Compressive vector reconstruction: Hypothesis for blind image deconvolution
Abstract
Alternative imaging devices propose to acquire and compress images simultaneously. These devices are based on the compressive sensing (CS) theory. A reduction in the measurement required for reconstruction without a post-compression sub-system allows imaging devices to become simpler, smaller, and cheaper. In this research, we propose a new algorithm to compress and reconstruct blurred images for CS imaging devices. Blur effect in images is common due to relative motion, lens, limited aperture dimensions, lack of focus, and/or atmospheric turbulence. Our intention is to compress a blurred image with CS techniques and then reconstruct a blur-free version using the proposed algorithm. To assess the performance of the proposed algorithm in comparison to other CS based compression schemes, we have used the Peak-Signal-to-Noise-Ratio (PSNR). Our algorithm is based on the previous work of compressive blind image deconvolution (BID) [1] and in a new way of organizing wavelet coefficients [2]. We can see an improvement up to 2 dBs in the PSNR for the two highest compression rates comparing the proposed algorithm with the one presented in [1].
Subject Area
Applied Mathematics|Electrical engineering
Recommended Citation
Orea Amador, Alonso, "Compressive vector reconstruction: Hypothesis for blind image deconvolution" (2017). ETD Collection for University of Texas, El Paso. AAI10284578.
https://scholarworks.utep.edu/dissertations/AAI10284578