Adaptive Medical Image Fusion Method based on NSCT and Unit-Linking PCNN
- DOI
- 10.2991/iccia-16.2016.86How to use a DOI?
- Keywords
- Medical image fusion; Nonsubsampled contourlet transform; Unit-linking PCNN; Canny operator.
- Abstract
This paper presents a self-adaptive medical image fusion method based on combining NSCT and Unit-Linking PCNN together. Firstly, for the strictly registered image to be fused, it will be decomposed at different directions and scales by utlizing nonsubsampled Contourlet transform (NSCT) to obtain low frequency sub-band coefficients and different directions of the high frequency sub-band coefficients. The selected value coefficient of the low frequency sub-band based on edges and high frequency sub-band coefficients are used as external excitation input for Unit-Linking PCNN, fuse low-frequency sub-band according to the first ignition timing of the corresponding point; Taking Canny operator to do the edge detection of the high frequency sub-band, then to fuse it by the first ignition timing of the corresponding point and the results of edge detection. Finally, fusion image will be obtained by NSCT's inverse transformation. The above fusion algorithms will be applied to CT/MRT medical image's fusion experiments, and do experimental comparative analysis with other different fusion algorithms. Most experimental results show that this fusion algorithm is obviously better than the comparative method in both subjective and objective evaluations.
- Copyright
- © 2016, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Wei Liu PY - 2016/09 DA - 2016/09 TI - Adaptive Medical Image Fusion Method based on NSCT and Unit-Linking PCNN BT - Proceedings of the 2016 International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2016) PB - Atlantis Press SP - 467 EP - 473 SN - 2352-538X UR - https://doi.org/10.2991/iccia-16.2016.86 DO - 10.2991/iccia-16.2016.86 ID - Liu2016/09 ER -