Enhancing image compression through a novel Structural Fidelity Weighted Ensemble (SFWE) model.

With the explosion of digital images across multiple sectors like social media, health care, medical imaging, and remote sensing, there is a demand to optimise the storage and transmission of images. In this paper, a novel Structural Fidelity Weighted Ensemble model is proposed to dynamically adjust the weights between SVD and PCA outputs to enhance the quality of reconstructed images. Unlike traditional static fusion techniques, the proposed SFWE deploys a fast bounded scalar optimization strategy so as to dynamically estimate the optimal fusion weights thereby ensuring non-negativity and simplex constraints while significantly reducing computational overhead compared to Sequential Quadratic Programming(SQP) or constrained gradient descent methods. Validation was done across multiple benchmarks datasets namely, USC-SIPI Sequences (grayscale TIFF), Kodak, BSDS500, DRIVE (Digital Retinal Images for Vessel Extraction), and ISPRS Potsdam which cover natural, medical, and remote-sensing images. Per-image processing, runtime measurement, and compressed ratio (CR) were produced automatically by the provided evaluation pipeline; The SFWE method provides greater image quality and structural fidelity across diverse datasets, attaining a PSNR of 40 dB and SSIM of 0.95, outperforming existing approaches such as Discrete Cosine Transform (DCT), Wavelet Transform, Singular Value Decomposition (SVD), and Principal Component Analysis and JPEG2000 + CNN models. In addition, it also maintains a good compression ratio leading to an effective balance between the reduction in file size as well as visual quality of the images, which confirms enhanced structural preservation across diverse image types.•To implement a novel ensemble model (SFWE) that optimally balances the outputs of SVD and PCA for doing effective image compression.•To achieve a higher SSIM (0.95) and good PSNR (40 dB) compared to compression techniques such as DCT, Wavelet, SVD, PCA, and JPEG2000 + CNN.•To ensure adaptive high-quality reconstruction across multiple datasets, demonstrating its suitability for diverse image-intensive applications.