Infrared and Visible Image Fusion Based on Morphological Image Enhancement of Dual-Tree Complex Wavelet

Li, Changxing; Liu, Lei; Zhang, Xiaolu

doi:10.1007/978-3-030-32591-6_80

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of image fusion based on the wavelet transform, Pu et al [ 15 ] proposed an image fusion algorithm based on contrast transformation and wavelet decomposition. In addition, Li et al [ 16 ] proposed an image fusion method combined with morphological image enhancement and a dual-tree complex wavelet. This method was a good solution for images with ringing, incomplete scene information, low contrast, and Gibbs artifacts.…”

Section: Introductionmentioning

confidence: 99%

Infrared and Visible Image Fusion Algorithm Based on Double-Domain Transform Filter and Contrast Transform Feature Extraction

Ma,

Li,

Deng

et al. 2024

Sensors

View full text Add to dashboard Cite

Current challenges in visible and infrared image fusion include color information distortion, texture detail loss, and target edge blur. To address these issues, a fusion algorithm based on double-domain transform filter and nonlinear contrast transform feature extraction (DDCTFuse) is proposed. First, for the problem of incomplete detail extraction that exists in the traditional transform domain image decomposition, an adaptive high-pass filter is proposed to decompose images into high-frequency and low-frequency portions. Second, in order to address the issue of fuzzy fusion target caused by contrast loss during the fusion process, a novel feature extraction algorithm is devised based on a novel nonlinear transform function. Finally, the fusion results are optimized and color-corrected by our proposed spatial-domain logical filter, in order to solve the color loss and edge blur generated in the fusion process. To validate the benefits of the proposed algorithm, nine classical algorithms are compared on the LLVIP, MSRS, INO, and Roadscene datasets. The results of these experiments indicate that the proposed fusion algorithm exhibits distinct targets, provides comprehensive scene information, and offers significant image contrast.

show abstract

Section: Introductionmentioning

confidence: 99%