Premium
Contrast enhancement of medical images using fuzzy set theory and nonsubsampled shearlet transform
Author(s) -
Qingrong Guo,
Zhenhong Jia,
Jie Yang,
Kasabov Nikola
Publication year - 2019
Publication title -
international journal of imaging systems and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.359
H-Index - 47
eISSN - 1098-1098
pISSN - 0899-9457
DOI - 10.1002/ima.22326
Subject(s) - contrast (vision) , artificial intelligence , computer science , fuzzy logic , pattern recognition (psychology) , inverse , shearlet , mean squared error , image (mathematics) , computer vision , set (abstract data type) , algorithm , mathematics , statistics , geometry , programming language
Noises and artifacts are introduced in medical images during the process of imaging and transmission, resulting in reduced definition and lack of detail. Therefore, a contrast enhancement method, based on fuzzy set theory and nonsubsampled shearlet transform (NSST), is proposed. First, the original image is decomposed into several high‐frequency components and a low‐frequency component by NSST. Then, the threshold method is used to remove noises in the high‐frequency components. In addition, a linear stretch is used to improve the overall contrast in the low‐frequency component. Then, the reconstruct image is reconstructed by applying the inverse NSST to the processed high‐frequency and low‐frequency components. Finally, the fuzzy contrast is used to improve the detail information and global contrast in the reconstruct image. Experimental results indicate that, relative to contrast algorithms, the peak signal‐to‐noise ratio of the proposed method is improved by approximately 18%, and the root mean square error (RMSE) is optimized to approximately 48%. The proposed method also improves the image definition and texture information. Moreover, when compared with the Improved Fuzzy Contrast Combined Adaptive Threshold in NSCT for Medical Image Enhancement, the processing time (time) of this proposed method optimizes about 86%, which can obviously improve the computational efficiency of this method.