Enhanced image fusion using directional contrast rules in fuzzy transform domain

Area of Science:

• Computer Vision
• Image Processing
• Signal Processing

Background:

• Image fusion combines multiple images into a single, more informative image.
• Existing fusion methods face challenges in preserving details and reducing artifacts.

Purpose of the Study:

• To propose a novel image fusion algorithm utilizing directional contrast in the fuzzy transform (FTR) domain.
• To enhance the quality of fused images by leveraging directional features.

Main Methods:

• Input images are divided into non-overlapping blocks.
• Sub-block components are fused using a directional contrast-based fuzzy fusion rule in the FTR domain.
• Fused sub-blocks are reconstructed using inverse-FTR and a maximum-based fusion rule.

Main Results:

• The proposed algorithm was compared visually and quantitatively against standard and recent fusion methods.
• Experimental results indicate superior performance of the proposed method.
• The algorithm effectively fuses image components while preserving important details.

Conclusions:

• The proposed directional contrast-based fuzzy transform fusion algorithm offers improved performance.
• This novel approach provides a valuable contribution to the field of image fusion.
• The method demonstrates significant potential for various image processing applications.