Optimization of Autoencoders for Speckle Reduction in SAR Imagery Through Variance Analysis and Quantitative Evaluation

Ahmed Alejandro Cardona-Mesa, Rubén Darío Vásquez-Salazar, Jean P. Diaz-Paz, Henry O. Sarmiento-Maldonado, Luis Gómez and Carlos M. Travieso-González ()
Additional contact information
Ahmed Alejandro Cardona-Mesa: Faculty of Sciences and Humanities, Institución Universitaria Digital de Antioquia, 55th Av, 42-90, Medellín 050012, Colombia
Rubén Darío Vásquez-Salazar: Faculty of Engineering, Politécnico Colombiano Jaime Isaza Cadavid, 48th Av, 7-151, Medellín 050022, Colombia
Jean P. Diaz-Paz: Faculty of Engineering, Politécnico Colombiano Jaime Isaza Cadavid, 48th Av, 7-151, Medellín 050022, Colombia
Henry O. Sarmiento-Maldonado: Faculty of Engineering, Politécnico Colombiano Jaime Isaza Cadavid, 48th Av, 7-151, Medellín 050022, Colombia
Luis Gómez: Electronic Engineering and Automatic Control Department, IUCES, Universidad de Las Palmas de Gran Canaria, 35001 Las Palmas de Gran Canaria, Spain
Carlos M. Travieso-González: Signals and Communications Department, IDeTIC, Universidad de Las Palmas de Gran Canaria, 35001 Las Palmas de Gran Canaria, Spain

Mathematics, 2025, vol. 13, issue 3, 1-27

Abstract: Speckle reduction in Synthetic Aperture Radar (SAR) images is a crucial challenge for effective image analysis and interpretation in remote sensing applications. This study proposes a novel deep learning-based approach using autoencoder architectures for SAR image despeckling, incorporating analysis of variance (ANOVA) for hyperparameter optimization. The research addresses significant gaps in existing methods, such as the lack of rigorous model evaluation and the absence of systematic optimization techniques for deep learning models in SAR image processing. The methodology involves training 240 autoencoder models on real-world SAR data, with performance metrics evaluated using Mean Squared Error (MSE), Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Equivalent Number of Looks (ENL). By employing Pareto frontier optimization, the study identifies models that effectively balance denoising performance with the preservation of image fidelity. The results demonstrate substantial improvements in speckle reduction and image quality, validating the effectiveness of the proposed approach. This work advances the application of deep learning in SAR image denoising, offering a comprehensive framework for model evaluation and optimization.

Keywords: despeckle; Synthetic Aperture Radar; deep learning; autoencoder; analysis of variance; hyperparameter (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/3/457/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/3/457/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:3:p:457-:d:1580063

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().