Multi-focal image fusion with convolutional sparse representation and stationary wavelet transform

Abstract

This paper illustrates a completely unique technique of multi-focus image fusion involving Stationary Wavelet Transform (SWT) and Convolutional Sparse Representation (CSR). Sparse-based fusion strategies do not retain information representation and cannot tolerate minor mistakes in registration. The SWT method does not have these issues. Multi-focus image fusion is the fusion of different parts of digital images, representing the common scene, in order to produce an image with everything in Focus, i.e., without the blur effect. Camera processors cannot fuse images by themselves. Thus, experts have to employ image editing methods to obtain clear photographs. The scheme stated in this paper uses SWT to distinguish focus levels accurately. The results suggest that the strategy is successful in ways comparable in terms of visual quality and clarity.