Image-Compression Techniques: Classical and "Region-of-Interest-Based" Approaches Presented in Recent Papers

Area of Science:

• Computer Science
• Image Processing
• Data Compression

Background:

• Image compression is crucial for resource-limited domains like automotive and telemedicine.
• Efficient storage, transmission, and decompression are vital for real-time systems.
• Region of Interest (ROI) compression techniques preserve critical image areas while reducing data size.

Purpose of the Study:

• To review and analyze relevant literature on ROI selection and compression techniques from the last decade.
• To highlight the novelty of hybrid compression methods by comparing them with classical approaches.
• To provide a categorized overview of compression methods based on performance metrics.

Main Methods:

• Systematic literature review of papers focusing on ROI selection and image compression.
• Analysis of classical and hybrid compression techniques.
• Categorization of methods based on compression ratio, Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM).

Main Results:

• Identified a range of classical and hybrid image compression techniques.
• Categorized methods based on key performance indicators (KPIs) like compression ratio and quality metrics.
• Highlighted the effectiveness of hybrid methods in balancing compression efficiency and image quality.

Conclusions:

• The study provides a comprehensive overview to guide researchers in selecting appropriate compression algorithms for specific domains.
• Understanding performance parameters like compression ratio and quality metrics is essential for optimizing image compression.
• Hybrid compression methods show promise for efficient image handling in various applications.