Image fusion using dual tree discrete wavelet transform and weights optimization

• Published in: The Visual computer Vol. 39; no. 3; pp. 1181 - 1191
• Main Authors: Aghamaleki, Javad Abbasi, Ghorbani, Alireza
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2023; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Computer Graphics; Computer Science; Computer vision; Decomposition; Deep learning; Discrete Wavelet Transform; Human error; Image processing; Image Processing and Computer Vision; Infrared imagery; Maximum entropy; Methods; Optimization; Original Article; Radiation; Wavelet transforms; Multi-scale decomposition (MSD); Dual tree discrete wavelet transform (DT-DWT); Image fusion; Infrared image
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-021-02396-9

Image fusion is a useful context in image processing. It goals to produce more informative image using multi-image data with different sensors. In this study, an effective approach in discrete wavelet transform domain for infrared and visible image fusion is proposed. In fact, important parts of thermal images along with details of visual image must be considered in fused images. Therefore, dual tree discrete wavelet transform is used to extract both subjects based on an optimization process. The optimization considers parts of input images with maximum entropy and minimum mean square error in fused image in comparison with both input images. Experimental results on a standard database demonstrate that proposed method can achieve a superior performance compared with other fusion methods in both subjective and objective assessments.