Contrast Enhancement Technique Based on Lifting Wavelet Transform

Contrast enhancement is an indispensable process for improving the subjective quality and information content of an image. Adjustment in the relative brightness and darkness of an image is done in order to attain the same. This paper employs lifting wavelet transform (LWT) to enhance the image since...

Full description

Saved in:
Bibliographic Details
Published in:3D research 2018-12, Vol.9 (4), p.1-13, Article 50
Main Authors: Goyal, Megha, Bhushan, Bharat, Gupta, Shailender, Chawla, Rashmi
Format: Article
Language:English
Subjects:
3DR Express
Algorithms
Brightness
Computer Imaging
Darkness
Engineering
Image acquisition
Image enhancement
Image Processing
Image quality
Lasers
Optical Devices
Optics
Pattern Recognition and Graphics
Performance measurement
Photonics
Signal,Image and Speech Processing
Vision
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Contrast enhancement is an indispensable process for improving the subjective quality and information content of an image. Adjustment in the relative brightness and darkness of an image is done in order to attain the same. This paper employs lifting wavelet transform (LWT) to enhance the image since it is computationally inexpensive. The application of LWT results in the low and high frequency components. The former components that contain most of the information are enhanced using CLAHE algorithm while the latter are kept unchanged. In addition, a weighted average matrix which controls the level of enhancement is used to acquire the enhanced output image. To measure the efficacy, the proposed technique is implemented in MATLAB-2013 and evaluated on the basis of several performance metrics such as: absolute mean brightness error, average information content, Contrast Improvement Index, degree of entropy unpreserved, Structural Similarity Index, Universal Quality Index. From experiment, it can be observed that the results obtained from proposed algorithm are better than or comparable to other popular techniques in literature in almost all the parameters undertaken.
ISSN:2092-6731
2092-6731
DOI:10.1007/s13319-018-0201-z