Fast Computation of Moments on Compressed Grey Images using Block Representation

I n image processing, moments are useful tools for analyzing shapes. Suppose that the input grey image with size N N has been compressed into the compressed image using the block representation, where the number of blocks used is K, commonly KoN due to the compression effect. This paper presents an efficient OðN ffiffiffiffi K p Þ-time algorithm for computing moments on the compressed image directly. Experimental results reveal a significant computational advantage of the proposed algorithm, while preserving a high accuracy of moments and a good compression ratio. The results of this paper extend the previous results in [7] from the binary image domain to the grey image domain.