Subband analysis of images

In this paper, an efficient parallel structure using the multirate techniques is introduced for the analysis of images by the methods of moments. The basic idea of the proposed method is to pass the original image through a bank of bandpass filters which split the image into a set of subband signals. These are lowpass translated by down-sampling resulting in a set of sub-images of lower dimensions, which are then analyzed separately using the method of moments. In image analysis using the method of moments, the major time-consuming task is the computation of the moments. Moreover, it is hard to reconstruct the detail of images from the moments since only moments of higher orders carry the fine detail of an image and they are vulnerable to white noise, such as the quantization noise. With the proposed technique, the computation time is reduced due to the parallel structure, the computational complexity is reduced by using only the dominant subimage in most applications and the fine detail of the image if necessary can be provided by the moments of upper-band subimages.