Application of Swarm Intelligence Optimization Algorithms in Image Processing: A Comprehensive Review of Analysis,...

Area of Science:

• Artificial Intelligence
• Computational Intelligence
• Image Processing

Background:

• Image processing is a challenging AI field, with swarm intelligence (SI) algorithms emerging as powerful optimization tools.
• SI algorithms, inspired by biological populations, offer efficient global optimization for complex problems.
• Combining SI with image processing presents a novel approach for significant advancements.

Purpose of the Study:

• To comprehensively review swarm intelligence algorithms applied to image processing tasks.
• To analyze and compare theoretical research, improvement strategies, and application domains.
• To identify current challenges and project future trends in SI-enhanced image processing.

Main Methods:

• In-depth study of ant colony, particle swarm, sparrow search, bat, and thimble colony algorithms.
• Review of algorithm models, features, and improvement strategies in image processing.
• Analysis of applications including image segmentation, matching, classification, feature extraction, and edge detection.

Main Results:

• Detailed comparison of SI algorithms' theoretical and applied aspects in image processing.
• Extraction and analysis of representative SI algorithms for image segmentation.
• Summary of unified frameworks, common characteristics, and differences among SI algorithms.

Conclusions:

• Swarm intelligence algorithms offer effective solutions for diverse image processing challenges.
• Current literature highlights various improvement strategies and application successes.
• Future research should address existing limitations and explore novel SI-image processing integrations.