Multi-Focus Image Fusion Based on Shearlet Transform Using Genetic Algorithm

Multi-Focus Image Fusion Based on Shearlet Transform Using Genetic Algorithm

In this paper, a novel method for multi focus image fusion based on shearlet transform using genetic algorithm is proposed. Proposed method consist of three basic steps. First of all, ST is firstly applied to source images separately. Then, fusion rate of source images is determined using GA and source images are fused according to the rate of fusion determined by GA. Lastly, fused image is obtained applying  inverse ST to fused image of ST. Fused image is evaluated according to quality metrics such as variance, spatial frequency. Experimental results show that the proposed method is more effectively than traditional method. Together with GA and ST for multi focus image fusion is firstly presented in literature.

___

1. V. Aslantaş, R. Kurban, "Fusion of multi-focus images using differential evolution algorithm", Expert Systems with Applications, Volume 37, Issue 12, December 2010, Pages 8861-8870.

2. R. Kurban, “Resim Uzayında Blok Seçmeye Dayalı Yeni Görüntü Birleştirme Yöntemleri”, Doktora Tezi, Erciyes Üniversitesi, Kayseri, 2012.

3. K. Guo, D. Labate, “Optimally sparse multi-dimensional representation using shearlet”, SIAM Journal of Mathematical Analysis and Application 39, 2007, pp. 298-318.

4. Y. Cao, S. Li and J. Hu, “Multi-Focus Image Fusion by Nonsubsampled Shearlet Transform”, Sixth International Conference on Image and Graphics, China,2011.

5. L. Lü, J. Zhao and H. Sun, “Multi-Focus Image Fusion Based on Shearlet and Local Energy”, 2nd International Conference on Signal Processing Systems, China, 2010.

6. H. Wang, Y. Liu and Shupeng Xu, “An Image Fusion Algorithm Based on Shearlet”, Third International Conference on Information Science and Technology, March 23-25, 2013; Yangzhou, Jiangsu, China.

7. Aslantas V., "A singular-value decomposition-based image watermarking using genetic algorithm", Int. J. Electron. Commun. (AEÜ) 62 (2008) 386 – 394, 2007.