An Advanced Whale Optimization Algorithm for Grayscale Image Enhancement

Area of Science:

• Computer Science
• Image Processing
• Artificial Intelligence

Background:

• Traditional image enhancement methods have limitations.
• Intelligent algorithms offer improved contrast and information quality.
• Parameter selection significantly impacts image enhancement outcomes.

Purpose of the Study:

• To optimize parameters for a transformation-based grayscale image enhancement function.
• To introduce an enhanced whale optimization algorithm (WOA) for improved global optimization and convergence.
• To validate the proposed algorithm's effectiveness in enhancing image quality.

Main Methods:

• Utilized a transformation function for global and local grayscale image enhancement.
• Employed an enhanced whale optimization algorithm (WOA) with new equations, exemplars, and spiral updates for parameter optimization.
• Validated performance on four diverse image datasets.

Main Results:

• The enhanced WOA demonstrated superior performance in the objective function compared to other algorithms.
• The algorithm excelled in image enhancement metrics: Peak Signal-to-Noise Ratio (PSNR), Feature Similarity Index (FSIM), Structural Similarity Index (SSIM), and Patch-based Contrast Quality Index (PCQI).
• The proposed method showed superiority across multiple images for each evaluated metric.

Conclusions:

• The enhanced WOA is effective for optimizing image enhancement parameters.
• The algorithm provides significant improvements in image quality, both subjectively and statistically.
• This intelligent approach is well-suited for advanced image enhancement applications.