TY - JOUR
T1 - A fusion of cuckoo search and multiscale adaptive smoothing based unsharp masking for image enhancement
AU - Maurya, Lalit
AU - Mahapatra, Prasant Kumar
AU - Kumar, Amod
N1 - Publisher Copyright:
Copyright © 2019, IGI Global.
PY - 2019/7/1
Y1 - 2019/7/1
N2 - Image enhancement means to improve the visual appearance of an image by increasing its contrast and sharpening the features. This article presents a fusion of cuckoo search optimization-based image enhancement (CS-IE) and multiscale adaptive smoothing based unsharping method (MAS-UM) for image enhancement. The fusion strategy is introduced to improve the deficiency of enhanced image that suppresses the saturation and over-sharpness artefacts in order to obtain a visually pleasing result. The ideology behind the selection of fusion images (candidate) is that one image should have high sharpness or contrast with maximum entropy and other should be high Peak Signal-to-Noise Ratio (PSNR) sharp image, to provide a better trade-off between sharpness and noise. In this article, the CS-IE and MAS-UM results are fused to combine their complementary advantages. The proposed algorithms are applied to lathe tool images and some natural standard images to verify their effectiveness. The results are compared with conventional enhancement techniques such as Histogram equalization (HE), Linear contrast stretching (LCS), Contrast-limited adaptive histogram equalization (CLAHE), standard PSO image enhancement (PSO-IE), Differential evolution image enhancement (DE-IE) and Firefly algorithm-based image enhancement (FA-IE) techniques.
AB - Image enhancement means to improve the visual appearance of an image by increasing its contrast and sharpening the features. This article presents a fusion of cuckoo search optimization-based image enhancement (CS-IE) and multiscale adaptive smoothing based unsharping method (MAS-UM) for image enhancement. The fusion strategy is introduced to improve the deficiency of enhanced image that suppresses the saturation and over-sharpness artefacts in order to obtain a visually pleasing result. The ideology behind the selection of fusion images (candidate) is that one image should have high sharpness or contrast with maximum entropy and other should be high Peak Signal-to-Noise Ratio (PSNR) sharp image, to provide a better trade-off between sharpness and noise. In this article, the CS-IE and MAS-UM results are fused to combine their complementary advantages. The proposed algorithms are applied to lathe tool images and some natural standard images to verify their effectiveness. The results are compared with conventional enhancement techniques such as Histogram equalization (HE), Linear contrast stretching (LCS), Contrast-limited adaptive histogram equalization (CLAHE), standard PSO image enhancement (PSO-IE), Differential evolution image enhancement (DE-IE) and Firefly algorithm-based image enhancement (FA-IE) techniques.
KW - Cuckoo Search Algorithm
KW - Histogram Equalization
KW - Image Enhancement
KW - Linear Contrast Stretching
KW - Multiscale Adaptive Smoothing Technique
KW - Particle Swarm Optimization Algorithm
KW - Unsharp Masking
UR - http://www.scopus.com/inward/record.url?scp=85070752253&partnerID=8YFLogxK
U2 - 10.4018/IJAMC.2019070108
DO - 10.4018/IJAMC.2019070108
M3 - Article
AN - SCOPUS:85070752253
SN - 1947-8283
VL - 10
SP - 151
EP - 174
JO - International Journal of Applied Metaheuristic Computing
JF - International Journal of Applied Metaheuristic Computing
IS - 3
ER -