Image Registration in Digital Ophthalmic Images for Spatial Filter in Clinical VEP Signal

Abstract

The visually evoked potential (VEP) is the measure of cortically evoked electrical activity that provides information about the integrity of the optic nerve and the primary visual cortex. Visual evoked potentials (VEP) are very weak and noisy signals. For this reason, powerful extraction tools are needed to improve their clinical use. In this paper, I present the adaptive noise canceller scheme where the input signals represent successive recorded VEP. To test the effectiveness of the method and compare their performance to conventional averaging traditionally used in hospitals. As compared to adaptive linear filtering or conventional averaging techniques, no assumptions are required on the VEP responses such as the stationarity of the signal and the white Gaussian nature of the background. The results obtained show that non-linear filtering performs efficient VEP extraction based on just a few single responses. This is very significant in terms of saving time especially when recording data from elders and children. The challenge of image registration (the process of correctly aligning two or more images accounting for all possible source of distortion) is of general interest in image processing.