Quantum-assisted image enhancement using Grover-based parameter optimization

This paper presents a hybrid quantum-classical framework for image enhancement, where a Grover-inspired quantum circuit is utilized to adaptively select enhancement parameters. The proposed method operates in a pixel-wise manner and integrates quantum optimization with classical intensity transformation to achieve balanced contrast enhancement while preserving structural details. The performance of the method is evaluated on diverse image types, including color-rich (pepper), texture-dominant (cloth), and structural grayscale (boat) images, and compared with classical techniques such as Histogram Equalization (HE) and Contrast Limited Adaptive Histogram Equalization (CLAHE). Experimental results demonstrate that the proposed method consistently achieves superior structural preservation and lower distortion. For the cloth image, the method achieves a PSNR of 26.03 dB and SSIM of 0.9546, outperforming HE (18.12 dB, 0.7814) and CLAHE (18.69 dB, 0.8623). Similarly, for the boat image, it attains 25.18 dB PSNR and 0.8886 SSIM, compared to 11.31 dB and 0.7317 for HE. On the pepper image, the method achieves the highest SSIM of 0.9104. The HE increases distortion and CLAHE increases noise amplification. In contrast, the proposed method offers a better contrast enhancement while preserving structural fidelity. The source code of the proposed Quantum-Assisted Image Enhancement (QAIE) framework is publicly available at GitHub https://github.com/Johnchristopherclement/Image-Enhancement-Using-Grover-Based-Parameter-Optimization and has been archived in Zenodo (Version 1.0.0) with the DOI 10.5281/zenodo.21987903 .