extract features of an image, various feature extraction methods are available. One of them is moment description. The Zernike Moment Descriptor is a moment based Shape Descriptor. It has many desirable properties such as rotation invariance, robustness to noise, expression efficiency and fast computation for describing the shapes of patterns. In this paper, we perform fast Content Based Image Retrieval (CBIR) of images from a database for the given query image. We have shown how fast computation of radial polynomials for computing Zernike Moments (ZMs) leads to the fast retrieval of relevant images according to the similarity measure calculated between features of the query image and images of the image database.
|