On the compression of video using the derivative of Gaussian transform

The derivative of Gaussian transform was introduced by the authors as a technique to locally represent image-frequency information using functions which have also been used to model certain aspects of human vision. This paper presents the application of this transform to the compression of image sequences. A set of basis selection criteria are used in order to minimize the leakage and edge artifacts which can be introduced by quantization of the coefficients. A quantization mask is derived which is based on a model of the contrast sensitivity function of the human visual system, appropriately extended for the DGT basis functions.