nOMP: A New Sparse Solution to Enhance the SSIM Levels of OMP-Based Encoded Images

Abstract

This work comprises the development of a quality enhancement technique for image encoders that use compressive sensing. The recommended solution seeks to maximize the perceptual quality based objective function, unlike other sparse representation algorithms that minimizes the error-based objective function. The key idea behind this work is to develop an iterative methodology that works as a modifier for the sparse coefficients. The modification procedure is SSIM-based and has been carried out in an iterative and linear manner. The conducted experiments revealed that the recommended technique works better than another SSIM-based modifier termed the SSIM-inspired OMP (iOMP) in terms of SSIM levels gained. The t-test is also utilized to examine our performance for significance, and the results show that the method works well for any type of image and any size, especially when a data-independent based dictionary is used.INDEX TERMS Orthogonal matching pursuit, compressive sensing, structural similarity index, image enhancement.

Nighttime road scene image enhancement based on cycle-consistent generative adversarial network

“…We conduct a comprehensive comparison between our proposed approach and four alternative methods: CycleGAN 24 , Uretinex-Net 6 , EnlightenGAN 35 , Zero-DCE 23 , Zero-DCE++ 15 , and LumiNet 28 . To assess the performance quantitatively, we use a set of image quality evaluation metrics, including PSNR 40 , SSIM 41 , NIQE 42 , and MetaIQA 43 . Larger values of PSNR, SSIM, MetaIQA, and smaller NIQE values correspond to images of higher quality.…”