Medical image fusion is one of the most effective and versatile techniques used for medical analysis and treatment. This paper describes a fusion framework that combines undecimated dual-tree complex wavelet transform (UDTCWT) and non-subsampled contourlet transform (NSCT) to cover the benefits of them both concurrently. The UDTCWT solved the dual-tree complex wavelet transform (DTCWT) by offering exact translation invariance. These properties can aid in making the system more efficient, whereby actual parent coefficients are within the fusion system. In this framework, the NSCT decomposition provides multi-scale and multi-direction scales followed by UDTCWT decomposition. Then, different fusion rules are employed to fuse the obtained coefficients, and finally, an inverse to get the combined final image. The results demonstrate that the proposed technique eventually attains accuracy and better performance than four representative fusion techniques in visual and objective evaluations.
CITATION STYLE
Hamidu, N. M., Liu, Q., & Zhang, C. (2021). Medical Image Fusion Based on Undecimated Dual-Tree Complex Wavelet Transform and NSCT. In Communications in Computer and Information Science (Vol. 1454 CCIS, pp. 472–484). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-7502-7_43
Mendeley helps you to discover research relevant for your work.