BFORE: Butterfly-Firefly Optimized Retinex Enhancement for Low-Light Image Quality Improvement

TL;DR

BFORE introduces a hybrid metaheuristic framework that automatically optimizes Retinex-based parameters, significantly enhancing low-light image quality without training data, outperforming traditional and deep learning methods.

Contribution

The paper presents a novel hybrid BOA-FA optimization approach for Retinex-based enhancement, improving parameter tuning and image quality in low-light conditions.

Findings

Achieves highest PSNR (17.22 dB) on LOL dataset among traditional methods.

Outperforms Histogram Equalization and MSRCR by over 17%.

Surpasses RetinexNet in PSNR and SSIM without training data.

Abstract

Low-light image enhancement is a fundamental challenge in computer vision and multimedia applications, as images captured under insufficient illumination suffer from poor visibility, low contrast, and color distortion. Existing Retinex-based methods rely on manually tuned parameters that fail to generalize across diverse lighting conditions. This paper proposes BFORE (Butterfly-Firefly Optimized Retinex Enhancement), a novel hybrid metaheuristic-optimized framework that automatically tunes the parameters of a multi-stage Retinex-based pipeline. The proposed method converts the input image to HSV color space and applies Adaptive Gamma Correction with Weighted Distribution (AGCWD) to the luminance channel, followed by adaptive denoising. A Butterfly Optimization Algorithm (BOA) optimizes the Multi-Scale Retinex with Color Restoration (MSRCR) parameters, while a Firefly Algorithm (FA) optimizes the AGCWD and denoising parameters. A hybrid BOA-FA switching strategy dynamically balances global exploration and local exploitation. Experimental evaluation on the LOL benchmark dataset (15 paired test images) demonstrates that BFORE achieves the highest PSNR (17.22 dB) among all traditional enhancement methods, with 20.3% improvement over Histogram Equalization and 17.5% over MSRCR. BFORE produces the most naturally balanced mean brightness (129.97), closest to the ideal mid-tone value. Notably, BFORE outperforms RetinexNet -- a deep learning baseline -- in both PSNR (17.22 vs. 16.77 dB) and SSIM (0.5417 vs. 0.4252) without requiring any training data. The hybrid BOA-FA optimization contributes a 12.3% PSNR improvement and 14.8% SSIM improvement over the unoptimized pipeline.