Two-Dimensional CS Adaptive FIR Wiener Filtering Algorithm for the Denoising of Satellite Images

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing 2017-12, Vol.10 (12), p.5245-5257
• Main Authors: Suresh, Shilpa, Lal, Shyam
• Format: Article
• Language: English
• Subjects: Adaptive algorithms; Adaptive filter algorithm; Adaptive filters; Algorithm design and analysis; Algorithms; Coefficients; Computational efficiency; Computer applications; Computing time; cuckoo search (CS) algorithm; Data processing; Filters; Finite impulse response filters; FIR filters; Heuristic methods; Information processing; Mathematical models; Measurement; metaheuristic optimization algorithms; Noise; Noise pollution; Noise reduction; Optimization; Satellite broadcasting; satellite image denoising; Satellite imagery; Satellites; Signal processing; Signal processing algorithms; Stability; two-dimensional finite-impulse response (2-D FIR) Wiener filter; Wiener filtering
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2017.2755068

In the recent years, researchers are quite much attracted in designing two-dimensional (2-D) adaptive finite-impulse response (FIR) filters driven by an optimization algorithm to self-adjust the filter coefficients, with applications in different domains of research. For signal processing applications, FIR Wiener filters are commonly used for noisy signal restorations by computing the statistical estimates of the unknown signal. In this paper, a novel 2-D Cuckoo search adaptive Wiener filtering algorithm (2D-CSAWF) is proposed for the denoising of satellite images contaminated with Gaussian noise. Till date, study based on 2-D adaptive Wiener filtering driven by metaheuristic algorithms was not found in the literature to the best of our knowledge. Comparisons are made with the most studied and recent 2-D adaptive noise filtering algorithms, so as to analyze the performance and computational efficiency of the proposed algorithm. We have also included comparisons with recent adaptive metaheuristic algorithms used for satellite image denoising to ensure a fair comparison. All the algorithms are tested on the same satellite image dataset, for denoising images corrupted with three different Gaussian noise variance levels. The experimental results reveal that the proposed novel 2D-CSAWF algorithm outperforms others both quantitatively and qualitatively. Investigations were also carried out to examine the stability and computational efficiency of the proposed algorithm in denoising satellite images.