TY - GEN
T1 - NSST Based MRI-PET/SPECT Color Image Fusion Using Local Features Fuzzy Rules and NSML in YIQ Space
AU - Ullah, Hikmat
AU - Zhao, Yaqin
AU - Wu, Longwen
AU - Abdalla, Fakheraldin Y.O.
AU - Mkindu, Hassan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - An improved algorithm for the fusion of anatomical structural MRI (magnetic resonance imaging) and metabolic functional PET (positron emission tomography) or SPECT (single photon emission computed tomography) images is proposed here. First, if any of the source image is in RGB format, it is converted to YIQ color space. Then by taking full advantage of non-subsampled shearlet transform (NSST), both the input images (channel-Y and/or gray-scale) are decomposed into one low frequency subbands (LFS) and several high frequency subbands (HFS). Second, local spatial frequency (SF) and region energy (RE) based fuzzy pixel-rules are applied for the fusion of LFS. Where, the fused HFS coefficient is directly selected by computing and comparing novel sum-modified-Laplacian (NSML) of every HFS, to extract maximum and more useful information. Finally, the required fused image is achieved by inversed NSST and inversed YIQ transform. Experimental results obtained shows that the algorithm significantly achieved maximum feature information from the source images, enhance visual quality and contrast of the fused image, and decrease computational task compared to other state-of-art proposed methods.
AB - An improved algorithm for the fusion of anatomical structural MRI (magnetic resonance imaging) and metabolic functional PET (positron emission tomography) or SPECT (single photon emission computed tomography) images is proposed here. First, if any of the source image is in RGB format, it is converted to YIQ color space. Then by taking full advantage of non-subsampled shearlet transform (NSST), both the input images (channel-Y and/or gray-scale) are decomposed into one low frequency subbands (LFS) and several high frequency subbands (HFS). Second, local spatial frequency (SF) and region energy (RE) based fuzzy pixel-rules are applied for the fusion of LFS. Where, the fused HFS coefficient is directly selected by computing and comparing novel sum-modified-Laplacian (NSML) of every HFS, to extract maximum and more useful information. Finally, the required fused image is achieved by inversed NSST and inversed YIQ transform. Experimental results obtained shows that the algorithm significantly achieved maximum feature information from the source images, enhance visual quality and contrast of the fused image, and decrease computational task compared to other state-of-art proposed methods.
KW - Fuzzy-rules
KW - Local-features
KW - MRI-PET and MRI-SPECT fusion
KW - NSML
KW - NSST
KW - YIQ
UR - https://www.scopus.com/pages/publications/85081347988
U2 - 10.1109/ISSPIT47144.2019.9001891
DO - 10.1109/ISSPIT47144.2019.9001891
M3 - 会议稿件
AN - SCOPUS:85081347988
T3 - 2019 IEEE 19th International Symposium on Signal Processing and Information Technology, ISSPIT 2019
BT - 2019 IEEE 19th International Symposium on Signal Processing and Information Technology, ISSPIT 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2019
Y2 - 10 December 2019 through 12 December 2019
ER -