Abstract

Shearlets not only possess all properties that other transforms have, but also are equipped with a rich mathematical structure similar to wavelets, which are associated to a multi-resolution analysis. Recently, shearlets have been used in image denoising, sparse image representation, and edge detection. However, its application in image fusion is still under study. In this letter, we study the feasibility of image fusion using shearlets. Fusion rules of larger high-frequency coefficients based on regional energy, regional variance, and absolute value are proposed because shearlet transform can catch detailed information in any scale and any direction. The fusion accuracy is also further improved by a region consistency check. Several different experiments are adopted to prove that fusion results based on shearlet transform can acquire better fusion quality than any other method.

© 2011 Chinese Optics Letters

Multi-focus image fusion algorithm based on Laplacian pyramids

Jianguo Sun, Qilong Han, Liang Kou, Liguo Zhang, Kejia Zhang, and Zilong Jin
J. Opt. Soc. Am. A 35(3) 480-490 (2018)

Multi-focus image fusion using a guided-filter-based difference image

Xiang Yan, Hanlin Qin, Jia Li, Huixin Zhou, and Tingwu Yang
Appl. Opt. 55(9) 2230-2239 (2016)

Multi-focus image fusion algorithm based on random features embedding and ensemble learning

Jinnian Zuo, Wenhao Zhao, Li Chen, Jun Li, Kai Du, Liang Xiong, Shaoyun Yin, and Jinyu Wang
Opt. Express 30(5) 8234-8247 (2022)

Multi-focus image fusion based on dictionary learning with rolling guidance filter

Xiang Yan, Hanlin Qin, and Jia Li
J. Opt. Soc. Am. A 34(3) 432-440 (2017)

Confocal microscopy multi-focus image fusion method based on axial information guidance

Tao Yuan, Wei Jiang, Yiqing Ye, Dongliang Wu, Yongjie Hai, and Dingrong Yi
Appl. Opt. 62(21) 5772-5777 (2023)