Image Interpolation Based on Spiking Neural Network Model

Image interpolation is used in many areas of image processing. It seen that techniques developed to date have been successful both protecting edges and increasing quality. However, these generally detect with gradient-based linear calculations. In this study, spiking neural networks (SNNs), which are known successfully simulate the human visual system (HVS), edge pixels instead gradient. With help proposed SNN-based model, marked as interpolated a 1D directional filter. For remaining pixels, standard bicubic technique used. Additionally, success method compared methods using various metrics. The experimental results show more than other methods.