Adaptive Cuckoo Search based optimal bilateral filtering for denoising of satellite images. (May 2020)

• Record Type: Journal Article
• Authors: Asokan, Anju; Anitha, J.
• Is Part Of: ISA transactions. Volume 100(2020)
• Page Start: 308
• Page End: 321
• Publication Date: 2020-05
• Subjects: Remote sensing -- Denoising -- Bilateral filter -- Adaptive Cuckoo Search -- Gaussian noise -- Particle Swarm Optimization -- Spatial filter; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2019.11.008
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: A satellite image transmitted from satellite to the ground station is corrupted by different kinds of noises such as impulse noise, speckle noise and Gaussian noise. The traditional methods of denoising can remove the noise components but cannot preserve the quality of the image and lead to over-blurring of the edges in the image. To overcome these drawbacks, this paper develops an optimized bilateral filter for image denoising and preserving the edges using different nature inspired optimization algorithms which can effectively denoise the image without blurring the edges in the image. Denoising the image using a bilateral filter requires the decision of the control parameters so that the noise is removed and the edge details are preserved. With the help of optimization algorithms such as Particle Swarm Optimization (PSO), Cuckoo Search (CS) and Adaptive Cuckoo Search (ACS), the control parameters in the bilateral filter are decided for optimal performance. It is observed that the proposed Adaptive Cuckoo Search based bilateral filter denoising gives better results in terms of Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), Feature Similarity Index (FSIM), Entropy and CPU time in comparison to traditional methods such as Median filter and RGB spatial filter. Highlights: Spatial domain image filtering. Optimization of filter parameter. Satellite image analysis. Image denoising. Remote sensing application.