An experiment with Gaussian derivatives for image enhancement

Reports the result of a set of computer experiments carried out to enhance a digital image. The authors use a special line-weight function, which is a combination of zero- and second-order Hermite functions. The authors are motivated by the physiological evidence reported in Young (1987) that visual receptive fields in the primate eye are shaped like the sum of a Gaussian function and its Laplacian. This function can also be derived mathematically when the contrast sensitivity experiments in psychophysics are posed as an eigenvalue problem. The authors show that higher order Hermite terms play a significant role in image enhancement. The experimental results with one- and two-dimensional data show that the proposed function has extremely good localisation capability (i.e., the points marked by the operator is as close as possible to the center of the true edge).