TY - GEN
T1 - Parametric Optimization of Logarithmic Transformation using GWO for Enhancement and Denoising of MRI Images
AU - Attar, Tushar
AU - Bhattacharjee, Tushar
AU - Kumar, Rajesh
AU - Dey, Nilanjan
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - For the detection of tumors, vascular lesion and numerous other diseases, computed tomography(CT) and magnetic resource imaging (MRI) are considered as two vital medical imaging modal. However, various noises such as speckle noise, salt-pepper noise, etc. corrupt the imaging which makes the analysis of clinical data difficult. Therefore, to get a sharp and clear image for diagnostic purposes, medical image enhancement is must which removes noises and enhance the contrast of the image which helps in accurate diagnosis. In this work, brain MRI images are being enhanced through grey wolf optimization based logarithmic transformation. Logarithmic transformation increases the dynamic range value of the pixels with low intensity. GWO is a meta-heuristic approach that is used to maximize the fitness of the results. The outcome of the recommended methodology have been compared with the results of GA, PSO and CS optimizer. To measure the robustness of the technique various Image Quality Analysis(IQA) such as mean square error, peak signal to noise ratio(PSNR) as well as execution time has been compared.
AB - For the detection of tumors, vascular lesion and numerous other diseases, computed tomography(CT) and magnetic resource imaging (MRI) are considered as two vital medical imaging modal. However, various noises such as speckle noise, salt-pepper noise, etc. corrupt the imaging which makes the analysis of clinical data difficult. Therefore, to get a sharp and clear image for diagnostic purposes, medical image enhancement is must which removes noises and enhance the contrast of the image which helps in accurate diagnosis. In this work, brain MRI images are being enhanced through grey wolf optimization based logarithmic transformation. Logarithmic transformation increases the dynamic range value of the pixels with low intensity. GWO is a meta-heuristic approach that is used to maximize the fitness of the results. The outcome of the recommended methodology have been compared with the results of GA, PSO and CS optimizer. To measure the robustness of the technique various Image Quality Analysis(IQA) such as mean square error, peak signal to noise ratio(PSNR) as well as execution time has been compared.
KW - Cuckoo Search
KW - Genetic Algorithm
KW - Grey Wolf optimization
KW - Logarithmic Image processing
KW - MRI Image enhancement
KW - Particle Swarm Opti-mization
UR - http://www.scopus.com/inward/record.url?scp=85066316350&partnerID=8YFLogxK
U2 - 10.1109/ICRAIE.2018.8710393
DO - 10.1109/ICRAIE.2018.8710393
M3 - Conference contribution
AN - SCOPUS:85066316350
T3 - 3rd International Conference and Workshops on Recent Advances and Innovations in Engineering, ICRAIE 2018
BT - 3rd International Conference and Workshops on Recent Advances and Innovations in Engineering, ICRAIE 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference and Workshops on Recent Advances and Innovations in Engineering, ICRAIE 2018
Y2 - 22 November 2018 through 25 November 2018
ER -