Contrast enhancement algorithm for infrared images based on adaptive morphological reconstruction and multi-curve...

Area of Science:

• Image Processing
• Computer Vision
• Signal Processing

Background:

• Infrared images often suffer from low contrast, blurring, and noise, limiting their visual quality.
• Current enhancement methods struggle to simultaneously address contrast, detail, and noise issues effectively.

Purpose of the Study:

• To develop an advanced infrared image contrast enhancement algorithm.
• To overcome limitations of existing methods in noise suppression and detail preservation.

Main Methods:

• Utilized multi-scale adaptive grayscale morphological reconstruction (MSAGMR) for noise suppression and edge preservation.
• Applied improved Gamma correction for base layer contrast adjustment.
• Employed difference in multi-scale adaptive gray morphology reconstruction (DoMSAGMR) and Laplace operator for detail enhancement.

Main Results:

• The proposed algorithm significantly enhances visual contrast and detail representation.
• Demonstrated effective noise suppression capabilities.
• Outperformed existing methods, particularly on complex, noisy, overexposed, or underexposed infrared images.

Conclusions:

• The developed algorithm provides a superior solution for infrared image enhancement.
• Achieves high-quality results by effectively fusing enhanced base and detail layers.
• Offers a robust approach for improving the visual quality of challenging infrared imagery.