Using the discrete radon transformation for grayscale image moments
share
Image moments are weighted sums over pixel values in a given image and are used in object detection and localization. Raw image moments are derived directly from the image and are fundamental in deriving moment invariants quantities. The current general algorithm for raw image moments is computationally expensive and the number of multiplications needed scales with the number of pixels in the image. For an image of size (N,M), it has O(NM) multiplications. In this paper we outline an algorithm using the Discrete Radon Transformation for computing the raw image moments of a grayscale image. It reduces two dimensional moment calculations to linear combinations of one dimensional moment calculations. We show that the number of multiplications needed scales as O(N + M), making it faster then the most widely used algorithm of raw image moments.
READ FULL TEXT