Optimisation of wavelet-based image fusion for multi-focused images

Abstract

Image fusion is a process of combining information from two or more images (multi–images) of the same scene to get a composite image, which is more suitable for human visual perception for further image processing tasks. In the present work, spatial–domain and transform domain image fusion techniques have been evaluated and compared. It was experimentally determined that wavelet–based image fusion provides the best fusion results. Further, the effect of wavelet–based decomposition level on fusion performance has also been determined and an optimal wavelet–based decomposition level for multi–focused image has been proposed. Two defocussed images were utilised to investigate the performance of image fusion scheme to select suitable wavelet family and wavelet decomposition level. The image quality was measured objectively for different wavelet filters of the fused image using Root Mean Square Error (RMSE) and an optimised level of decomposition was determined.